This study uses machine learning techniques to address the classification of lithological units in an iron deposit based on their physical and chemical properties. The importance of this problem lies in the challenges of identifying the material origin when traceability is lost during processing. Supervised learning algorithms, including Random Forest, were applied to data from 18 boreholes comprising multiple lithotypes. Initially, the model achieved an f1-score of 0.89 for lithology classification. By grouping similar lithologies, notably different types of itabirites, the score improved to 0.97. These results suggest introducing new features, such as compactness, could further refine accuracy. This work demonstrates that machine learning offers a promising methodology for lithotype classification and may be adapted to other geological contexts.
JungDChoiY. Systematic review of machine learning applications in mining: exploration, exploitation, and reclamation. Minerals2021; 11: 148.
2.
RussellSJNorvigP. Artificial intelligence: a modern approach. 3rd ed.Upper Saddle River, NJ: Pearson Education, 2010.
3.
DrumondDA. Estimativa e classificação de variáveis geometalúrgicas a partir de técnicas de aprendizado de máquina. PhD Thesis, Universidade Federal do Rio Grande do Sul, Porto Alegre, 2019.
4.
PereiraSP. Classificação de unidades litológicas a partir de propriedades físicas e químicas. PhD Thesis, Universidade Federal do Rio Grande do Sul, Porto Alegre, 2024.
5.
CatéAPerozziLGloaguenE,et al.Machine learning as a tool for geologists. Lead Edge2017; 36: 215–219.
6.
BerettaFRodriguesALPeroniRL,et al.Automated lithological classification using UAV and machine learning on an open cast mine. Appl Earth Sci2019; 128: 179–188.
7.
AkyildizOBasarirHEllefmoSL. The development of a lithology prediction model using measurement while drilling data in a quartzite quarry. Appl Earth Sci2024; 128: 93–109.
8.
AliMZhuPHuolinM, et al.Data-driven machine learning approaches for precise lithofacies identification in complex geological environments. Appl Earth Sci2024; 130: 1–21.
9.
AmaranteFANRoloRMCostaJFCL. Boundary simulation – a hierarchical approach for multiple categories. Appl Earth Sci2021; 130: 87–104.
10.
GoldringDC. Iron ore categorisation for the iron and steel industry. Appl Earth Sci2003; 112: 93–109.
11.
MukherjeeBKarSSainK. Machine learning assisted state-of-the-art-of petrographic classification from geophysical logs. Pure Appl Geophys2024; 181: 2839–2871.
12.
PrajapatiRMukherjeeBSinghUK, et al.Machine learning assisted lithology prediction using geophysical logs: a case study from Cambay Basin. J Earth Syst Sci2024; 133: Article 108.
13.
MukherjeeBSainK. Vertical lithological proxy using statistical and artificial intelligence approach: a case study from Krishna-Godavari Basin, offshore India. Mar Geophys Res2021; 42: Article 3.
14.
ShrivastavaHSridharanS. Conception of data preprocessing and partitioning procedure for machine learning algorithms. Int J Recent Adv Eng Technol2013; 1: 160–164.
15.
KotsiantisSKanellopoulosDPintelasPE. Data preprocessing for supervised learning. Int J Comput Sci2006; 1: 111–117.
16.
VafaeiNRibeiroRACamarinha-MatosLM. Importance of data normalization in decision making: case study with TOPSIS method. Int J Inf Decis Sci2018; 10: 19–38.
17.
JolliffeITCadimaJ. Principal component analysis: a review and recent developments. Phil Trans R Soc A2016; 374: 20150202.
18.
MüllerACGuidoS. Introduction to machine learning with Python: a guide for data scientists. 1st ed.Sebastopol, CA: O’Reilly Media, 2017.
19.
BreimanL. Random forests. Mach Learn2001; 45: 5–32.
20.
FriedmanJH. Greedy function approximation: a gradient boosting machine. Ann Stat2001; 29: 1189–1232.
AitchisonJ. Principal component analysis of compositional data. Biometrika1983; 70: 57–65.
23.
JolliffeIT. Principal component analysis. 2nd ed. New York: Springer, 2002.
24.
NilssonNJ. Introduction to machine learning: an early draft of a proposed textbook. Stanford: Department of Computer Science, Stanford University, 1998.
25.
MukherjeeBGautamPKSainK. Machine learning assisted crustal velocity proxy: a case study over the Tibetan Plateau and its surroundings. J Asian Earth Sci2024; 263: 106004.
