State-of-the-art review of machine learning applications for bridge inspections

Abstract

Traditional bridge inspection methods, such as visual inspections and basic non-destructive tests, remain foundational but face limitations due to labor intensity and dependency on inspector expertise, often resulting in inconsistencies. Machine learning (ML) tools offer transformative solutions by enabling the analysis of large datasets to enhance damage detection accuracy, optimize maintenance schedules, and improve resource allocation. The objective of this study was to explore the integration of advanced inspection tools, such as Unmanned Aerial Vehicles (UAVs), digital imaging, and fiber optic sensors, with ML models to enhance data accuracy, decision-making, and inspection rating efficiency. A state-of-the-art review is conducted in this study on the application of ML techniques in bridge inspection and maintenance, encompassing 60 articles and reports published in the last decade. The results of this study show that ML’s ability to integrate advanced inspection tools to improve data accuracy, decision-making, and inspection efficiency. However, the existing challenges persist in data quality, model generalization, and the need for standardization approaches across diverse bridge conditions. The review provides insights into current methodologies, benefits, limitations, and future directions, emphasizing ML’s pivotal role in modernizing bridge health monitoring for a safer and more sustainable infrastructure network. The findings of this study are expected to assist transportation agencies in planning and operating predictive maintenance strategies, focusing on damage detection, maintenance optimization, and resource allocation.

Keywords

machine learning (ML)structural health monitoring (SHM)bridge inspection predictive maintenance unmanned aerial vehicles (UAVs)advanced inspection technologies damage detection

Introduction

Bridges are an important component of the United States’ transportation system, connecting communities, facilitating the movement of goods, and enabling societal advancements by overcoming natural and manmade obstacles like mountains, railroads, and rivers (FHWA, 2023). Any damage to bridges can cause economic losses, service disruptions, and safety concerns for the traveling public (Pratama et al., 2024; Xiang et al., 2023). In the United States, the federal highway office of bridges and structures offers technical guidance and national policies regarding the design, construction, inspection, assessment, administration, and preservation of the country’s inventory of highway bridges, tunnels, culverts, walls, and other ancillary structures (FHWA, 2023). Approximately 42,000 bridges in the United States are structurally deficient, many of which are nearing the end of their designed lifespan (Meyersohn, 2024). The average age of bridges across the country is 44 years. The $1.2 trillion federal infrastructure bill passed in 2021, which allocates $110 billion for roads, bridges, and key infrastructure projects, could provide funding for essential bridge upgrades. The existing transportation statistics highlight the critical need for investment to enhance climate resilience and ensure the reliability and safety of the country’s bridge network (Argyroudis et al., 2022).

Bridges are complex structures, consisting of several elements, including decks, girders, piers, and foundations (Bian et al., 2013; Ellobody, 2023). Various construction materials (e.g., steel, concrete) and methods (e.g., reinforced, prestressed) contribute to different durability levels and maintenance needs (Bian et al., 2013; Cakir et al., 2021; Ellobody, 2023). Decks provide a travel surface for vehicular traffic and are typically made of reinforced concrete (RC), steel, open grating, or wood (Han, 2024). Concrete provides higher durability, whereas steel provides the capacity for a lighter design with a much greater load capacity than would otherwise be possible (Han, 2024). Girders, generally composed of steel, RC, or prestressed concrete (PC) materials, support the deck and act as the primary load-bearing element of the bridge superstructure (Ellobody, 2023). Abutments, piers, and foundations constitute the substructure part of the bridge and are primarily constructed from RC material (Han, 2024; Stefanidou and Kappos, 2023).

Bridge inspection is essential for ensuring public safety and infrastructure longevity, assisting in identifying and addressing structural deficiencies such as concrete cracks, steel corrosion, excessive deformations, and other forms of degradation (Shahin et al., 2024). Effective inspection allows for timely maintenance and repairs, preventing catastrophic failures and extending bridge life (Boone, 2023). The American Road & Transportation Builders Association indicated that approximately one in three U.S. bridges requires repair or replacement and that 42,400 bridges are rated in poor condition (ARTBA, 2024). The annual cost of additional maintenance and reduced production due to unplanned bridge failures in the United States is estimated at $750 billion, underscoring the critical need for robust and effective bridge management techniques (Wedel and Marx, 2022).

Background—Conventional inspection methods

Conventional bridge inspection methods include visual inspection, manual measurement, and basic non-destructive tests (NDT) like sounding and chain-dragging (FHWA, 2022). These methods are valued for their simplicity, cost-effectiveness, and ability to quickly identify visible defects like cracks, corrosion, and delamination (Lee and Kalos, 2015). However, the effectiveness of conventional bridge inspection is limited by its dependence on the inspector’s expertise, which can lead to variability in results. It is also labor-intensive, time-consuming, and can miss internal or subsurface defects that are not visible on the surface, potentially allowing hidden structural issues to go undetected (Shahin et al., 2024).

The inherent limitations of the conventional inspection methods highlighted the need for more advanced inspection technologies to complement and enhance traditional methods, to ensure a more thorough assessment of bridge safety and integrity (Alabama DOT, 2021; California DOT, 2017). Advancements in inspection technology, including advanced NDT, high-resolution imaging, unmanned aerial vehicles (UAVs), and robotic platforms, have enhanced the efficiency, expediency, and accuracy of inspection, allowing for detailed assessments and continuous monitoring (ARTBA, 2024).

Background—Advanced inspection methods

Advancements in the fields of data analytics, machine learning (ML), and artificial intelligence (AI) have greatly enhanced bridge inspection and maintenance (Stevens et al., 2020; Zhang et al., 2023b). These methods have several advantages, such as allowing the automated analysis and processing of massive amounts of inspection data, providing early warning of potential issues (Gagliardi et al., 2021; Neves et al., 2017), and enabling the creation of maintenance prediction models that result in optimal resource allocation and failure prevention (Ye et al., 2021). Additionally, digital twins and Building Information Modeling (BIM) provide real-time dynamic visualizations to develop bridge health (Yang and Xia, 2023).

The synergy in improvements of hardware and software has resulted in exponential advancements in structural health monitoring (SHM) and their adoption in bridge inspection (Assaad and El-adaway, 2020; Gomez-Cabrera and Escamilla-Ambrosio, 2022). Predictive maintenance is a method in which the service life of a bridge is predicted based on inspection or diagnosis using an array of sensors to continuously collect real-time data. The sheer volume and complexity of the data collected can be difficult to interpret using traditional methods such as visual inspection (Zinno et al., 2023). ML models offer a promising solution to this problem (Gomez-Cabrera and Escamilla-Ambrosio, 2022).

Despite the progress made, the integration of ML techniques within bridge SHM remains limited, as many bridge authorities continue to rely on traditional methods (ARTBA, 2024). ML models such as ANNs, SVMs, and RF have been used in SHM, accounting for 27.84%, 17.72%, and 13.92% of existing applications respectively (Rashidi Nasab and Elzarka, 2023). Similarly, ML techniques: convolutional neural network (CNN) and long short-term memory (LSTM) networks are effective in processing complex datasets, detecting cracks, and predicting structural responses (Assaad and El-adaway, 2020; Catbas and Malekzadeh, 2016; Jeong et al., 2022; Meddaoui et al., 2024). The use of sensors, particularly temperature (60.71%) and vibration (46.42%) types, is integral to collecting real-time data for ML analysis (Catbas and Malekzadeh, 2016; Chalouhi et al., 2017; Darsono and Torbol, 2017).

Significance and objectives

The objective of this study was to provide a state-of-the-art review of advanced bridge inspection methods and highlight the advances in data acquisition and processing techniques, particularly the use of AI and ML tools to enhance damage detection accuracy and optimize maintenance schedules for bridges. Specifically, the design of this study focused on various ML algorithms and their efficiency in processing and forecasting bridge-related conditions and maintenance needs for transportation agencies. For this purpose, studies published in the last decade in journal and conference articles, technical reports, and documents from the federal highway administration (FHWA) and states’ departments of transportation (DOTs) were collected, analyzed, and summarized. This study analyzed and discussed the benefits, limitations, existing methods, and recent developments in SHM bridge infrastructure, with an emphasis on emerging ML models, including supervised, unsupervised, and reinforcement learning (RL). Essential information such as types of sensors used, data collection techniques, and the integration of AI and ML tools in analyzing and interpreting SHM data is discussed. Examples and applications of ML tools in bridge maintenance are given to assess their efficacy in enhancing the reliability, safety, and cost-effectiveness of bridge inspections. Research gaps and future trends were highlighted. Table 1 lists the common abbreviations and acronyms used in the article.

Table 1.

List of common abbreviations and acronyms.

Abbreviation	Definition
AANN	Auto-associative neural network
ADT	Average daily traffic
AI	Artificial intelligence
ANN	Artificial neural network
ANOVA	Analysis of variance
AR	Augmented reality
ARMA	Autoregressive moving average model
BD	Big data
BIM	Building information modeling
CART	Classification and regression tree
CCF	Cross-correlation function
CFRP	Carbon fiber–Reinforced plastic
CNN	Convolutional neural network
CSD	Cross spectral density
DBN	Deep belief network
DL	Deep learning
DNN	Deep neural networks
DOT	Department of transportation
DT	Decision tree
EOF	Environmental and operational factor
FA	Factor analysis
FDD	Frequency domain decomposition
FEM	Finite element method
FHWA	Federal highway administration
GA	Genetic algorithms
GKPCA	Greedy kernel principal component analysis
GMM	Gaussian mixture model
GP	Gaussian process
ICA	Independent component analysis
IoT	Internet of things
IRF	Impulse response function
k-NN	K-nearest neighbor
KPCA	Kernel principal component analysis
LDA	Linear discriminant analysis
LLE	Locally linear embedding
LQD-RKHS	Log quantity density of reproducing kernel Hilbert space
LR	Lasso regression
LRFR	Load and resistance factor rating
LSTM	Long short-term memory
ML	Machine learning
MLP	Multilayer perceptrons
MLR	Multiple linear regression
mRMR	Minimum redundancy feature selection
MSD	Mahalanobis squared distance
NB	Naive bayes
NBI	National bridge inventory
NDE	Non-destructive evaluation
NDT	Non-destructive testing
NN	Neural networks
PCA	Principal component analysis
PCR	Principal component regression
PdM	Predictive maintenance
PPCA	Probabilistic principal component analysis
PR	Pattern recognition
PSD	Power spectral density
PSI	Persistent scatterer interferometry
QDA	Quadratic discriminant analysis
QP	Quadratic programming
RDA	Regularized discriminant analysis
RF	Random forest
ROVs	Remotely operated vehicles
RRA	Robust regression analysis
SA	Stacked autoencoders
SFA	Slow feature analysis
SNR	Signal-to-noise ratio
SSI	Stochastic subspace identification
SVD	Singular value decomposition
SVDD	Support vector data description
SVM	Support vector machine
SVR	Support vector regression
UAV	Unmanned aerial vehicles
UmRnR	Unsupervised redundancy-maximum relevance
VR	Virtual reality
WIM	Weigh-in-Motion
WT	Wavelet threshold denoising
HHT	Hilbert-Huang transform
WSN	Wireless sensor network
SAR	Synthetic aperture radar
OCSVM	One-class support vector machine
RR	Ridge regression

Conventional and advanced bridge inspection methods

Several methods are employed in bridge inspection. Conventional methods, as outlined in the FHWA document “Methods and Equipment for Bridge Inspection,” include using binoculars, flashlights, and digital cameras for capturing visual data, dimensional measurements, and photographic records of cracks, corrosion, deformations, and overall structural health Figure 1 (Dues et al., 2021; Rossow et al., 2012). Underwater inspections utilize diving gear, underwater cameras, and ROVs to examine submerged elements, marine growth, and structural damage. NDT tools like hammer sounding and ultrasonic testing are used to detect delamination and voids, and assess concrete quality through physical samples. State DOTs have used conventional methods because they are well-established and easy to implement with the right expertise. These methods have been the foundation of bridge inspection programs for decades (Alabama DOT, 2021; California DOT, 2017).

Figure 1.

Sample of traditional bridge inspection methods.

However, these traditional approaches have limitations. They are labor-intensive and time-consuming, often requiring huge manpower and resources to cover large or complex structures (Civera et al., 2022; Zhang et al., 2023a). Additionally, the accuracy and reliability of these inspections are highly dependent on the skill and judgment of the inspectors, which can lead to inconsistencies in data and potential oversights, especially for internal or subsurface issues that are not visible during routine inspections (Civera et al., 2022; Zhang et al., 2023a). Additionally, the increase in demand for bridge inspections and workforce disruptions, such as that caused by the COVID-19 pandemic led several states to face shortages in human inspectors (Assaad and El-adaway, 2020; Ye et al., 2021).

Advanced bridge inspection tools include digital image correlation, laser scanning, UAVs, fiber optic sensors, and acoustic emission testing, Figure 2, (Bassier et al., 2022; Catbas and Malekzadeh, 2016; Wedel and Marx, 2022). These techniques provide continuous, high-resolution data that enhance monitoring capabilities by detecting strain distribution, temperature effects, active cracks, and internal defects that might go unnoticed with traditional methods (Gagliardi et al., 2021). For example, UAVs allow for the inspection of hard-to-reach areas without the need for extensive scaffolding or traffic disruptions, while fiber optic sensors enable real-time monitoring of critical structural health indicators (Haupt et al., 2019). For example, UAVs equipped with visual sensors collect images, videos, and GPS data, Figure 3 (Perry et al., 2020). The data is processed using Structure-from-Motion (SfM) techniques to create a 3D as-built bridge information model (AB-BrIM). ML algorithms are then used for bridge element segmentation and defect detection, identifying damages such as cracks and spalling. Defect information, including location and severity, is mapped to specific bridge elements in the model. The system offers a 3D visualization of damage, suitable for bridge rating according to AASHTO and FHWA standards (Perry et al., 2020).

Figure 2.

Sample of advanced bridge inspection tools.

Figure 3.

Process of using UAVs in bridge inspection.

Table 2 provides a comprehensive overview of both conventional and advanced methods for bridge inspection from FHWA (FHWA, 2022), categorizing each by type, equipment used, data acquired, inspected components, and inspection mechanism. Conventional methods, such as visual inspection, underwater inspection, hammer sounding, and coring, rely on direct human intervention and basic equipment to evaluate bridge conditions. Advanced methods, including laser scanning, UAVs, fiber optic sensors, and acoustic emission testing, integrate technology-driven approaches, such as Light Detection and Ranging (LiDAR), drones, and sensors, enabling high-resolution, continuous, and real-time monitoring. These advanced tools allow inspectors to obtain precise, detailed data on structural strain, temperature, geometry, and internal defects with reduced human intervention, especially in hard-to-reach or underwater areas. The table illustrates a shift towards more efficient, accurate, and data-intensive inspection practices, which support proactive bridge maintenance and enhance infrastructure resilience, particularly as environmental demands on infrastructure increase.

Table 2.

Conventional and advanced methods for bridge inspection and data inquiry (FHWA, 2022).

Type	Methods	Equipment	Data type	Acquired data	Components inspected
Conventional method	Visual inspection	Binoculars, flashlights, measuring tape, and a digital camera.	Visual data, dimensional measurements, and photographic records	Cracks, corrosion, deformations, and general conditions of structural elements	Deck, superstructure, substructure
	Underwater inspection	Diving gear (SCUBA or surface-supplied air), underwater cameras, clearwater boxes, and ROVs	Visual and photographic data, underwater video footage	Condition of submerged elements, marine growth, scour, and underwater structural damage	Substructure (piers, foundations)
	Hammer sounding	Hammer	Sound feedback	Identification of delamination or voids within concrete	Deck, piers, concrete elements
	Coring	Coring drills (pneumatic or hydraulic), core barrels	Physical samples	Concrete quality, presence of voids, and compressive strength	Deck, beams, piers, columns
Advanced method	Digital image correlation	High-resolution cameras, DIC software	Strain and displacement data	Full-field strain maps, deformation measurements	Deck, superstructure
	Laser scanning	LiDAR scanners	3D point clouds	Detailed geometric data, surface contours, and volumetric measurements	Entire structure
	UAVs	Drones equipped with cameras and sensors	High-resolution images and videos	Aerial view of the structure, hard-to-reach areas, and surface defects	Deck, superstructure, substructure
	Fiber optic sensors	Fiber optic cables, interrogators	Strain, temperature	Continuous monitoring data, strain distribution, and thermal effects	Superstructure, cables, beams
	Acoustic emission testing	Acoustic sensors	Acoustic signals	Detection of active cracks, crack growth, and internal defects	Superstructure, beams, deck

Condition assessment and load rating

Conventional bridge assessment methods primarily include visual inspections, component condition ratings, load rating analysis, NDE, and the condition state methodology (Arkansas DOT, 2022). Visual inspections are the primary method for bridge assessment, in which trained personnel visually examine the bridge for signs of wear, damage, and defects such as cracks and corrosion (Alabama DOT, 2021; Arkansas DOT, 2022; California DOT, 2017). These inspections are complemented by component condition rating, an empirical system ranging from 0 to 9 that evaluates the state of key bridge components, namely: deck, superstructure, and substructure, Table 3 (FHWA, 2022). The numerical rating is associated with a descriptive condition statement outlining the state of the member, type, and level of deterioration, action type, and schedule needed to rectify degradation issues. Ratings of five and above are typically indicative of members in good condition with no serious problems or imminent need for action. Lower ratings reflect various levels of degradation, some requiring immediate maintenance, repair, load posting, or road closure (FHWA, 2022).

Table 3.

FHWA bridge condition ratings based on 2022 NBIS guidelines.

Rating	Condition	Description
9	Excellent condition	No deficiencies or problems. The bridge is in a new condition with no signs of wear, damage, or deterioration.
8	Very good condition	Minor issues are present, but no significant problems. The bridge may have some cosmetic deterioration (like slight cracking), but nothing affecting the structural integrity.
7	Good condition	Minor problems are beginning to emerge, but all primary structural elements are sound. There might be slight cracking, weathering, or other minor damage not affecting functionality.
6	Satisfactory condition	Minor deterioration in structural elements, but the bridge remains in good overall condition. Some attention is needed, though the integrity of the bridge is still intact.
5	Fair condition	All main structural elements are still sound, but there are moderate issues such as section loss, cracks, spalling, or scour. These issues do not yet affect the overall load-bearing capacity but require maintenance soon.
4	Poor condition	More serious issues are present, such as advanced deterioration or section loss. Structural integrity could be affected if not repaired soon. This is a critical point where maintenance planning becomes urgent.
3	Serious condition	Significant deterioration or section loss has occurred. There may be fatigue cracks in steel or shear cracks in concrete, increasing the risk of failure without urgent repairs. Local failures are possible.
2	Critical condition	Advanced deterioration affects the load-bearing capacity of the bridge. The bridge may be closed or under observation for emergency repairs. Cracks and section loss are evident, and failure is imminent without intervention.
1	Imminent failure condition	Major structural problems are present. The bridge may show signs of movement or collapse. The bridge is often closed to all traffic at this point. Major structural intervention or demolition is required.
0	Failed condition	The bridge has failed or is beyond repair. The structure is closed to traffic, and it is unsafe to use. The bridge must be replaced.

Load rating analysis is another conventional evaluation method, assessing the bridge’s load-carrying capacity and structural integrity against permeant and transient traffic loads (Sun et al., 2022). The American Association of Transportation and Highway Officials (AASHTO) Manual for Bridge Evaluation (MBE) uses the following equation to determine the load rating factor (RF) for in-service bridges and culverts (AASHTO, 2017):

R F = \frac{C - (γ_{D C} D C + γ_{D W} D W \pm γ_{P} P)}{γ_{L L} (L L + {L L}_{l e g a l}) (1 + I M)}

(1)

where C represents the nominal capacity of the bridge component, and γ_DC, γ_DW, and γ_P are load factors for dead loads, wearing surfaces, and permanent loads, respectively. The live load effect (LL) and dynamic load allowance (IM), also known as the impact factor, account for the traffic and impact forces on the bridge. Two levels of ratings are typically used an Inventory Rating level, which denotes the bridge’s capacity for long-term service under regular conditions, and an operating rating, which represents the maximum load the bridge can handle on a temporary or occasional basis without risking structural integrity. A rating factor greater than one signifies the bridge can carry the load safely, while a factor less than one indicates the need for restrictions or repairs (WSDOT, 2024).

Machine learning techniques in bridge inspection

ML has emerged as a transformative tool in numerous engineering fields, including SHM and bridge maintenance (Civera et al., 2022; Favarelli and Giorgetti, 2021). Traditional methods of monitoring and maintenance such as visual inspections, NDT, and underwater inspections, involve periodic inspections and reactive measures, often resulting in high costs and potential safety risks due to unforeseen failures (Sun et al., 2020). By leveraging ML, engineers can predict and identify potential issues before they become critical, thereby optimizing maintenance schedules and improving overall bridge health management (Gomez-Cabrera and Escamilla-Ambrosio, 2022; Sun et al., 2020). ML algorithms can be categorized into supervised, unsupervised, and RL, each serving distinct purposes in the context of bridge monitoring and maintenance (Gomez-Cabrera and Escamilla-Ambrosio, 2022). In addition to the classic paradigms of supervised, unsupervised, and RL, current bridge inspection applications leverage semi-supervised and weakly supervised learning methods to mitigate the challenge of limited labeled data.

Applications categorized based on ML types

Supervised learning

Supervised learning algorithms such as SVM, ANNs, and RF have been adopted in SHM systems for their ability to learn from labeled data and make accurate predictions (Sonbul and Rashid, 2023). SVMs, powerful classification tools that find the optimal hyperplane separating different classes in the feature space, are effective in high-dimensional spaces and are used to classify structural states, distinguishing between healthy and damaged conditions (Noori Hoshyar et al., 2023). Random forests, which are ensembles of DT, improve predictive performance by averaging multiple trees’ outputs, making them robust against overfitting (Samatas et al., 2021). In bridge maintenance, random forests help in predicting degradation patterns and identifying factors contributing to structural wear (Samatas et al., 2021). DT works by splitting data into subsets based on feature values, providing interpretable results useful for decision-making in maintenance planning and identifying critical risk factors in bridge structures (Almarahlleh et al., 2024). Lastly, K-NN, which classifies data points based on the majority class of their nearest neighbors, is a straightforward algorithm used in SHM to compare new sensor readings with historical data, facilitating the identification of abnormal conditions and damage (Assaad and El-adaway, 2020).

Unsupervised learning

Unsupervised learning algorithms such as c-means, K-means, and GMMs play a crucial role in SHM by analyzing unlabeled data to detect patterns and anomalies (Gagliardi et al., 2021; Nick et al., 2015). Fuzzy c-means clustering allows data points to belong to multiple clusters with varying degrees of membership, providing flexibility in handling uncertainty in data and clustering structural conditions that may not have clear boundaries (Silva et al., 2016). K-means clustering partitions data into k-clusters by minimizing variance within each cluster and is employed in SHM to group similar structural states and identify common patterns in sensor data (Nick et al., 2015). GMMs, which assume that data is generated from a mixture of several Gaussian distributions, are effective for modeling complex data distributions in SHM and detecting subtle changes in structural behavior (Silva et al., 2016). Association analysis discovers interesting relationships and correlations between variables in large datasets, different types of sensor readings, and structural conditions. Finally, techniques like ICA, used in blind source separation, separate multivariate signals into additive, independent components, which is useful in SHM for isolating different sources of structural vibrations or identifying specific damage signatures from mixed sensor data (Malekloo et al., 2022).

Reinforcement learning

RL is another promising area in the application of ML for bridge maintenance and SHM (Zhou et al., 2022). RL involves training an agent to make a sequence of decisions by rewarding desirable outcomes and penalizing undesirable ones. This approach is useful for developing adaptive maintenance strategies where the agent learns optimal actions through trial and error (Zhou et al., 2022). For example, an RL model can be used to determine the best times for maintenance activities by balancing the cost of maintenance with the risk of bridge failure. Over time, the RL agent can improve its strategy by learning from the outcomes of past actions, leading to more efficient and cost-effective maintenance plans. The ability of RL to adapt to changing conditions and learn from continuous feedback makes it a powerful tool for enhancing the sustainability and safety of bridge infrastructure (Fan et al., 2021).

Recent studies have demonstrated the increasing value of RL in optimizing bridge inspection and maintenance strategies. For instance (Lei et al., 2025), developed an RL-based decision-making framework that dynamically adjusts inspection frequencies based on structural condition transitions and resource availability. Similarly (Lai et al., 2024), applied deep reinforcement learning (DRL) to evaluate bridge maintenance actions under budget constraints, adding improvements in lifecycle cost savings and reliability. Moreover (Lei et al., 2023), proposed a multi-agent RL approach for real-time coordination of inspection resources across a network of aging bridges, demonstrating the ability of RL not only to optimize performance but also to reduce carbon footprint and economic costs in long-term infrastructure management. These studies confirm the growing potential of RL as a state-of-the-art technique for predictive and adaptive infrastructure management.

Deep learning

DL has emerged as a transformative approach in bridge inspection and SHM due to its ability to automatically extract hierarchical features from complex, high-dimensional data. Among the most widely used architectures, CNNs have shown excellent performance in detecting surface-level defects such as cracks, spalls, and corrosion in image-based datasets. For instance, CNNs have been successfully trained to identify concrete damage with high precision using UAV-captured imagery and thermal images (Babu et al., 2023). In applications involving time-series sensor data (e.g., acceleration, strain), RNNs and their variants such as LSTM networks have been adopted to capture temporal dependencies and degradation trends (Li et al., 2023). With innovations such as transfer learning from architectures like GoogLeNet, and attention modules like SE blocks and hourglass-shaped depthwise separable convolutions, deep learning models are now capable of detecting fine-scale defects effectively and efficiently (Hajializadeh, 2023; Song et al., 2024). These techniques demonstrate potential for automating bridge inspection processes when paired with drone-based data collection.

Semi-supervised and weakly supervised learning

Semi-supervised learning uses a small set of labeled data with a larger set of unlabeled data. For example (Zhang et al., 2023b), created a semi-supervised Mask R-CNN architecture that employed inspector input to increase segmentation accuracy on UAV-captured bridge data while eliminating the requirement for manual annotation. In addition, weakly supervised learning provides alternative, efficient paradigms by using unrefined or imprecise labels, such as image-level tags or region-level annotations, rather than entirely pixel-level masks (Zhu and Song, 2020) developed a weakly supervised network for crack detection on asphalt concrete bridge decks, employing an autoencoder-based feature extractor, k-means clustering, and CNNs. Their model achieved a segmentation accuracy of 98% across various crack types under challenging lighting and environmental conditions.

Recent developments and literature reviews

Recent literature on ML applications in bridge monitoring and maintenance reveals a growing focus on leveraging advanced algorithms for SHM. Jia and Li (2023), conducted a comprehensive review of deep learning techniques in SHM, covering the period from 2017 to 2023. This study highlights the latest data, algorithms, applications, challenges, and emerging trends in the field. Similarly, Niyirora et al. (2022), provided a systematic review of intelligent damage diagnosis in bridges using vibration-based monitoring and ML, spanning from 2011 to 2022. Fan et al. (2021), focused on the application of ML in the design and inspection of reinforced concrete bridges, identifying resilient methods and new applications from 2011 to 2022.

Xu et al. (2023a), reviewed the SHM of concrete and steel bridges, offering insights into ML application choices over the extensive period from 2000 to 2023. Gomez-Cabrera and Escamilla-Ambrosio (2022), examined various ML techniques applied to SHM systems for both building and bridge structures, covering research from 2011 to 2022. Additionally, Sonbul and Rashid (2023), provided a systematic literature review on algorithms and techniques for SHM of bridges, analyzing studies from 2016 to 2023. These reviews underscore the advancements and ongoing research efforts in employing ML for enhancing the monitoring and maintenance of bridge infrastructures. They highlight the diverse algorithms and methodologies being explored, from traditional supervised learning techniques to more advanced deep learning approaches, all aimed at improving the accuracy, efficiency, and reliability of structural health assessments.

Previous reviews which focused on either data acquisition techniques or ML algorithmic development in isolation. However, this study provides an integrated overview that connects advanced data collection tools (e.g., UAVs, LiDAR, sensors) with ML models customized to different bridge components and data types (1D, 2D, 3D). It classifies ML applications based on bridge elements (e.g., decks, piers, cables, mechanical systems) and data techniques, highlighting practical use-cases for superstructure and substructure inspections. Furthermore, the study covers developing ML paradigms such as semi-supervised, weakly supervised, and deep learning, which have been underrepresented in previous reviews. By doing so, it provides a decision-focused framework for selecting appropriate ML tools based on dataset features, inspection targets, and component types, something that earlier evaluations lacked. These perspectives offer actionable guidance to both researchers and transportation agencies aiming to modernize their inspection and maintenance workflows using AI.

Summary of tools and techniques

ML models have been applied to bridge inspection and SHM, each offering unique strengths depending on the datatypes and inspection objectives. Table 4 illustrates the summary of various ML models used in bridge assessment and monitoring, their applications, strengths, and limitations. These tools support multiple tasks from defect classification and damage detection to predictive maintenance scheduling and hazards recognition.

Table 4.

Commonly used ML models for bridge assessment.

Model	Mathematical model	Common applications	Strengths	Limitations
Linear regression	y = β₀ + β₁x + ε	Predictive maintenance, bridge load prediction	Simple, interpretable, and fast to implement.	Assumes linearity, prone to overfitting with high dimensionality, sensitive to outliers.
Decision trees	Non-linear tree structure If−Else rules	Structural defect classification, material quality	Easy to interpret, can handle both categorical and numerical data.	Prone to overfitting, less robust, and sensitive to noise in data.
Random forest	Combination of multiple decision trees (bagging)	Bridge failure prediction, risk assessment	Reduces overfitting, handles large datasets, improves accuracy.	It can become computationally expensive, difficult to interpret due to the number of trees.
SVM	wᵀx + b = 0 separates classes with a hyperplane	Crack detection, classification tasks	Effective in high-dimensional spaces, works well with both linear and non-linear classification problems.	Requires careful tuning of parameters, difficult to interpret, sensitive to the choice of kernel function.
KNN	Distance-based classification d (p,q) = √Σ(pᵢ - qᵢ)²	Damage classification, anomaly detection	Simple, no training phase, good for small datasets.	Computationally intensive for large datasets, sensitive to noise and irrelevant features.
ANNs	Multi-layer perceptrons, backpropagation algorithm	Structural health monitoring, failure mode prediction	Flexible, capable of capturing complex non-linear relationships.	Requires large datasets, prone to overfitting, difficult to interpret, requires significant computational power.
CNNs	Feature extraction via convolution layers w∗x + b	Image-based crack detection, surface damage detection	Excellent for image recognition, automatically learn features from data.	Require large datasets, computationally expensive, complex to implement.
Reinforcement learning	Markov decision process (MDP), reward maximization	Autonomous drone inspection, optimal maintenance scheduling	Learns optimal policies, adaptable to dynamic environments.	Complex and time-consuming to train requires careful definition of reward functions.
GP	f(x)∼GP (m(x),k (x,x’)	Fatigue life prediction of shear connectors,	Uncertainty quantification, predictive modeling	Struggle with large datasets and are limited in extrapolating beyond observed data.

Table 5 presents a detailed overview of previous literature reviews regarding ML in bridge monitoring and maintenance. This compilation underscores the breadth and depth of research conducted in recent years, emphasizing the diverse methodologies and periods covered. The reviews span various aspects of ML applications, from deep learning approaches to traditional methods, highlighting the evolving nature of SHM techniques. Despite the number of literature reviews exploring the application of ML in SHM for bridges, there remains a critical need for a comprehensive synthesis that integrates these findings. The reviews by Fan et al. (2021) and Samatas et al. (2021), have focused on specific ML models like ANNs and SVMs within specific contexts. Moreover, while advanced models like CNNs and RNNs have been explored for their potential in damage detection and structural response prediction, the fragmented nature of these studies leaves a gap in understanding how these techniques can be applied across varying bridge types, and conditions (Jia and Li, 2023; Xu et al., 2023b). Additional work is needed to collect and analyze existing research, including that not synthesized in the published reviews, discuss emerging developments in automated inspection, data collection tools, data analysis, and ML models, and outline recommendations, research gaps, and research directions.

Table 5.

Previous literature reviews on ML applications in bridge inspection.

No.	Key findings		Future work recommended	Review period	Reference
No.	Data collection	Machine learning models	Future work recommended	Review period	Reference
1	Vibration signals and images dominate the research, making up 80% of the reviewed studies.	CNNs are the most used DL algorithms, accounting for 60% of studies, particularly for tasks like crack detection and structural damage classification.	Integrating SHM with digital twin technologies, enhancing data diversity and algorithm robustness.	2017–2023	(Jia and Li, 2023)
2	Vibration-based monitoring is a key technique for data collection in SHM. It uses parameters like natural frequencies and mode shapes, with sensors strategically placed to gather data efficiently.	ANN, SVM, and hybrid models like cuckoo Search-ANN, which have shown over 90% accuracy in some cases for damage localization and classification.	Optimizing sensor placement, integrating unsupervised learning, and leveraging advanced algorithms and big data to enhance real-world applicability.	2007–2022	(Niyirora et al., 2022)
3	Comprehensive datasets, including dynamic data for SHM and historical performance records, are critical for effective ML applications in bridge engineering.	ANN and CNN demonstrate high efficiency and accuracy in tasks like crack detection, damage classification, and strength prediction.	Developing more generalized and hybrid ML models to enhance adaptability, accuracy, and integration across bridge engineering applications.	2015–2022	(Fan et al., 2021)
4	Diverse data types, including sensors, discrete, imagery, and multimodal data, enhance SHM, with machine learning models address challenges like noise, and labor-intensive preparation.	CNNs are highly effective for image-based damage detection, such as crack identification, while RNNs are promising for regression tasks predicting structural responses based on time-series data.	Exploring transformer models for their efficiency with large, complex datasets and suggests incorporating physics-informed ML models that blend physical laws with data-driven methods.	2000–2023	(Xu et al., 2023a).
5	SHM systems rely on advanced sensing technologies like IoT and big data to capture high-dimensional, real-time data for improved damage detection and assessment.	DT ensemble methods achieved an accuracy of over 90% for damage detection and partial localization in structural elements.	Exploring population-based SHM where data from multiple structures can be pooled to support ML models across varied environments.	1993–2022	(Malekloo et al., 2022)
6	Vibration-based systems, particularly those using accelerometers, dominate SHM due to their cost-effectiveness and capability to generate reliable data.	CNNs, SVMs, and ANNs were found most effective ML techniques for SHM, especially when combined with advanced preprocessing techniques like WT and PCA.	Integrating hybrid models combining physics-based and data-driven approaches, and developing real-time SHM systems for large-scale infrastructure	2011–2022	(Gomez-Cabrera and Escamilla-Ambrosio, 2022)
7	SHM systems for bridges rely on diverse sensors like accelerometers, strain sensors, and optical fibers to monitor parameters such as corrosion, cracking, displacement, and vibration.	CNNs and ANNs are highly utilized for PdM tasks. CNNs excelling in image-based assessments and ANNs in predictive analytics.	Exploring a more integrative analysis of SHM systems to enhance decision-making and damage identification in bridge infrastructure.	2016–2023	(Sonbul and Rashid, 2023)
8	The most used sensors in PdM were temperature sensors (60.71%), vibration sensors (46.42%), and noise/acoustic sensors (32.14%), highlighting their critical role in PdM applications.	ANNs, SVMs, and RF are the top three algorithms, collectively accounting for 62% of the cases.	Improving explainability of ML models and integrating more advanced sensor technologies.	2011–2020	(Samatas et al., 2021)
9	Advanced sensors, drones, and IoT integration enable real-time, accurate, and comprehensive data collection for bridge monitoring, addressing accessibility and environmental challenges.	DL algorithms are crucial in damage detection and pattern recognition, offering robust solutions for analyzing large datasets and predicting structural health with high precision.	Focusing on enhancing sensor accuracy, addressing environmental variability in data, and exploring the full potential of DL in SHM systems.	2003–2023	(Zinno et al., 2023)
10	While advancements in sensor technologies, data integration frameworks, and emerging tools like UAVs have enhanced data collection for SHM, challenges persist in sensor limitations, data sparsity, environmental influences, and integrating heterogeneous and unstructured data sources effectively.	ML methods, especially supervised and unsupervised learning, enhance damage detection and condition assessment by addressing challenges like data variance, bias, and uncertainties through flexible and scalable models..	Integrating advanced big data and AI techniques, such as DL and real-time processing, to address uncertainties, improve damage detection accuracy, and enhance the practical application of SHM in real-world bridge systems.	2010–2020	(Sun et al., 2020)

Systematic literature review methodology

Research questions

The review was guided by the following research questions:

(1) How to use ML tools in bridge inspection/maintenance?

(2) When to use the ML methods in bridge inspection/maintenance?

(3) How to select an appropriate ML method (selection criteria)?

(4) What recommendations and trends can be extracted for future research in this area?

To address the research questions, a systematic search of the literature was performed using several academic databases, including IEEE Xplore, ScienceDirect, SpringerLink, and Google Scholar. The search terms included combinations of keywords such as “ML”, “predictive maintenance”, “bridges”, “structural health monitoring”, “substructure”, “superstructure”, “scour risk”, and “deformation monitoring”. The distribution of published papers on the research topic across various journals is shown in Figure 4, with Sensors and Automation in Construction being the leading sources of publications, followed by SHM and Transportation Research Procedia, indicating the widespread interest in diverse fields such as sensor technology, automation, and infrastructure monitoring.

Figure 4.

List of journals housing research on ML applications for bridge inspection.

Literature search and inclusion criteria

The inclusion criteria for this review were peer-reviewed journal articles and conference papers published between 2014 and 2024, written in English, and focusing on the application of ML techniques to the maintenance and monitoring of bridge infrastructures. The exclusion criteria were studies that do not explicitly focus on bridges, articles not available in full text, and non-peer-reviewed sources such as editorials, opinion pieces, and dissertations. The initial search identified many studies. Screening was conducted based on the title, abstract, and keywords to filter out irrelevant studies. This step ensured that only studies relevant to the research questions were retained. The remaining studies were then assessed for document type (journal papers) and publication year (2014–2024). Figure 5 illustrates the increase in the number of papers published on the topic of research over the years. There was a rise in the number of publications in 2021, 2022, and 2023, indicating growing interest and advancements in the field. The trend shows that the topic has gained substantial traction in recent years, with 2022 experiencing the highest number of published papers, followed closely by 2023. This trend highlights the relevance and the increasing focus of researchers on your area of study.

Figure 5.

Temporal distribution of surveyed articles related to ML applications in bridge inspection (n = 60).

Data extraction and synthesis process

For each selected study, the following data were extracted: title, authors, and year of publication; objectives and research questions; ML algorithms used; bridge components targeted (e.g., substructure, superstructure); key findings and conclusions; and identified research gaps. The checklist included criteria such as the clarity of research objectives, appropriateness of the methodology, robustness of the data analysis, and relevance of the findings. The extracted data were synthesized to provide a comprehensive overview of the state of research on ML applications in bridge maintenance. The synthesis involved categorizing studies based on the bridge components they addressed (e.g., substructure, superstructure); summarizing the ML techniques and models used in each study; identifying common themes, patterns, and trends in the research; highlighting findings and contributions of each study; and discussing the identified research gaps and suggesting areas for future research.

The findings of the literature review were reported in a structured format, aligned with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. The report includes an introduction outlining the background and importance of the review; a detailed description of the methodology used for the review; a results section presenting the synthesized findings; a discussion section highlighting the implications of the findings and identifying research gaps; and a conclusion summarizing the key insights and recommendations for future research. The PRISMA chart in Figure 6 illustrates the flow of studies through the review process.

Figure 6.

Flowchart showing procedure followed in designing the literature review.

Applications of ML tools by bridge elements and data type

The categorization of the studies was based on two primary criteria: the bridge elements monitored, and the data types and collection methods. The first category, bridge elements, includes both superstructure and substructure components. As shown in Figure 7, Superstructure elements encompass the parts of the bridge above the abutments, such as girders, beams, cables, and the bridge deck itself, which are critical for supporting traffic loads and ensuring the overall stability of the bridge. Substructure elements include the foundation, piers, and abutments, which support the superstructure and transfer loads to the ground. The second category pertains to the data types and the methods used to collect this data. Studies utilized a variety of data types, such as structural vibrations, strain measurements, and displacement data, collected through various methods including sensor networks, visual inspections, and remote sensing technologies. ML enhances the process by automating data analysis, identifying patterns, and detecting anomalies that may not be immediately visible (Favarelli and Giorgetti, 2021). It enables predictive maintenance by analyzing data like structural vibrations and strain measurements to forecast potential failures, making it an essential tool for transforming raw data into actionable insights (Wedel and Marx, 2022).

Figure 7.

Schematics showing key bridge anatomy.

The classification in this section is not intended to imply that ML tools are tied to one structural domain or material type, but it is used to place the data inputs, computational approaches, and decision-making frameworks that have proven effective in practice. For example, vibration-based ML models used for scour detection in foundations differ substantially from vision-based models applied to deck crack segmentation, even if both use CNNs. Similarly, the type of bridge (e.g., cable-stayed, arch, beam) and accessibility of components (e.g., bearing systems vs pier walls) shape both the data collection strategy and the ML algorithm selected. The tables and subsections that follow reflect this integrated understanding, highlighting how bridge type, material, damage visibility, and inspection goal collectively influence the choice of ML tools and data sources.

Studies are also classified based on bridge type to better understand how structural material and system complexity influence ML tool selection. Figure 8 illustrates the distribution of reviewed studies by bridge material type. This distribution reflects a research focus toward conventional bridge types (e.g., concrete and steel), which often provide more accessible datasets and standardized inspection protocols. However, studies on more complex or less common bridge types—such as cable-supported and movable bridges—highlight emerging needs for tailored ML models that accommodate unique inspection challenges, such as joint movement, bearing wear, and unpredictable element behavior. Bridge types have been incorporated as part of our classification, aiming to provide more context-sensitive insights into how ML methods are matched to structural behavior, data availability, and inspection requirements.

Figure 8.

Distribution of reviewed studies by bridge material type.

Bridge elements used in ML studies

Superstructure elements in bridges

The superstructure of a bridge refers to the portion of the bridge that supports the load and spans the obstacle the bridge is designed to cross, such as a road, river, or railway (Wedel and Marx, 2022). This includes various components such as beams, girders, decks, and cables. Understanding and maintaining these components are critical for the safety and longevity of bridges, and recent advancements in ML and data analysis have provided new tools and methods for this purpose (Bao and Li, 2021; Darsono and Torbol, 2017). The comparative performance of various ML algorithms in bridge damage detection is summarized in Table 6, where the best-performing algorithms, their accuracy, root mean square error (RMSE), and references are listed, providing an overview of the most effective approaches for predictive maintenance.

Table 6.

Articles on ML applications for maintenance of bridge superstructure elements.

No.	Bridge element	ML algorithms used	Best ML algorithm	Samples used for training/testing	Accuracy of best ML algorithm	Reference
1	T-beam	NN	NN	52,560/4032	99.64%	(Wedel and Marx, 2022)
1	T-beam	NN	NN	52,560/4032	RMSE = 0.340	(Wedel and Marx, 2022)
2	Decks	Decision tree, ANNs, kNNs, logistic regression, SVMs, random forest, XGBoost	XGBoost	14,938/3735	86.83%	(Rashidi Nasab and Elzarka, 2023)
3	Decks	ANNs	ANNs	19,269 with ratio 8:2	91.44%.	(Assaad and El-adaway, 2020)
3	Decks	KNNs	ANNs	19,269 with ratio 8:2	91.44%.	(Assaad and El-adaway, 2020)
4	Mechanical components such as the gearbox, motor, and rack and pinion systems	RRA	RRA	16,000 data points	-	(Catbas and Malekzadeh, 2016)
5	Beams	Multi-layer perceptron (MLP) neural network	MLP-NN	160 units in input layer, 75 units in hidden layer and 4 units in output layer	-	(Darsono and Torbol, 2017)
6	Decks	ANNs,	ANNs	Data from 300/100 train passages	Receiver operator characteristic (ROC) = 0.7786	(Chalouhi et al., 2017)
6	Decks	Gaussian processes	ANNs	Data from 300/100 train passages	Receiver operator characteristic (ROC) = 0.7786	(Chalouhi et al., 2017)
7	Girders	PCA, KPCA, GMM, ANN, OCCNN, OCCNN2	OCCNN2	2399/854	96%	(Favarelli and Giorgetti, 2021)
8	Beams	ANN combined with cuckoo search (CS), particle swarm optimization (PSO), and GA.	ANN combined with cuckoo search (ANN-CS)	8500 data for training in single damage, and 12,000 data for multiple damage scenarios	98.85%	(Tran-Ngoc et al., 2019)
9	Beams	CNNs,	CNNs	-	94.10%	(Bao and Li, 2021)
9	Beams	DNNs	CNNs	-	94.10%	(Bao and Li, 2021)
10	Decks	CNN compined with generative adversarial networks (Cycle-GAN)	CNN architecture combined with Cycle-GAN	1300 image for training/700 for testing	F-score = 0.870	(Munawar et al., 2022)
11	Girders and decks	Graph signal processing (GSP) and graph neural networks (GNNs)	T-GCN	2914 sequences of length 10 (10 × 100 ms)	RMSE = 0.380	(Bloemheuvel et al., 2021)
12	Beams	ANN	ANN	100	-	(Malekjafarian et al., 2019)
13	Decks	ANN, linear, lasso,	ANN	-	99.59%	(Hielscher et al., 2023)
13	Decks	Ridge	ANN	-	RMSE = 0.919	(Hielscher et al., 2023)
14	Decks	ANN	DT	-	-	(Stevens et al., 2020)
		Genetic algorithms k-NN
		Linear regression
		Deep learning networks
		Decision tree
15	Girders	RF	RF	52,560 samples after processing for first group and 48,672 for second group	RMSE = 0.794	(Wang et al., 2022)
		SVR
		Back-propagation neural network (BPNN)
		Univariate linear regression (ULR)
16	Decks	Logistic regression, gradient boosting, AdaBoost, random forest, extra trees,	CatBoost classifier	28,786 with ratio 4:1	96.66%	(Almarahlleh et al., 2024)
16	Decks	KNN, naive bayes, decision tree, LightGBM, CatBoost, and bagging.	CatBoost classifier	28,786 with ratio 4:1	96.66%	(Almarahlleh et al., 2024)
17	Beams	SVM based on misclassified data (SVM-MD), SVM based on hybrid kernels (SVM-S2 and SVM-SP), and SVM based on ensemble classifiers (SVM-EN).	SVM-MD	698 signals	87.20%	(Noori Hoshyar et al., 2023)
18	Beams and decks	WT, XGBoost	XGBoost	80% for training and 20% for testing	R² = 0.977	(Li et al., 2024)
19	Cables of the bridge	LSTM, linear regression and a backpropagation (BP) neural network	LSTM	432,000 data points throughout the year (75%/25%)	93.96%	(Li et al., 2023)
19	Cables of the bridge		LSTM	432,000 data points throughout the year (75%/25%)	MSE = 0.000000073461	(Li et al., 2023)
20	Bearings	SVM, linear discriminant analysis (LDA), DT, RF, and K-NN	DT	12,264 rows and 8 columns, with (70%/30%)	99.84%	(Cakir et al., 2021)
21	Decks	CNNs specifically ResNet50	ResNet50	(948 time series/474 time series)	97.50%	(Santaniello and Russo, 2023)
22	Top chords of the steel truss girder	Gradient boosting regression tree (GBRT), ANNs, SVM, DT, and RF	GBRT	1000 samples (80%/20%)	R² = 0.9180	(Sun et al., 2022)
22	Top chords of the steel truss girder		GBRT	1000 samples (80%/20%)	RMSE = 0.0755 × 10^-6	(Sun et al., 2022)
23	Beams	CNN, GoogLeNet	GoogLeNet	2100 simulated acceleration signals from 100 different vehicle speeds and 18 different damage scenarios at 3 different locations on the bridge. (70%/30%)	Above 80%	(Hajializadeh, 2023)
24	Girders, slabs, anchor bolts	CNN and gated recurrent units (GRU)	CNN and GRU with the attention mechanism	422,290 images with 504,923 explanatory texts, collected from inspections of 3118 bridges. The dataset was split as: 2500 bridges for training, 500 bridges for validation, and 118 bridges for testing	92.90%	(Chun et al., 2022)
25	Beams	NNs and genetic algorithms (GA)	NN	Around 1000 measured bridges (80%/10%/10% validation)	85.76%	(Ye et al., 2021)
26	Decks	YOLO, pyramid scene parsing network (PSPNet)	CR-YOLO	About 5000 images	90.88%	(Zhang et al., 2022)
27	Decks	XGBoost	XGBoost	152,714 data points after preprocessing, split into (80%/20%) sets.	91%	(Kong et al., 2022)
27	Decks	XGBoost	XGBoost		F1 score of 0.95	(Kong et al., 2022)
28	Simple supported beam	NNs	NNs	20,000 data entries split into (14000 training/3000 testing/3000 validating)	93.37%	(Chiaia and De Biagi, 2020)
28	Simple supported beam	NNs	NNs		RMSE = 0.470	(Chiaia and De Biagi, 2020)
29	Decks	ResNet50 and mask R-CNN	Mask R-CNN	3549 images	94%	(Zhang et al., 2023a)
30	Shear connectors	Linear regression, DT, SVR, bagged trees (BT), Gaussian process regression (GPR), and ANN	Gaussian process regression (GPR)	694 samples	RMSE = 0.84	(Roshanfar et al., 2024)
31	Beams	GMM, mahalanobis-based	Mahalanobis-based algorithm	100 dynamic impulse/30 samples	96%	(Figueiredo et al., 2022)
32	Fixed-end beams	One-class support vector machine (OCSVM)	OCSVM	500/1500 data points	95%	(Baba and Kondoh, 2022)
32	Fixed-end beams	K-means clustering	OCSVM	500/1500 data points	95%	(Baba and Kondoh, 2022)
33	Decks, girders, bracing	ANNs	ANN	150/150 train passages	99.30%	(Neves et al., 2017)

Beams and girders are critical components of the bridge superstructure, providing the primary means of support and load distribution (Tran-Ngoc et al., 2019). Beams typically run horizontally and are designed to carry vertical loads, while girders are the main horizontal supports that often carry the loads transferred from the beams (Noori Hoshyar et al., 2023). Accurate prediction of the effects of temperature and other environmental factors on these elements is essential for their maintenance. Wang et al. (2022), developed advanced methods to predict the cross-sectional effective temperature and vertical temperature difference in flat steel box girders of long-span bridges using a combination of on-site environmental data and ML techniques. This study demonstrated that the multifactor RF model outperforms traditional single-factor models, improving predictive performance by 60%–90% (Wang et al., 2022). Additionally, studies have utilized ML for damage detection in beams, such as the work by Darsono and Torbol (2017), who applied deep learning techniques for damage detection in bridge structures, showcasing the potential for high accuracy in identifying structural weaknesses.

The bridge deck is the surface layer that carries traffic and distributes loads to the underlying structural elements (Kong et al., 2022). Deterioration of bridge decks can affect the overall health of the bridge (Almarahlleh et al., 2024). ML approaches have been utilized to enhance the prediction of bridge deck deterioration (Althaqafi and Chou, 2022). For instance Rashidi Nasab and Elzarka (2023), developed a framework for optimizing ML algorithms to predict bridge deck conditions in Ohio. Their study demonstrated that ensemble ML algorithms, such as random forest and XGBoost, predicted deck conditions more accurately than single models when using “optimal” features. Assaad and El-adaway 2020, introduced a computational data-driven asset management system that evaluates and predicts bridge deck conditions using ANNs and KNNs, achieving a prediction accuracy of 91.44%. Similarly, Almarahlleh et al. (2024), utilized hyperparameter optimization to develop accurate ML models for classifying bridge deck conditions and predicting deterioration trajectories.

In cable-stayed and suspension bridges, cables are key structural elements that bear loads and provide stability (Zhou et al., 2022). The fundamental frequency of these cables, influenced by environmental factors such as temperature and wind, is crucial for maintenance. Predicting temperature variations accurately helps in planning maintenance activities and ensuring the structural integrity of the bridge (Zhou et al., 202); Li et al., 2023; Li et al., 2023), developed a real-time intelligent prediction model using LSTM networks to model the non-linear relationships between temperature changes and the fundamental frequency of bridge cables. This model outperformed traditional linear regression and backpropagation neural network models, providing more precise predictions with reduced error rates (Li et al., 2023).

Movable bridges, such as drawbridges, have mechanical components like gearboxes, motors, and rack and pinion systems that require constant monitoring to ensure proper operation. Catbas and Malekzadeh (2016), introduced a ML-based algorithm for processing massive data collected from the mechanical components of movable bridges such as temperatures, vibration data from the accelerometers, and acoustic data from microphones. This approach uses robust regression analysis for long-term operational monitoring and has shown satisfactory performance in detecting common damage scenarios such as leakage and insufficient oil in the gearbox, as well as bolt removal from the rack and pinion system. This study highlights the potential of ML techniques in automating the monitoring and maintenance of mechanical components in movable bridges (Catbas and Malekzadeh, 2016).

Additionally, Darsono and Torbol (2017), found that key components of bridges, such as the deck, superstructure, substructure, and mechanical elements in movable bridges, are vulnerable to damage such as cracks, corrosion, deformation, and mechanical wear. Data for damage detection was collected using vibration sensors, strain gauges, and displacement sensors, with sensor networks transmitting real-time data. This data was processed using techniques like modal analysis, finite element modeling, and autoregressive models. ML, particularly deep neural networks trained with historical data, was used to predict and classify damage. The ML process involved data preprocessing, feature extraction, and model training through backpropagation, allowing for early damage identification and more effective maintenance strategies.

Similarly, Chalouhi et al. (2017), found that the primary type of damage evaluated was related to structural anomalies in the railway bridge, such as changes in stiffness and integrity of the bridge components. These anomalies could be caused by issues such as material degradation, fatigue cracks, or other structural failures that affect the overall performance of the bridge. The study focused on detecting deviations in the bridge’s response to train crossings, where abnormalities in acceleration measurements indicated potential damage or degradation in the bridge’s structure. This study confirmed the potential of ML techniques in real bridge health monitoring by effectively detecting structural anomalies. The data was collected using accelerometers and thermocouples installed on the bridge. Pre-processing of the acceleration data involves extracting features related to the crossing train, such as speed and number of axles. ANNs and Gaussian processes were then trained on data from the bridge’s reference condition to predict accelerations under various operational and environmental conditions. The model was validated using data from the San Michele Bridge in Italy, where the algorithm successfully detected structural anomalies by identifying discrepancies between predicted and measured responses (Chalouhi et al., 2017).

Substructure elements in bridges

Recent studies have leveraged ML techniques to improve the monitoring and maintenance of bridge substructure elements, addressing the limitations of traditional methods in terms of efficiency, accuracy, and cost. Traditional methods for predicting scour depth at bridge piers primarily relied on empirical or semi-empirical formulas, such as the HEC-18 formula commonly used in the United States (Chou and Nguyen, 2022; Dong et al., 2020). These methods were based on physical models that incorporate hydraulic parameters like flow depth, velocity, and sediment characteristics (Dong et al., 2020). However, these approaches often struggle to account for the complex interaction between various environmental factors, leading to less accurate predictions of scour depth in real-world scenarios (Dong et al., 2020). To enhance prediction accuracy, modern studies have integrated ML techniques with advanced sensors for data acquisition (Dong et al., 2020). Common sensors include GPR, accelerometers, and GPS, which are used to monitor structural deformation and displacements (Chou and Nguyen, 2022). Additionally, remote sensing technologies, such as SAR, have been employed to track surface deformations over time (Gagliardi et al., 2021). These sensors, combined with ML models like CNNs and DBNs, allow for more accurate and dynamic predictions of scour depth (Dong et al., 2020). In particular, studies utilizing PSI for satellite-based assessments have demonstrated the potential for large-scale, efficient monitoring of infrastructure (Gagliardi et al., 2021).

Data collection for scour prediction and bridge monitoring primarily involved both laboratory-controlled experiments and field data. For instance, Chou and Nguyen (2022), utilized a laboratory dataset containing 151 instances of scour depth measurements from various experimental setups, focusing on different pier geometries and hydraulic conditions. This data was instrumental in developing and validating ML models like the LSSVR, RBFNN, and FBI algorithms. Additionally, field data was collected from 79 bridge sites across 17 U.S. states, providing real-world environmental conditions, such as varying water velocities, sediment types, and pier structures (Chou and Nguyen, 2022). The combination of field and laboratory data allows for comprehensive analysis and prediction. In another study, PSI was used to collect satellite-based data over a 3-year observation period, which helped monitor deformation patterns on bridge structures (Gagliardi et al., 2021). Advanced sensors such as GPR, accelerometers, and GPS were employed to gather real-time data on pier displacement and scour depth (Gagliardi et al., 2021).

Different ML models have been applied to address various aspects of substructure monitoring. The use of SVM, RF, and XGBoost for scour risk assessment emphasizes the importance of selecting appropriate algorithms based on accuracy and precision needs (Wang et al., 2023). Additionally, clustering algorithms in SHM, such as the AOMA for masonry arch bridges, highlight the versatility of ML in adapting to specific structural challenges (Civera et al., 2022). Unsupervised clustering techniques like k-means have proven effective in analyzing large datasets from remote sensing technologies (Gagliardi et al., 2021). Table 7 lists the existing research on the use of ML applications in the inspection of bridge piers.

Table 7.

Articles on ML applications for maintenance of bridge piers.

No.	ML algorithms used	Best ML algorithm	Samples used for training/testing	Accuracy of best ML algorithm	Reference
1	SVM, RF, XGBoost	XGBoost	208/40	92%	(Wang et al., 2023)
2	SSI, AOMA using clustering techniques for modal identification	AOMA	1:2 scale model	-	(Civera et al., 2022)
3	k-means	k-means	196 persistent scatterers	-	(Gagliardi et al., 2021)
4	Kriging model and BPNN	Kriging model	43 samples with 8:2 ratio	99.96%	(Xu et al., 2023b)
5	Linear regression, BPNN, GA-BP neural network, CNN, DBN	DBN model	534 with 8:2 ratio	Correlation coefficient (R) = 0.826 RMSE = 0.391	(Dong et al., 2020)
6	RR, LR, KNN, SVR, CART, RF, GBT, and XGBoost	XGBoost	18,106 pier specimens with 8:2 ratio	99.50% RMSE = 2.82 × 10^-4	(Wakjira et al., 2022)
7	Least squares SVR, radial basis function NN, metaheuristics-optimized stacking system (MOSS)	MOSS	562 with 8:2 ratio	92.70% RMSE = 0.021865	(Chou and Nguyen, 2022)

Data types used in ML studies

In recent years, the integration of advanced tools and data types has enhanced bridge monitoring and maintenance, particularly through the application of ML techniques. The comprehensive categorization of these tools includes sensors, databases, and UAVs, each contributing unique and essential data for thorough bridge condition analysis. As shown in Table 8, sensors play a crucial role in capturing a wide range of physical measurements. Thermometers, for instance, record temperatures and humidity, providing critical insights into the thermal impact on bridge materials (Favarelli and Giorgetti, 2021; Hielscher et al., 2023; Wedel and Marx, 2022). Solar radiation sensors measure the amount of solar radiation affecting the bridge, aiding in the assessment of weathering effects (Wedel and Marx, 2022). Additionally, microphones collect acoustic data through sound signals, which can indicate structural anomalies such as cracks or faults (Catbas and Malekzadeh, 2016; Nick et al., 2015). Precipitation sensors measure the amount of precipitation impacting the bridge, allowing for the correlation of weather conditions with structural health (Wedel and Marx, 2022). Strain gauges provide displacement values by measuring the strain on the bridge structure in both vertical and horizontal directions, offering data on stress and deformation (Bloemheuvel et al., 2021; Almarahlleh et al., 2024). Ultrasonic anemometers measure wind speed and direction through ultrasonic sound waves, which are vital for assessing dynamic loading on bridges (Li et al., 2023; Sun et al., 2022). Accelerometers capture acceleration data to detect vibrations and movements (Darsono and Torbol, 2017; Santaniello and Russo, 2023).

Table 8.

Summary of Tools and Data Types Extracted from Previous Studies on bridge health monitoring.

Tool (no. of papers)	Type	Data type	Data measured	References
Sensors (22)	Ammeters	Electrical data	Monitoring amperage levels helps detect indicators of improper functioning in the motor, such as high current draw	(Catbas and Malekzadeh, 2016)
	Thermometers	Temperatures and humidity	Air temperature - bridge temperature	(Favarelli and Giorgetti, 2021; Hielscher et al., 2023; Li et al., 2023; Silva et al., 2016; Zhou et al., 2024)
	Solar radiation sensors	Solar radiation	Amount of solar radiation impacting the bridge.	(Wedel and Marx, 2022)
	Microphones	Acoustic data	Sound signals can capture unusual sounds, like grinding which may show problems such as parts being out of place, or wear and tear in gears, bearings, or the rack and pinion system.	(Cakir et al., 2021; Nick et al., 2015; Noori Hoshyar et al., 2023)
	Strain gauge	Displacement values, vibration	Measure the strain on the bridge structure in both vertical and horizontal directions	(Baba and Kondoh, 2022; Chiaia and De Biagi, 2020; Santaniello and Russo, 2023; Sun et al., 2022; Tang et al., 2023)
	Anemometers	Ultrasonic sound waves	Measured three-dimensional wind speeds to evaluate aerodynamic loading.	(Li et al., 2024; Sun et al., 2022; Wang et al., 2022)
	Accelerometers	Acceleration data	Measure the vibrations to identify mode shapes and analyze the bridge’s dynamic responses to assess its overall structural health and load distribution.	(Chalouhi et al., 2017; Bloemheuvel et al., 2021; Favarelli and Giorgetti, 2021; Civera et al., 2022; Hajializadeh, 2023)
Surveys and inspections (15)	Annual inspections conducted by state and local transportation agencies	FHWA (NBI)	Age of the bridge, structure length, roadway width, deck width, design load, ADT, percent daily trucks, Degree’s skew, structure type, latitude and longitude coordinates, year built	(Althaqafi and Chou, 2022; Assaad and El-adaway, 2020; Jaafaru and Agbelie, 2022; Kong et al., 2022; Liu and El-Gohary, 2022)
Surveys and inspections (15)		Bridge inspection application system, managed by INDOT	Cracked and non-cracked images. Sealed and non-sealed cracks. Normal cracks and map cracks (for unsealed images).	(Zhang et al., 2023a)
Surveys and inspections (15)	Annual inspections conducted by state and local transportation agencies	Inspection reports (regional bridge database)	Route codes, bridge names, bridge dimensions (width and length), climate conditions, owner details, and traffic data ADT and ADTT	(Ye et al., 2021)
		Asset-wise Ohio department of transportation	Asset-wise also contains information such as ADT, age of the bridge, area of the deck, deck width, deck geometry, and conditions of core elements of the bridge including superstructure, substructure, and deck condition	(Rashidi Nasab and Elzarka, 2023)
		Inspection reports data from the French national railway company (SNCF).	Flow type, riverbed slope, flood flow, pier shape, foundation type, scour history	(Wang et al., 2023)
	Laboratory, field tests	Experimental data (push-out tests, direct shear tests, and beam tests)	Shear strength of shear connectors, compressive strength of concrete, shear connectors stress range, diameter of shear connectors.	(Roshanfar et al., 2024)
	Laboratory, field tests	Laboratory experiments, field data collection	Pier diameter, grain size of bed material, flow velocity, flow depth, scour depth, pier shape factor, the skew of the pier, gradation of bed material.	(Chou and Nguyen, 2022)
	Digital camera	(2D) images	Cracks, corroded steel reinforcements, deteriorated concrete, honeycombs, moisture spots, pavement degradation, and shrinkage cracks.	(Cardellicchio et al., 2023; Chun et al., 2022; Zhang et al., 2022)
UAV (2)	Digital camera	High resolution images	Simple cracks, hairline cracks, and artificial marking cracks.	(Munawar et al., 2022; Perry et al., 2020)
UAV (2)	Lidar	3D point-cloud data	Generated using structure-from-motion techniques, which help create a 3D model of the bridge. This model is used for further analysis and damage mapping.	(Perry et al., 2020)
Radar (1)	Multi-temporal interferometric synthetic aperture	High-resolution X-Band SAR images	Structural displacements and subsidence.	(Gagliardi et al., 2021)
Finite element analysis (4)	Structural response data	Structural displacement, energy transformation, and deformation due to ship-pier collisions.	Density, young’s modulus	(Neves et al., 2017; Wakjira et al., 2022; Xu et al., 2023b; Yang and Xia, 2023)
			Poisson’s ratio, yield strength
			Failure strain, unconfined compression strength.

Databases such as NBI and the FHWA compile extensive bridge attributes, including age, structure length, roadway width, deck width, design load, and ADT (Kong et al., 2022; Zhang et al., 2023b). The AssetWise Ohio Department of Transportation database integrates typical bridge attributes with information on deck width, deck geometry, and core element conditions of the superstructure and substructure (Ohio DOT, 2021; Rashidi Nasab and Elzarka, 2023). Additionally, inspection reports from the French National Railway Company (SNCF) offer detailed structural condition insights, including flow type, riverbed slope, flood flow, pier shape, foundation type, and scour history (Wang et al., 2023). In addition to that, many U.S. states have developed their own systems to manage and assess the structural integrity of bridges. For example, Alabama DOT uses advanced techniques such as drones, ultrasonic testing, and ground-penetrating radar to inspect its bridges and has allocated federal funds to repair structurally deficient structures (Alabama DOT, 2021). Alaska DOT, facing unique geographic challenges, relies on the AASHTOWare Bridge Management system, which compiles extensive data from bridge inspections and helps prioritize rehabilitation projects across its vast, remote areas (Alaska DOT, 2023). California’s bridge inspections, overseen by Caltrans, incorporate both visual assessments and advanced technologies such as drones and AI-based imagery analysis to enhance the speed and accuracy of inspections (California DOT, 2017).

While many ML applications in bridge inspection focus on 1D (sensor signals) and 2D (image-based) data, recent advancements in 3D data processing and ML have expanded bridge inspection. For example, (Xia et al., 2022), demonstrated effective semantic segmentation of LiDAR-derived bridge point clouds, enabling automated identification of structural components, and applied a semantic segmentation algorithm that extracts local geometric features (e.g., curvature, density) to differentiate between elements such as decks, girders, piers, and railings. Similarly, (Yang et al., 2022), combined PointNet with GNN to classify bridge elements (such as deck, pier, abutment, bearing, etc.) from a dataset consisting of full-scale 3D scans of concrete bridges captured with terrestrial laser scanning with over 99% accuracy, showcasing scalable digital twin capabilities. Moreover (Bolourian et al., 2023), developed a surface-normal-enhanced PointNet++ model to detect and segment 3D defects—cracks and spalls—with high reliability (≥92% recall). These studies collectively illustrate the promise of 3D deep learning architectures (e.g., PointNet, 3D-CNN, GNN) for comprehensive bridge modeling, structural segmentation, and defect detection, thereby enabling more holistic and geometry-aware inspection strategies.

Critical insights from literature review

Data collection

The findings from the review of various tools and data types used in bridge monitoring and inspection (shown in Table 8) highlight a comprehensive approach to SHM. Different sensors, such as ammeters, thermometers, and strain gauges, are employed to gather electrical data, temperature, humidity, displacement, and vibration data, which are crucial for identifying improper performance, temperature effects, and structural strain. Solar radiation sensors and ultrasonic anemometers further contribute by measuring environmental factors like solar radiation, wind speed, and direction. Accelerometers and microphones capture essential vibration and acoustic data to assess the integrity of bridge structures. In addition to these sensors, advanced methods such as UAVs and LiDAR are used to collect high-resolution images and 3D point-cloud data, facilitating detailed visual inspections and damage mapping. Radar systems, specifically synthetic aperture radar, measure structural displacements and subsidence, providing insights into large-scale changes. Moreover, field surveys, annual inspections, and sophisticated systems like AssetWise and the Bridge Inspection Application System (BIAS) are integral for gathering and managing critical data on bridge age, design load, traffic, and structural condition. Finite Element Analysis is also widely utilized to simulate structural responses, offering detailed insights into potential displacement and deformation under various conditions. These tools and data types form a robust framework for detecting damage, monitoring environmental influences, and ensuring the longevity of bridges.

Conventional methods are more widely used, papers focusing on traditional approaches such as strain gauges, accelerometers, annual inspections, and digital cameras for 2D images. These techniques have been established for decades and continue to play a critical role in bridge inspection due to their reliability and widespread adoption. In contrast, advanced methods, including the use of UAVs, LiDAR, Radar, and FEA, are represented in only seven papers. This indicates a gradual shift towards integrating modern technologies, such as 3D modeling and UAVs, into bridge inspections. While conventional methods remain dominant, the growing application of advanced techniques reflects the industry’s evolving approach to more efficient and accurate damage detection and structural monitoring.

Bridge components

The analysis of component types in the context of ML for predictive maintenance of bridges reveals a pronounced focus on superstructure components (Shown in Figure 9). As illustrated in the pie chart, most of the studies emphasize the superstructure elements, indicating their critical importance in bridge maintenance research. In contrast, the substructure components receive less attention, with an even smaller fraction of studies addressing both superstructure and substructure elements. This highlights the research gap which indicates the relative underrepresentation of substructure components in predictive maintenance studies. There is a pressing need to expand the scope of ML applications to include substructure maintenance. This gap identifies a critical area for future research, a balanced focus between superstructure and substructure elements for comprehensive bridge maintenance.

Figure 9.

Distribution of focus on bridge components, for research related to ML applications in bridge inspection.

Furthermore, a portion of the studies conducted on superstructure components are dedicated to bridge decks, beams & girders. However, mechanical components, such as gearboxes, motors, and rack and pinion systems, along with bridge bearings and bridge cables, are less frequently addressed. This disparity indicates several research gaps that need to be addressed to develop a comprehensive predictive maintenance strategy. Furthermore, bridge bearings, which play a crucial role in accommodating movements and forces within the bridge structure, are also underrepresented in the research. The lack of focus on these elements may lead to incomplete maintenance strategies, potentially overlooking critical stress points that can affect the bridge’s overall performance and longevity.

ML tools

Tables 6 and 7 show that there is an increasing use and success of specific ML algorithms in bridge maintenance, particularly XGBoost and ANNs. XGBoost has consistently demonstrated high accuracy in both substructure and superstructure applications, making it a prominent choice for predictive maintenance tasks. Its proven performance across various components, such as bridge piers and decks, highlights its effectiveness in handling large datasets while delivering accurate predictions (Kong et al., 2022; Li et al., 2024; Wang et al., 2023). Additionally, a key trend is the rise of hybrid models, which combine multiple ML techniques to boost performance. For example, ANNs integrated with evolutionary algorithms like PSO, and CNNs combined with GANs, have shown remarkable improvements in prediction accuracy (Munawar et al., 2022). These hybrid approaches capitalize on the strengths of different algorithms, resulting in more robust models capable of handling complex data (Munawar et al., 2022; Tran-Ngoc et al., 2019).

DT is also prominent, with six occurrences in the superstructure and one in the substructure, followed by Gradient Boosting (7 times), SVMs (8 times), and Random Forest (7 times). These algorithms effectively perform predictive maintenance, damage detection, and structural assessment tasks for components such as decks, beams, girders, and piers. Ensemble methods like Gradient Boosting and Random Forest provide high accuracy and robustness, making them valuable tools for bridge health monitoring.

Another notable observation is the variety of data types used in these models, including large-scale numerical datasets, dynamic signals, and image-based data. This shift toward integrating diverse data sources could enhance the comprehensiveness and accuracy of bridge health assessments. By incorporating various data inputs into advanced ML models, future research could create more precise and effective predictive maintenance systems, leading to better-informed decision-making in bridge health monitoring. The current studies in ML for bridge maintenance have several limitations that need to be addressed to enhance the effectiveness and applicability of these technologies. For instance, many studies primarily rely on specific data types or limited data sources. The reliance on a narrow range of sensor data or environmental factors can lead to incomplete models that do not fully capture the complexities of real-world bridge environments, restricting the generalizability of the findings across different bridge types and conditions.

As shown in Figure 10, to effectively select the appropriate ML tool for inspecting specific bridge components or conditions, several factors should be considered. These include the type of data, the desired performance level, the size of the dataset, and the computational efficiency of the algorithm. Recent studies have demonstrated the utility of advanced deep learning architectures in bridge inspection tasks. For example, ResNet50 has been widely used for image classification tasks such as crack detection, achieving high accuracy up to 97.5% (Santaniello and Russo, 2023). On the other hand, Cycle-GAN is typically applied in image-to-image translation tasks, such as enhancing low-quality inspection images or generating synthetic training data under varying lighting conditions (Munawar et al., 2022). These models serve different functions and are selected based on the specific needs of the inspection pipeline. In addition, sensor-based vibration monitoring, often used for cables and girders, benefits from temporal sequence models like LSTM networks, which effectively capture time-dependent patterns and achieve high accuracy, such as 93.96% in specific cases (Li et al., 2023).

Figure 10.

The most appropriate algorithms used with different bridge elements.

Selecting an ML tool for bridge inspections depends on many factors, such as the data types and the dataset size. Detailed performance metrics of ML algorithms and selection criteria are provided in the Supplemental Material section for readers who are interested in learning more about this topic.

Current studies emphasize short-term predictions and immediate damage detection, with less focus on long-term maintenance planning and lifecycle cost analysis. This short-term focus can lead to maintenance strategies that are reactive rather than proactive, missing opportunities for more efficient and cost-effective long-term solutions. There is a need for more robust validation and testing of ML models in diverse and challenging environments to ensure their reliability and effectiveness in varied real-world applications. There is a lack of standardized methodologies for integrating diverse data sources and ML techniques, resulting in varied performance and reliability across different studies. The application of ML models often faces challenges related to data quality, sensor accuracy, and environmental noise, which can affect the predictive accuracy of these models. Additionally, while some studies have demonstrated the potential of advanced algorithms like neural networks and RL, their practical implementation in real-world scenarios is often limited by computational complexity and the need for extensive training data.

Conclusions and recommendations

This study conducts a systematic review of the application of ML techniques in the inspection and maintenance of bridges. The analysis encompassed 60 key studies published between 2015 and 2024. The studies were categorized based on bridge elements monitored, data types and collection methods employed, and ML algorithms used for data analyses and prediction.

The study finds that NNs, SVMs, and RF are the most widely applied ML algorithms in bridge SHM, accounting for 27.84%, 17.72%, and 13.92% of applications, respectively. These algorithms have shown high effectiveness in detecting structural damage, predicting maintenance needs, and improving overall bridge safety. The research emphasizes that ML models have enabled a shift from reactive maintenance practices to proactive approaches, allowing for more efficient maintenance planning and reduced costs due to fewer unexpected failures. However, despite the progress, the study concludes that more work is needed to address challenges such as enhancing data quality, improving model generalization, and ensuring that diverse bridge conditions are represented in the models.

Practical implications

The use of sensors and ML algorithms enables continuous monitoring, allowing for timely interventions that can prevent major structural issues, thus ensuring the longevity and reliability of bridge systems. The study offers several recommendations for action items in industry and transportation agencies. First, there should be a concerted effort to standardize data collection and integration methodologies to ensure the reliability of ML models across different bridge systems. This includes developing industry-wide protocols for sensor installation, data collection, and data sharing. Second, the industry should invest in advanced sensor technologies and data analytics tools to facilitate continuous monitoring and real-time data processing. Implementing state-of-the-art sensors and robust data infrastructure will enhance the precision and utility of the collected data.

Third, training and capacity-building programs should be established to equip engineers and maintenance personnel with the necessary skills to implement and manage ML-based SHM systems effectively. These programs should cover the fundamentals of ML, data analysis, and the practical aspects of integrating these technologies into existing maintenance workflows. Fourth, ML results should be connected with decision-making systems, such as Bridge Management Systems (BMS), to enable automated inspection and repair predictions. Finally, model performance must be continuously monitored and evaluated, with expert comments used to adjust the models over time. For example, ML models trained in historical inspection, inventory, and environmental data exceed traditional methods in predicting future bridge conditions or deterioration rates. Predicting time needed to failure, condition rating, or risk scores can be integrated into BMS optimization tools (e.g., PONTIS, AASHTOWare BrM) to assist with life-cycle cost analysis and intervention timing. Agencies can start by exporting the existing BMS data, training ML models externally, and then bringing the results back into the system to help with scheduling and managing the expenses. Another integration can be performed over time by using software to connect live BMS data to real-time ML services, allowing for automated updates and dynamic decision-making. This solution enables agencies to move from reactive maintenance to proactive, data-driven asset management, while ensuring ML insights are accessible, interpretable, and embedded within existing workflows.

An example of a project done by (Kulhandjian, 2023), it integrates drones equipped with both infrared and high-resolution optical cameras, along with an onboard minicomputer running ML algorithms to perform fully autonomous inspections of roads and potentially bridges. The system demonstrated an accuracy of 84.6% using optical images and 95.1% using thermal images in detecting roadway defects and incorporates real-time navigation and defect localization without human intervention. Although the prototype was primarily tested on roads due to airspace restrictions, the modular framework has clear potential for bridge inspection automation. This approach represents a major step toward scalable, cost-effective infrastructure monitoring using AI-powered aerial systems (Turkan and Xu, 2019) developed a comprehensive inspection framework combining UAVs, computer vision, and Bridge Information Modeling (BrIM). In their case study on an Oregon bridge, UAV-captured imagery was processed to detect surface-level defects like cracks, which were then automatically mapped to corresponding 3D BrIM elements, enabling centralized, cloud-based access to up-to-date inspection data for all stakeholders. This integration not only improved inspection accuracy and efficiency but also allowed inspection outputs to be directly linked with lifecycle decision modules in the BMS. Together, these examples illustrate how transportation agencies can harness ML-driven technologies to automate data collection, improve condition assessments, and enhance data-informed maintenance planning within modern BMS frameworks.

Recommendations and future research

For future research, the study recommends expanding the focus to include both superstructure and substructure elements to develop a more comprehensive maintenance strategy. Current research has focused on superstructure components, leaving a critical gap in the understanding and maintenance of substructure elements like foundations, piers, and scour protection measures. Additionally, exploring innovative data fusion techniques that combine different types of sensor data, such as vibrations, strain, temperature, and environmental factors, will provide a more holistic understanding of bridge health. Further research should also address the challenges related to data quality, sensor accuracy, and environmental noise to enhance the generalizability and reliability of ML models.

Also, hybrid modeling approaches, which integrate ML algorithms with physics-based simulations, can improve forecast interpretability and reliability, particularly when the data is limited or noisy. In addition, multi-sensor data fusion methods, such as combining visual imagery, LiDAR, acoustic emission, vibration, and thermal monitoring, can provide a more complete picture of structural behavior. This multi-source integration has the potential to overcome the limitations of single-source datasets, allowing for more accurate and robust prediction models.

Finally, emerging sensor technologies such as fiber optic sensors, UAV-based LiDAR, multispectral imaging, and digital twins show a promise for improving data collection during bridge inspections. These techniques can increase the quality, resolution, and frequency of data input into ML models, resulting in more accurate and timely assessments. However, real-world implementation presents obstacles such as data diversity, environmental instability, scalability, and interoperability among sensor systems. It is necessary to explore the generalization capability of ML models across various bridge types, geographic locations, and environmental conditions. Most current models are created and validated on isolated datasets, limiting their adaptability. Future research should emphasize the generation of standard datasets that cover a variety of structural types and deterioration changes. Advanced methods, including transfer learning, domain adaptation, and meta-learning, can also be used to increase the scalability and resilience of ML applications in real-world bridge management systems.

Supplemental Material

Supplemental Material - State-of-the-art review of machine learning applications for bridge inspections

Supplemental Material for State-of-the-art review of machine learning applications for bridge inspections by Amr Ashmawi, Phuong Nguyen, and Akram Jawdhari in Advances in Structural Engineering

Footnotes

ORCID iDs

Amr Ashmawi

Phuong Nguyen

Funding

The authors received no financial support for the research, authorship, and/or publication of this article.

Declaration of conflicting interests

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Data Availability Statement

The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.*

Supplemental Material

Supplemental material for this article is available online.

References

AASHTO (2017) AASHTO LRFD Bridge Design Specifications. American Association of State Highway and Transportation Officials (AASHTO). Available at: https://bit.ly/3qDFdFv

Alabama DOT (2021) Alabama manual for bridge inspection. Available at: https://www.dot.state.al.us/publications/Maintenance/pdf/Bridge/BridgeInspectionManual.pdf

Alaska DOT (2023) Alaska bridges and structures manual.

Almarahlleh

Liu

Abudayyeh

(2024) Predicting concrete bridge deck deterioration: a hyperparameter optimization approach. Journal of Performance of Constructed Facilities 38(3): 04024009.

Althaqafi

Chou

(2022) Developing bridge deterioration models using an artificial neural network. Infrastructures 7(8): 101.

Argyroudis

Mitoulis

Chatzi

, et al. (2022) Digital technologies can enhance climate resilience of critical infrastructure. Climate Risk Management 35: 100387.

Arkansas DOT (2022) Bridge inspection manual. Available at: https://www.ardot.gov/wp-content/uploads/2022/05/ARDOT_BIM_20220507.pdf

ARTBA (2024) Bridge report. Available at: https://artbabridgereport.org/

Assaad

El-adaway

(2020) Bridge infrastructure asset management system: comparative computational machine learning approach for evaluating and predicting deck deterioration conditions. Journal of Infrastructure Systems 26(3): 04020032.

10.

Baba

Kondoh

(2022) Damage evaluation of fixed beams at both ends for bridge health monitoring using a combination of a vibration sensor and a surface acoustic wave device. Engineering Structures 262(May): 114323.

11.

Babu

Khandagale

Shinde

, et al. (2023) Enhancing infrastructure safety: a UAV-based approach for crack detection. Engineering Journal 27(12): 11–22.

12.

Bao

(2021) Machine learning paradigm for structural health monitoring. Structural Health Monitoring 20(4): 1353–1372.

13.

Bassier

Vermandere

De Winter

(2022) Linked building data for construction site monitoring: a test case. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences V-2-2022(2): 159–165.

14.

Bian

Bai

Kang

, et al. (2013) A review of durability research of concrete bridge. Applied Mechanics and Materials 423–426: 1132–1136.

15.

Bloemheuvel

van den Hoogen

Atzmueller

(2021) A computational framework for modeling complex sensor network data using graph signal processing and graph neural networks in structural health monitoring. Applied Network Science 6(1): 97.

16.

Bolourian

Nasrollahi

Bahreini

, et al. (2023) Point cloud–based concrete surface defect semantic segmentation. Journal of Computing in Civil Engineering 37(2): 04022056.

17.

Boone

(2023) Quality over quantity: today’s bridge & tunnel inspection. Available at: https://csengineermag.com/quality-over-quantity-todays-bridge-tunnel-inspection/

18.

Cakir

Guvenc

Mistikoglu

(2021) The experimental application of popular machine learning algorithms on predictive maintenance and the design of IIoT based condition monitoring system. Computers & Industrial Engineering 151(October 2020): 106948.

19.

California DOT (2017) Caltrans bridge element inspection manual. Available at: https://dot.ca.gov/-/media/dot-media/programs/maintenance/documents/f0009170-elem-man-a11y.pdf

20.

Cardellicchio

Ruggieri

Nettis

, et al. (2023) Physical interpretation of machine learning-based recognition of defects for the risk management of existing bridge heritage. Engineering Failure Analysis 149(March): 107237.

21.

Catbas

Malekzadeh

(2016) A machine learning-based algorithm for processing massive data collected from the mechanical components of movable bridges. Automation in Construction 72: 269–278.

22.

Chalouhi

Gonzalez

Gentile

, et al. (2017) Damage detection in railway bridges using machine learning: application to a historic structure. Procedia Engineering 199: 1931–1936.

23.

Chiaia

De Biagi

(2020) Archetypal use of artificial intelligence for bridge structural monitoring. Applied Sciences (Switzerland) 10(20): 7157.

24.

Chou

Nguyen

(2022) Scour depth prediction at bridge piers using metaheuristics-optimized stacking system. Automation in Construction 140(May): 104297.

25.

Chun

Yamane

Maemura

(2022) A deep learning-based image captioning method to automatically generate comprehensive explanations of bridge damage. Computer-Aided Civil and Infrastructure Engineering 37(11): 1387–1401.

26.

Civera

Mugnaini

Zanotti Fragonara

(2022) Machine learning-based automatic operational modal analysis: a structural health monitoring application to masonry arch bridges. Structural Control and Health Monitoring 29(10): 1–23.

27.

Darsono

Torbol

(2017) Bridges damage detection using deep learning. Advances in Structural Engineering and Mechanics, [Preprint].

28.

Dong

Sun

, et al. (2020) Artificial intelligence for predicting local scour depth around piers based on dimensional analysis. Journal of Coastal Research 111(sp1): 21–25.

29.

Dues

Kent

Matlock

(2021) New techniques elevate bridge inspection options. Available at: https://www.gannettfleming.com/blog/new-techniques-elevate-bridge-inspection-options/

30.

Ellobody

(2023) Chapter 2 - Nonlinear material behavior of the bridge components. In: Ellobody (ed) Finite Element Analysis and Design of Steel and Steel-Concrete Composite Bridges. Second Edition. Butterworth-Heinemann, pp. 53–118.

31.

Fan

Chen

, et al. (2021) Machine learning applied to the design and inspection of reinforced concrete bridges: resilient methods and emerging applications. Structures 33(June): 3954–3963.

32.

Favarelli

Giorgetti

(2021) Machine learning for automatic processing of modal analysis in damage detection of bridges. IEEE Transactions on Instrumentation and Measurement 70: 1–13.

33.

FHWA (2022) Bridge inspector’s reference manual (BIRM). Available at: https://www.fhwa.dot.gov/bridge/nbis/pubs/nhi23024.pdf

34.

FHWA (2023) Bridges & structures. Available at: https://www.fhwa.dot.gov/bridge/

35.

Figueiredo

Moldovan

Alves

, et al. (2022) Smartphone application for structural health monitoring of bridges. Sensors 22(21): 8483.

36.

Gagliardi

Tosti

Bianchini Ciampoli

, et al. (2021) Monitoring of bridges by MT-InSAR and unsupervised machine learning clustering techniques, 16.

37.

Gomez-Cabrera

Escamilla-Ambrosio

(2022) Review of machine-learning techniques applied to structural health monitoring systems for building and bridge structures. Applied Sciences (Switzerland) 12(21): 10754.

38.

Hajializadeh

(2023) Machine-learning-based bridge damage detection using train-borne measurements. Proceedings of the Institution of Civil Engineers - Smart Infrastructure and Construction 177: 1–15.

39.

Han

(2024) Study on steel and concrete composite structure bridge. Highlights in Science, Engineering and Technology 106: 305–310.

40.

Haupt

Akinlolu

Raliile

(2019) Applications of digital technologies for health and safety management in construction. In: 8th World Construction Symposium, Colombo, Sri Lanka, 8–10 November, 2019, pp. 88–97.

41.

Hielscher

Khalil

Virgona

, et al. (2023) A neural network based digital twin model for the structural health monitoring of reinforced concrete bridges. Structures 57(February): 105248.

42.

Jaafaru

Agbelie

(2022) Erratum: bridge maintenance planning framework using machine learning, multi-criteria decision analysis and evolutionary optimization models (automation in construction (2022) 141, (S0926580522003338), (10.1016/j.autcon.2022.104460)). Automation in Construction 143(September): 104585.

43.

Jeong

Seo

Wacker

(2022) UAV-aided bridge inspection protocol through machine learning with improved visibility images. Expert Systems with Applications 197: 116791.

44.

Jia

(2023) Deep learning for structural health monitoring: data, algorithms, applications, challenges, and trends. Sensors (Basel, Switzerland) 23(21): 8824.

45.

Kong

Zhang

, et al. (2022) Bridge deck deterioration: reasons and patterns. Transportation Research Record 2676(7): 570–584.

46.

Kulhandjian

(2023) AI-Based bridge and road inspection framework using drones.

47.

Lai

Dong

Andriotis

, et al. (2024) Synergetic-informed deep reinforcement learning for sustainable management of transportation networks with large action spaces. Automation in Construction 160(April 2023): 105302.

48.

Lee

Kalos

(2015) Bridge inspection practices using non-destructive testing methods. Journal of Civil Engineering and Management 21(5): 654–665.

49.

Lei

Dong

Frangopol

(2023) Sustainable life-cycle maintenance policymaking for network-level deteriorating bridges with a convolutional autoencoder–structured reinforcement learning agent. Journal of Bridge Engineering 28(9): 04023063.

50.

Lei

Dong

Frangopol

(2025) Integration of inspection and monitoring data for RL-enhanced sustainable life-cycle management of infrastructure networks. Structure and Infrastructure Engineering 21(0): 1288–1302.

51.

Zhao

Yue

, et al. (2023) Real-time intelligent prediction method of cable’s fundamental frequency for intelligent maintenance of cable-stayed bridges. Sustainability 15(5): 4086.

52.

Meng

, et al. (2024) Quantifying the impact of environment loads on displacements in a suspension bridge with a data-driven approach. Sensors 24(6): 1877.

53.

Liu

El-Gohary

(2022) Deep learning–based analytics of multisource heterogeneous bridge data for enhanced data-driven bridge deterioration prediction. Journal of Computing in Civil Engineering 36(5): 04022023.

54.

Malekjafarian

Golpayegani

Moloney

, et al. (2019) A machine learning approach to bridge-damage detection using responses measured on a passing vehicle. Sensors (Switzerland) 19(18): 4035.

55.

Malekloo

Ozer

AlHamaydeh

, et al. (2022) Machine learning and structural health monitoring overview with emerging technology and high-dimensional data source highlights. Structural Health Monitoring 21: 1906–1955.

56.

Meddaoui

Hachmoud

Hain

(2024) Advanced ML for predictive maintenance: a case study on remaining useful life prediction and reliability enhancement. The International Journal of Advanced Manufacturing Technology 132(1): 323–335.

57.

Meyersohn

(2024) 1 in every 13 bridges in America is in ‘poor’ condition. Thousands could collapse from a collision, Available at: https://www.cnn.com/2024/03/30/business/americas-bridges-climate-infrastructure/index.html

58.

Munawar

Hammad

AWA

Waller

, et al. (2022) Modern crack detection for bridge infrastructure maintenance using machine learning. Human-Centric Intelligent Systems 2(3–4): 95–112.

59.

Neves

González

Leander

, et al. (2017) Structural health monitoring of bridges: a model-free ANN-Based approach to damage detection. Journal of Civil Structural Health Monitoring 7(5): 689–702.

60.

Nick

Asamene

Bullock

, et al. (2015) A study of machine learning techniques for detecting and classifying structural damage. International Journal of Machine Learning and Computing 5(4): 313–318.

61.

Niyirora

Masengesho

, et al. (2022) Intelligent damage diagnosis in bridges using vibration-based monitoring approaches and machine learning: a systematic review. Results in Engineering 16(October): 100761.

62.

Noori Hoshyar

Rashidi

, et al. (2023) Proposed machine learning techniques for bridge structural health monitoring: a laboratory study. Remote Sensing 15(8): 1984.

63.

Ohio DOT (2021) Bridge inspection notes in assetwise. Available at: https://www.transportation.ohio.gov/wps/wcm/connect/gov/a41c8953-6d17-47cf-a3e0-346d39e93758/Addendum+3_Inspection+Comments+Requirement_eff.+02262021.pdf?MOD=AJPERES&CONVERT_TO=url&CACHEID=ROOTWORKSPACE.Z18_M1HGGIK0N0JO00QO9DDDDM3000-a41c8953-6d17-47cf-a3

64.

Perry

Guo

Atadero

, et al. (2020) Streamlined bridge inspection system utilizing unmanned aerial vehicles (UAVs) and machine learning. Measurement: Journal of the International Measurement Confederation 164: 108048.

65.

Pratama

Handayani

Dwiretnani

, et al. (2024) Analisa Penilaian Kondisi Jembatan Sarolangun Batang Tembesi Dengan Metode Bridge Manajemen System (BMS). Jurnal Talenta Sipil 7(1): 330.

66.

Rashidi Nasab

Elzarka

(2023) Optimizing machine learning algorithms for improving prediction of bridge deck deterioration: a case study of Ohio bridges. Buildings 13(6): 1517.

67.

Roshanfar

Ghiami Azad

Forouzanfar

(2024) Predicting fatigue life of shear connectors in steel-concrete composite bridges using artificial intelligence techniques. Fatigue and Fracture of Engineering Materials and Structures 47(3): 818–832.

68.

Rossow

IMP

Retired

(2012)FHWA bridge inspector’s manual section 1 - Bridge inspection programs table of contents, 472.

69.

Samatas

Moumgiakmas

Papakostas

(2021) Predictive maintenance-bridging artificial intelligence and IoT. In: 2021 IEEE World AI IoT Congress, AIIoT 2021, Seattle, WA, USA, 10–13 May 2021, pp. 0413–0419.

70.

Santaniello

Russo

(2023) Bridge damage identification using deep neural networks on time–frequency signals representation. Sensors 23(13): 6152.

71.

Shahin

Chen

Maghanaki

, et al. (2024) Improving the concrete crack detection process via a hybrid visual transformer Algorithm. Sensors 24: 3247.

72.

Silva

Santos

Figueiredo

, et al. (2016) A novel unsupervised approach based on a genetic algorithm for structural damage detection in bridges. Engineering Applications of Artificial Intelligence 52: 168–180.

73.

Sonbul

Rashid

(2023) Algorithms and techniques for the structural health monitoring of bridges: systematic literature review. Sensors 23(9): 4230.

74.

Song

Sun

Yuan

(2024) Autonomous identification of bridge concrete cracks using unmanned aircraft images and improved lightweight deep convolutional networks. Structural Control and Health Monitoring 2024: 7857012.

75.

Stefanidou

Kappos

(2023) Integrating the foundation component into seismic fragility analysis of bridges. Soil Dynamics and Earthquake Engineering 164: 107627.

76.

Stevens

Lydon

Marshall

, et al. (2020) Identification of bridge key performance indicators using survival analysis for future network-wide structural health monitoring. Sensors (Switzerland) 20(23): 1–15.

77.

Sun

Shang

Xia

, et al. (2020) Review of bridge structural health monitoring aided by big data and artificial intelligence: from condition assessment to damage detection. Journal of Structural Engineering 146(5): 04020073.

78.

Sun

Santos

Caetano

(2022) Data-driven prediction and interpretation of fatigue damage in a road-rail suspension bridge considering multiple loads. Structural Control and Health Monitoring 29(9): 1–18.

79.

Tang

Wang

(2023) Understanding the effects of service innovation capability on firm performance in AEC industry: mediating role of business model. Engineering Construction and Architectural Management 32: 893–911.

80.

Tran-Ngoc

Khatir

De Roeck

, et al. (2019) An efficient artificial neural network for damage detection in bridges and beam-like structures by improving training parameters using cuckoo search algorithm. Engineering Structures 199(August): 109637.

81.

Turkan

(2019) Bridge sutructural inspections using bridge information modeling (BrIM) and unmanned aerial vehicles (UAVs). Available at: https://www.pactrans.org/

82.

Wakjira

Rahmzadeh

Alam

, et al. (2022) Explainable machine learning based efficient prediction tool for lateral cyclic response of post-tensioned base rocking steel bridge piers. Structures 44(April): 947–964.

83.

Wang

Zhang

, et al. (2022) Temperature prediction of flat steel box girders of long-span bridges utilizing in situ environmental parameters and machine learning. Journal of Bridge Engineering 27(3): 04022004.

84.

Wang

Reiffsteck

Chevalier

, et al. (2023) Machine learning (ML) based predictive maintenance policy for bridges crossing waterways. Transportation Research Procedia 72: 1037–1044.

85.

Wedel

Marx

(2022) Application of machine learning methods on real bridge monitoring data. Engineering Structures 250(July 2021): 113365.

86.

WSDOT (2024) WSDOT bridge design manual.

87.

Xia

Yang

Chen

(2022) Automated semantic segmentation of bridge point cloud based on local descriptor and machine learning. Automation in Construction 133(September 2021): 103992.

88.

Xiang

Liu

, et al. (2023) The Origin and Development of Bridges BT. In: 70 Years of China’s Bridges. Springer Nature Singapore, pp. 1–17.

89.

Forde

, et al. (2023a) Concrete and steel bridge structural health monitoring—insight into choices for machine learning applications. Construction and Building Materials 402(August): 132596.

90.

Cao

Wang

, et al. (2023b) A novel machine learning-based framework for predicting impact force in ship-bridge pier collisions. Ocean Engineering 285(P1): 115347.

91.

Yang

Xia

(2023) Advancing bridge construction monitoring: AI-based building information modeling for intelligent structural damage recognition. Applied Artificial Intelligence 37(1): 2224995.

92.

Yang

del Rey Castillo

Zou

, et al. (2022) Automated semantic segmentation of bridge components from large-scale point clouds using a weighted superpoint graph. Automation in Construction 142(July): 104519.

93.

Xiaoming

Peng Wang

(2021) Artificial intelligence based structural assessment for regional inspection information.

94.

Zhang

Qian

Tan

(2022) Automated bridge surface crack detection and segmentation using computer vision-based deep learning model. Engineering Applications of Artificial Intelligence 115(May): 105225.

95.

Zhang

Eric Wogen

Chu

, et al. (2023a) Machine-supported bridge inspection image documentation using artificial intelligence. Transportation Research Record 2677(5): 720–736.

96.

Zhang

Wogen

Liu

, et al. (2023b) Machine-aided bridge deck crack condition state assessment using artificial intelligence. Sensors 23(9): 4192.

97.

Zhou

Yuan

Yang

, et al. (2022) An advanced multi-agent reinforcement learning framework of bridge maintenance policy formulation. Sustainability (Switzerland) 14(16): 10050.

98.

Zhou

Peng

(2024) Cost optimization of graphene oxide-modified ultra-high-performance concrete based on machine learning methods. Tongji Daxue Xuebao/Journal of Tongji University 52(7): 1018–1023.

99.

Zhu

Song

(2020) Weakly supervised network based intelligent identification of cracks in asphalt concrete bridge deck. Alexandria Engineering Journal 59(3): 1307–1317.

100.

Zinno

Haghshenas

Guido

, et al. (2023) The state of the art of artificial intelligence approaches and new technologies in structural health monitoring of bridges. Applied Sciences (Switzerland) 13(1): 97.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.12 MB