ML-Based Mineral Exploration through Metallogenic Maps


EOI: 10.11242/viva-tech.01.05.010

Download Full Text here



Citation

Vrushika Naik, Akshita Raut, Mansi Limbad, Saniket Kudoo, "ML-Based Mineral Exploration through Metallogenic Maps", VIVA-IJRI Volume 1, Issue 6, Article 10, pp. 1-6, 2023. Published by Computer Engineering Department, VIVA Institute of Technology, Virar, India.

Abstract

Mineral locations become more difficult to locate in geo-locations. Despite the existence of traditional means, the process of seeking is still not faster. Finding economically viable mineral reserves has become increasingly difficult. The iterative process of collecting various datasets, followed by geological interpretation, might take a long period during exploration. Massive volumes of data are gathered and analyzed, frequently with no notable mineral discoveries. As a result, processes need to increase finding rates and shorten the traditional exploration life cycle, which identifies mineral locations by overlaying numerous layers of geoscientific data in GIS software. This project is proposed for better mineral exploration by creating ML-based mining exploration models by combining geographical data. The Geological Survey of India's BHUKOSH portal and other sources contain a variety of geological datasets. The proposed project tries to analyze the problems and leverage the country's accessible geological datasets by delivering a Machine Learning solution for mineral exploration through the construction of a metallogenic model for better mineral exploration based on the geographic factors of a particular area.

Keywords

Machine Learning, Metallogenic model, Mineral exploration.

References

  1. Yongliang Chen , Wei Wu and Qingying Zhao," A Bat-Optimized One-Class Support Vector Machine for Mineral Prospectivity Mapping"Institute of Mineral Resources Prognosis on Synthetic Information, Jilin University, Changchun 130026, China.
  2. Zhenghui Chen, Nan Li and Jie Xiang, "Mineral Prospectivity Mapping based on Isolation Forest and Random Forest: Implication for the Existence of Spatial Signature of Mineralization in Outliers"Natural Resources Research, May 2021,20.
  3. Xishihui Du, Kefa Zhou , Yao Cui, Jinlin Wang and Shuguang Zhou, "Mapping Mineral Prospectivity Using a Hybrid Genetic Algorithm–Support Vector Machine (GA–SVM) Model"ISPRS Int. J.Geo-Inf., 2021, 10.
  4. Lin, N.; Chen, Y.; Liu, H. Liu, H., “A Comparative Study of Machine Learning Models with Hyperparameter Optimization Algorithm for Mapping Mineral Prospectivity” Minerals, 2021, 11.
  5. Yihui Xiong, Renguang Zuo, Emmanuel John M. Carranza, "Mapping mineral prospectivity through big data analytics and a deep learning algorithm" Elsevier, 2018, 30.
  6. Yan Niu, Jun Zhao, Zhiyuan Li , Wenjun Xu, Dong Liu, and Meng Zhao, "Optimization of Geological and Mineral Exploration by Integrating Remote Sensing Technology and Borehole Database" Wireless Communications and Mobile Computing Volume 2022, Article ID 9717749, 11.
  7. Chandragiri Sandeep, Yellepeddi Srikar, Kodali Rajani, Duvvada Rajeswara Rao, "Comparative Analysis of Mineral Identification using CNN and Random Forest" Department of Computer Science & Engineering, VR Siddhartha Engineering College,2021,10.
  8. Du, X.; Zhou, K.; Cui, Y.; Wang, J.; Zhou, S. Mapping Mineral Prospectivity Using a Hybrid Genetic Algorithm–Support Vector Machine (GA–SVM) Model. ISPRS Int. J.Geo-Inf. 2021, 10, 766.