Advancing Mineral Exploration: Robust and Interpretable Carbonate Quantification in Drill Cores via Hyperspectral Machine Learning
Minerals · 30.04.2026 · 16 (5) · 479
DOI: 10.3390/min16050479 ↗Kurz gefasst
Fachartikel in der Zeitschrift Minerals, online erschienen am 30.04.2026. Verfasst von Vinicius Sales und 13 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Petrobras, National Agency of Petroleum, Natural Gas and Biofuels, Coordenação de Aperfeicoamento de Pessoal de Nível Superior.
Abstract (Originalsprache)
Accurate quantification of mineralogical composition in carbonate rocks is essential for reservoir characterization in the oil industry, directly influencing petrophysical properties such as porosity and permeability. However, traditional methods such as X-ray diffraction (XRD) are destructive and provide limited spatial sampling. The aim of this study was to develop and validate a workflow for the continuous quantification of calcite and dolomite in drill cores from the Brazilian pre-salt oil province by integrating short-wave infrared (SWIR) hyperspectral imaging (HSI) and Machine-Learning algorithms. A total of 80 m of cores were evaluated using 170 XRD-validated samples to calibrate linear, nonlinear, and ensemble models. The results showed that the combination of Multiplicative Scatter Correction (MSC) preprocessing with Multilayer Perceptron (MLP) and Support Vector Regression (SVR) achieved the best performance, reaching an R2 of 0.84. Explainable Artificial Intelligence (SHAP) confirmed the relevance of diagnostic bands between 2330 and 2360 nm, improving geological interpretability of the predictions. The proposed methodology provides a non-destructive and high-resolution alternative for mineralogical profiling, supporting the evaluation of complex reservoirs and decision-making in the oil and gas industry. Although the workflow was validated using a specific pre-salt dataset, future studies should assess its transferability to other carbonate reservoirs and broader geological settings.
Förderung
- Petrobras
- National Agency of Petroleum, Natural Gas and Biofuels
- Coordenação de Aperfeicoamento de Pessoal de Nível Superior
Zitieren
APA
Sales, V., Racolte, G., Souza, L., Aires, A., Lorenz, J., Silva, R., Silva, L. D., Dias, R., Mariani, D., Marques, A., Zanotta, D., Ibanez, D., Gonzaga, L., & Veronez, M. (2026). Advancing Mineral Exploration: Robust and Interpretable Carbonate Quantification in Drill Cores via Hyperspectral Machine Learning. Minerals, 16(5), 479. https://doi.org/10.3390/min16050479
Vancouver
Sales V, Racolte G, Souza L, Aires A, Lorenz J, Silva R, et al. Advancing Mineral Exploration: Robust and Interpretable Carbonate Quantification in Drill Cores via Hyperspectral Machine Learning. Minerals. 2026;16(5):479. doi:10.3390/min16050479
BibTeX
@article{Sales2026,
author = {Sales, Vinicius and Racolte, Graciela and Souza, Lais and Aires, Alysson and Lorenz, Julia and Silva, Reginaldo and Silva, Luiza da and Dias, Rafael and Mariani, Diego and Marques, Ademir and Zanotta, Daniel and Ibanez, Delano and Gonzaga, Luiz and Veronez, Mauricio},
title = {Advancing Mineral Exploration: Robust and Interpretable Carbonate Quantification in Drill Cores via Hyperspectral Machine Learning},
journal = {Minerals},
year = {2026},
volume = {16},
number = {5},
pages = {479},
doi = {10.3390/min16050479}
}
EUVIMED