In this study, multi-source remote sensing data and machine learning algorithms were used to delineate the prospect area of remote sensing geological prospecting in eastern Botswana. Landsat 8 remote sensing images were used to produce iron stain and hydroxyl anomaly maps, ASTER remote sensing images were used to extract chalcopyrite mineral distribution maps, and Microsoft high-resolution remote sensing data were used to extract lithology and structure maps to comprehensively analyze regional metallogenic information. Then, the random forest, classification regression tree (CART) and gradient Lift Tree (GBT) classification algorithms were used to compare the models. The results showed that the random forest algorithm had the best performance in identifying mineralization potential areas, and its accuracy reached 0.95. Finally, the remote sensing geological prospect area of eastern Botswana was delineated based on random forest algorithm, which provided important technical support for mineral resource exploration in this area. This study shows that the combination of multi-source remote sensing data and efficient classification algorithm has great potential in geological prospecting, and provides scientific methods and technical means for the follow-up remote sensing prospecting research.
References
[1]
Peyghambari, S. and Zhang, Y. (2021) Hyperspectral Remote Sensing in Lithological Mapping, Mineral Exploration, and Environmental Geology: An Updated Review. Journal of Applied Remote Sensing, 15, Article 031501. https://doi.org/10.1117/1.jrs.15.031501
[2]
Rajesh, H.M., Safonov, O.G., Belyanin, G.A., Letshele, K.P. and Vorster, C. (2024) Metasomatism of Mafic-Intermediate Rocks in the Motloutse Complex, Botswana: Effect on Ore Mineralization and Implication for the Paleoproterozoic Large Alkali Metasomatic Province (LAMP) in Southern Africa. Precambrian Research, 406, Article 107402. https://doi.org/10.1016/j.precamres.2024.107402
[3]
Shirmard, H., Farahbakhsh, E., Müller, R.D. and Chandra, R. (2022) A Review of Machine Learning in Processing Remote Sensing Data for Mineral Exploration. Remote Sensing of Environment, 268, Article 112750. https://doi.org/10.1016/j.rse.2021.112750
[4]
Abdel-Karim, A.M., El-Awady, A., Khedr, M.Z., El-Afandy, A.H., Elwan, W., Tamura, A., et al. (2021) Genesis of Sulfide Mineralization, Atshan and Darhib Areas, South Eastern Desert of Egypt: Evidence of Fluid Pathway Effects along Shear Zones. Arabian Journal for Science and Engineering, 47, 641-665. https://doi.org/10.1007/s13369-021-05736-y
[5]
El-Omairi, M.A., El Garouani, M. and El Garouani, A. (2025) Enhanced Lithological Mapping via Remote Sensing: Employing SVM, Random Trees, ANN, with MNF and PCA Transformations. The Egyptian Journal of Remote Sensing and Space Sciences, 28, 34-52. https://doi.org/10.1016/j.ejrs.2024.12.001
[6]
Sekandari, M., Masoumi, I., Beiranvand Pour, A., M Muslim, A., Rahmani, O., Hashim, M., et al. (2020) Application of Landsat-8, Sentinel-2, ASTER and Worldview-3 Spectral Imagery for Exploration of Carbonate-Hosted Pb-Zn Deposits in the Central Iranian Terrane (CIT). Remote Sensing, 12, Article 1239. https://doi.org/10.3390/rs12081239
[7]
Chang, R.S., Tacon, P.R., Abiragi, M., Cao, L., Hong, G., Le, J., et al. (2024) Random Forest Machine Learning to Detect Cardiac Amyloidosis. Journal of the American College of Cardiology, 83, 311. https://doi.org/10.1016/s0735-1097(24)02301-5
[8]
Zhang, K., Jiang, D., Lyu, X. and Zhang, X. (2024) Current Application of Machine Learning Models in the Analysis of Remote Sensing Survey Data for Geological Hazards. Chinese Journal of Geological Hazard and Control, 35, 126-134.
[9]
Xi, Y., Mohamed Taha, A.M., Hu, A. and Liu, X. (2022) Accuracy Comparison of Various Remote Sensing Data in Lithological Classification Based on Random Forest Algorithm. Geocarto International, 37, 14451-14479. https://doi.org/10.1080/10106049.2022.2088859
[10]
He, L., Lyu, P., He, Z., Zhou, J., Hui, B., Ye, Y., et al. (2022) Identification of Radioactive Mineralized Lithology and Mineral Prospectivity Mapping Based on Remote Sensing in High-Latitude Regions: A Case Study on the Narsaq Region of Greenland. Minerals, 12, Article 692. https://doi.org/10.3390/min12060692
[11]
Zhang, X., Zhou, Z. and Yuan, Q. (2021) Potential and Investment Prospect of Important Mineral Resources in Botswana. Geology and Exploration, 57, 1297-1303.
[12]
Mapeo, R.B.M., Key, R.M., Moore, A.E., Mulder, J.A., Gardiner, N.J. and Robb, L.J. (2023) Syn-Bushveld “Granite Sheets” Associated with the Molopo Farms Complex Intruding into Transvaal Supergroup Strata in Southern Botswana. South African Journal of Geology, 126, 161-176. https://doi.org/10.25131/sajg.126.0012
[13]
Botros, N.S. (2015) The Role of the Granite Emplacement and Structural Setting on the Genesis of Gold Mineralization in Egypt. Ore Geology Reviews, 70, 173-187. https://doi.org/10.1016/j.oregeorev.2015.04.014
[14]
Pazhanikumar, K. and KuzhalVoiMozhi, S.N. (2023) Remote Sensing Image Classification Using Modified Random Forest with Empirical Loss Function through Crowd-Sourced Data. Multimedia Tools and Applications, 83, 53899-53921. https://doi.org/10.1007/s11042-023-17556-3
[15]
Ouyang, S., Chen, W., Qin, X., et al. (2024) Geological Background Prototype Learning-Enhanced Network for Remote-Sensing-Based Engineering Geological Lithology Interpretation in Highly Vegetated Areas. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 8794-8809. https://doi.org/10.1109/JSTARS.2024.3385541
[16]
Yang, X., Mao, J., Zhang, Z., Robbins, L.J., Planavsky, N.J., Jiang, Z., et al. (2021) Episodic Ferruginous Conditions Associated with Submarine Volcanism Led to the Deposition of a Late Carboniferous Iron Formation. Geochimica et Cosmochimica Acta, 292, 1-23. https://doi.org/10.1016/j.gca.2020.09.017
[17]
Alfonso, C.P., Müller, D., et al. (2025) Spatio-Temporal Copper Prospectivity in the American Cordillera Predicted by Positive-Unlabeled Machine Learning. Bulletin of the Geological Society of America, 137, 702-711. https://doi.org/10.1130/B37614.1
[18]
Zhang, Y., Gao, J., Ma, D. and Pan, J. (2018) The Role of Hydrothermal Alteration in Tungsten Mineralization at the Dahutang Tungsten Deposit, South China. Ore Geology Reviews, 95, 1008-1027. https://doi.org/10.1016/j.oregeorev.2018.04.006
[19]
Ye, F.W., Zhang, C., Xu, Q.J., Meng, S., Qiu, J.T. and Wang, J.G. (2019) Demonstration Analysis of Hydrothermal Fluid Activity Using Hyperspectral Remote Sensing Technology: A Case Study of Baiyanghe Uranium Deposit, Xinjiang. Mineral Deposits, 38, 1347-1364.
[20]
Schmidt, G., Franchi, F., Salvini, F., Selepeng, A.T., Luzzi, E., Schmidt, C., et al. (2023) Fault Controlled Geometries by Inherited Tectonic Texture at the Southern End of the East African Rift System in the Makgadikgadi Basin, Northeastern Botswana. Tectonophysics, 846, Article 229678. https://doi.org/10.1016/j.tecto.2022.229678
[21]
Zeng, Q., Shi, S., Qian, T., Wu, C., Pan, J., Wei, Y. and Chen, Y. (2024) Magmatic Contributions to the Mineralization of Several Important Hydrothermal Deposits. Acta Geoscientica Sinica, 45, 337-348.
[22]
Yuan, X., Zhang, Y., Jiang, Z., Liu, X., Huo, Y. and Ge, P. (2025) Formation Mechanism and Geological Significance of Shale Reservoirs in Cretaceous Continental Faulted Basins of the Yanshan Tectonic Belt, Northeastern China: A Case Study of the Luanping Basin. Journal of Asian Earth Sciences, 280, Article 106472. https://doi.org/10.1016/j.jseaes.2024.106472
[23]
Liu, S., Lee, E.Y., Zhang, J., Wagreich, M., Zhao, L. and Liu, H. (2021) Tectono-Paleogeographic Impact on the Permian Depositional Environment and Provenance around the Chaiwopu Depression in the Southern Junggar Basin, NW China. Minerals, 11, Article 1237. https://doi.org/10.3390/min11111237
[24]
Wu, C.Y., Dai, J.J., Chen, W., Jiang, B., Wang, D.H., Wang, C.L., et al. (2023) Extraction of Remote Sensing Alteration Information and Its Ore Prospecting Indication in Sumochagan Obao Fluorite Mining Area, Inner Mongolia. Mineral Deposits, 42, 845-858.
[25]
Choudhary, S., Sajeev, R. and Konwar, P. (2019) Identification of Alteration Zone Targeting Base Metal Potential Area Using ASTER Data Near Umra, Udaipur, Rajasthan, India. Indian Journal of Geosciences, 73, 15-24.
[26]
Wang, X., Jing, G., Li, W., He, J., Wang, Y., Liu, X., et al. (2024) Lineament Mapping and Deposit Prospecting in the Gouli Area, East Kunlun, Qinghai Province: Using Multisource Remote Sensing Data. Bulletin of Geological Science and Technology, 43, 326-342
[27]
Chavez, P.S. (1996) Image-Based Atmospheric Corrections—Revisited and Improved. Photogrammetric Engineering and Remote Sensing, 62, 1025-1036.
[28]
Shevyrev, S. and Carranza, E.J.M. (2022) Application of Maximum Entropy for Mineral Prospectivity Mapping in Heavily Vegetated Areas of Greater Kurile Chain with Landsat 8 Data. Ore Geology Reviews, 142, Article 104758. https://doi.org/10.1016/j.oregeorev.2022.104758
[29]
El Mimouni, M., Aarab, A., Lakhloufi, A., Hamzaoui, A., Aabi, A. and Benyas, K. (2024) Detection of Potentially Ore-Bearing Hydrothermal Alteration Zones in the Rehamna Massif (Morocco). Ecological Engineering & Environmental Technology, 25, 163-173. https://doi.org/10.12912/27197050/190631
[30]
Abdelwahab, W. and El-Shamy, A.M. (2024) Exploring Talc Deposits: Physical Characteristics, Geological Factors, and Formation in Ultramafic and Mafic Rocks—A Comprehensive Review. Chemistry Africa, 8, 43-83. https://doi.org/10.1007/s42250-024-01151-6
[31]
Emmela, S., Rama Lahari, V., Anusha, B., Bhavana, D., Yasyukevich, Y.V., Demyanov, V.V., et al. (2024) Global Ionospheric Total Electron Content Short-Term Forecast Based on Light Gradient Boosting Machine, Extreme Gradient Boosting, and Gradient Boost Regression. Advances in Space Research, 74, 3642-3653. https://doi.org/10.1016/j.asr.2024.07.012
[32]
Bishop, B.A. and Robbins, L.J. (2024) Using Machine Learning to Identify Indicators of Rare Earth Element Enrichment in Sedimentary Strata with Applications for Metal Prospectivity. Journal of Geochemical Exploration, 258, 107388. https://doi.org/10.1016/j.gexplo.2024.107388
[33]
Yao, J., Xiao, C., Zhang, Z., Wang, L. and Zhang, K. (2024) Vegetation Feature Type Extraction in Arid Regions Based on GEE Multi-Source Remote Sensing Data. Arid Zone Research, 41, 157-168.
