Gypsum Detection from satellite image using Remote Sensing with Machine Learning in Nakhon Sawan Province, Thailand.

Abstract

Remote sensing is a valuable tool for reducing the cost and time associated with mineral exploration, particularly in the identification of potential gypsum deposits, which are high-demand industrial minerals. This study integrates remote sensing techniques with machine learning to delineate prospective gypsum deposit areas in Nong Bua, Nakhon Sawan Province, Thailand—an important source of gypsum. Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data were processed using the band ratio technique and a supervised classification approach, specifically the Extreme Gradient Boosting (XGBoost) algorithm, to enhance the classification of gypsum-bearing regions. The accuracy of the classification was evaluated using an error matrix, resulting in a good classification of gypsum in the mining area, yielding a high overall accuracy of 97%. This research can significantly improve the efficiency of mineral exploration and resource management of gypsum in the future.