Evaluating the Performance of PRISMA Shortwave Infrared Imaging Sensor for Mapping Hydrothermally Altered and Weathered Minerals Using the Machine Learning Paradigm

Satellite images provide consistent and frequent information that can be used to estimate mineral resources over a large spatial extent. Advances in spaceborne hyperspectral remote sensing (HRS) machine learning help support various remote-sensing-based applications, including exploration. Leveraging these advances, the present study evaluates recently launched PRISMA satellite map hydrothermally altered weathered minerals using machine-learning-based classification algorithms. The was performed for town of Jahazpur Rajasthan, India (75°06′23.17″E, 25°25′23.37″N). distribution such as kaolinite, talc, montmorillonite generated spectral angle mapper technique. resultant verified through an intensive field validation survey on surface exposures minerals. Furthermore, obtained pixels end-members were develop models. Measures accuracy, kappa coefficient, F1 score, precision, recall, ROC curve employed evaluate performance developed results show stochastic gradient descent artificial-neural-network-based multilayer perceptron classifiers more accurate than other Results confirm dataset has enormous potential mapping mountainous regions utilizing framework.