Application of Satellite Remote Sensing, UAV-Geological Mapping, and Machine Learning Methods in the Exploration of Podiform Chromite Deposits

The irregular and sporadic occurrence of chromite pods in podiform deposits (PCD), especially mountainous terranes with rough topography, necessitates finding innovative methods for reconnaissance prospecting. This research combines several remote sensing to discriminate the highly serpentinized peridotites hosting from other barren ultramafic mafic cumulates. case study is area Sabzevar Ophiolite (NE Iran), which hosts known mineral deposits. integration satellite images [e.g., Advanced Spaceborne Thermal Emission Reflection Radiometer (ASTER) sensor, Landsat series, Sentinel-2] coupled change detection, band rationing, target detection algorithms [including Spectral Angle Mapper (SAM)] were used distinguish potential lithological units chromites. Results have been verified by an initial on-field checking compared high-resolution (GSD ~6 cm) orthomosaic obtained processing photographs taken Unmanned Aerial Vehicle (UAV) at a promising 35 km2. combination visual interpretation supervised classification machine learning [Support Vector Machine (SVM)] yielded production geological map, structures are outlined, including crust-mantle transition zone units, cumulates, crosscutting dykes, mantle sequences. validation results was performed through second phase, made up field mapping, sampling, chemical analysis, microscopic studies, leading discovery new occurrences mineralized zones. All classified into four groups based on degree serpentinization, represented intensity their average spectral reflectance. Based presumed protolith, ultramafics serpentinites two main categories (dunite or harzburgite). serpentinite probable dunitic discriminated peculiar Fe-rich Ni-bearing lateritic crust, more productive particularly true contact akin some worldwide our work highlight multi-scale UAV-based find footprints