Data-driven prediction of CIMS signal intensity for pesticide detection via dibromomethane reagent using machine learning techniques

Abstract

This research introduces a model utilizing machine learning for forecasting Chemical Ionization Mass Spectrometry (CIMS) signal intensity in pesticide detection, using dibromomethane (DBrMe) as a reagent. Accurate detection of pesticides is crucial for agricultural safety and compliance. The model explores the relationship between signal intensity and ten molecular features, including molar mass, COO, N-O, N-N, N-S, C-C, S, Cl, P, and pesticide concentration in DBrMe (ppm), using algorithms like Decision Tree, AdaBoost, Random Forest, and Ensemble Learning. A dataset of 2460 samples was used for training and validation. Among the features, pesticide concentration had the strongest influence, followed by N-O, COO, and molar mass. SHAP analysis confirmed these trends, while a Leverage-based method was used to identify and remove outliers, improving model reliability. Random Forest outperformed other models, achieving the highest R² (0.401) and lowest error. In contrast, Decision Tree and AdaBoost showed overfitting issues. Sensitivity analysis demonstrated that all variables contribute to the prediction, highlighting the model's robustness. This approach offers a cost-effective, accurate alternative to traditional experimental methods for estimating CIMS signal intensity across various pesticides and conditions, supporting faster and more efficient chemical analysis in agricultural monitoring.

Keywords

machine learning pesticide detection CIMS signal intensity prediction leverage outlier detection SHAP analysis

Get full access to this article

View all access options for this article.

References

De Hoffmann

Stroobant

. Mass spectrometry: principles and applications. John Wiley & Sons, 2007.

Sipilä

, et al. Molecular-scale evidence of aerosol particle formation via sequential addition of HIO3. Nature 2016; 537: 532–534.

Laskin

Nizkorodov

. Mass spectrometry analysis in atmospheric chemistry. Anal Chem 2018; 90: 166–189.

Eisele

Tanner

. Measurement of the gas phase concentration of H2SO4 and methane sulfonic acid and estimates of H2SO4 production and loss in the atmosphere. Journal of Geophysical Research: Atmospheres 1993; 98: 9001–9010.

Riva

, et al. Evaluating the performance of five different chemical ionization techniques for detecting gaseous oxygenated organic species. Atmos Meas Tech 2019; 12: 2403–2421.

Lee

, et al. An iodide-adduct high-resolution time-of-flight chemical-ionization mass spectrometer: application to atmospheric inorganic and organic compounds. Environ Sci Technol 2014; 48: 6309–6317.

Rissanen

, et al. The formation of highly oxidized multifunctional products in the ozonolysis of cyclohexene. J Am Chem Soc 2014; 136: 15596–15606.

Rissanen

, et al. Multi-scheme chemical ionization inlet (MION) for fast switching of reagent ion chemistry in atmospheric pressure chemical ionization mass spectrometry (CIMS) applications. Atmos Meas Tech 2019; 12: 6635–6646.

Sandström

, et al. Data-driven compound identification in atmospheric mass spectrometry. Advanced Science 2024; 11: 2306235.

10.

Partovi

, et al. Pesticide residue fast screening using thermal desorption multi-scheme chemical ionization mass spectrometry (td-Mion ms) with selective chemical ionization. ACS omega 2023; 8: 25749–25757.

11.

Partovi

, et al. Ambient-Pressure Multischeme Chemical Ionization for Pesticide Detection: A MION-Orbitrap Mass Spectrometry Study. ACS Omega, 2025.

12.

Taser

. Application of bagging and boosting approaches using decision tree-based algorithms in diabetes risk prediction. MDPI, 2021.

13.

Shorabeh

, et al. A decision model based on decision tree and particle swarm optimization algorithms to identify optimal locations for solar power plants construction in Iran. Renewable Energy 2022; 187: 56–67.

14.

Ramana

, et al. An Enhanced Novel Data Visualization Based on Flood Prediction Method Using Highest and Lowest Rainfall Patterns by Comparing Decision Tree Over Logistic Regression. Springer.

15.

, et al. Adapting boosting for information retrieval measures. Inf Retr Boston 2010; 13: 254–270.

16.

Kaur

, et al. Water quality assessment using machine learning: a focus on coliform prediction in water. Asian J Water Environ Pollut 2024; 21: 19–26.

17.

Solomatine

Shrestha

. AdaBoost. RT: a boosting algorithm for regression problems. in 2004 IEEE international joint conference on neural networks (IEEE Cat. No. 04CH37541). 2004. IEEE.

18.

Adetunji

, et al. House price prediction using random forest machine learning technique. Procedia Comput Sci 2022; 199: 806–813.

19.

, et al. Predictive modeling of groundwater nitrate pollution and evaluating its main impact factors using random forest. Chemosphere 2022; 290: 133388.

20.

Lin

, et al. Analyzing the impact of three-dimensional building structure on CO2 emissions based on random forest regression. Energy 2021; 236: 121502.

21.

Liu

, et al. Risk factor detection and landslide susceptibility mapping using geo-detector and random forest models: the 2018 hokkaido eastern iburi earthquake. Remote Sens (Basel) 2021; 13: 1157.

22.

Wang

, et al. Spatial heterogeneity modeling of water quality based on random forest regression and model interpretation. Environ Res 2021; 202: 111660.

23.

Isles

PDF

. A random forest approach to improve estimates of tributary nutrient loading. Water Res 2024; 248: 120876.

24.

Kunapuli

. Ensemble methods for machine learning. Simon and Schuster, 2023.

25.

Ngo

Beard

Chandra

. Evolutionary bagging for ensemble learning. Neurocomputing 2022; 510: 1–14.

26.

Piotrowski

, et al. Advanced ensemble methods using machine learning and deep learning for one-day-ahead forecasts of electric energy production in wind farms. Energies 2022; 15: 1252.

27.

Zhou

, et al. Multi-condition wear prediction and assessment of milling cutters based on linear discriminant analysis and ensemble methods. Measurement ( Mahwah N J) 2023; 216: 112900.

28.

Saleh

, et al. Flash flood susceptibility mapping in urban area using genetic algorithm and ensemble method. Geocarto Int 2022; 37: 10199–10228.

29.

Szostak

. Machine learning ensemble methods for optical network traffic prediction. in 14th International Conference on Computational Intelligence in Security for Information Systems and 12th International Conference on European Transnational Educational (CISIS 2021 and ICEUTE 2021) 14. 2022. Springer.

30.

Zhang

Liu

C-A

. Model averaging prediction by K-fold cross-validation. J Econom 2023; 235: 280–301.

31.

Yan

, et al. Prediction of geological characteristics from shield operational parameters by integrating grid search and K-fold cross validation into stacking classification algorithm. Journal of Rock Mechanics and Geotechnical Engineering 2022; 14: 1292–1303.

32.

Aigbe

, et al. Optimization and prediction of biogas yield from pretreated ulva Intestinalis linnaeus applying statistical-based regression approach and machine learning algorithms. Renewable Energy 2024; 235: 121347.

33.

Vaja

, et al. Ac/dc conductivity and ML-based evaluation of electric characteristics of methylene blue solution. J Mol Liq 2024; 410: 125676.