PRISMA hyperspectral data for lithological mapping in the Egyptian Eastern Desert: Evaluating the support vector machine, random forest, and XG boost machine learning algorithms

•Detailed lithological mapping using PRISMA hyperspectral data and RF, XGB, and SVM.•SVM and XGB results are more precise than RF. The first four PCs constitute reasonable data input but adopting the whole number of bands delivers better accuracy.•As a first study over ANS, the adopted approach is strongly recommended for further detailed mapping and mineral exploration programs.