Lithological mapping enhancement by integrating Sentinel 2 and gamma-ray data utilizing support vector machine: A case study from Egypt

Hybrid data fusion mostly gives a better diagnosis to lithological units compared single-source mapping techniques. Rock unit discrimination depends mainly on variations in the concentrations of chemical elements. Remote sensing datasets reflect these as different spectral reflectances, while gamma-ray spectrometric measurements enable recording varied K, Th, and U rock units. Accordingly, this study, we use Support-Vector Machine (SVM) learning algorithm classify combined high resolution Sentinel 2 with content rocks differentiate lithologically complex area Egypt. SVM classifier has been trained tested reference map (built from FCCs, principal independent component analysis remote images, well previous geological maps) allocate 13 targets. U, total count maps are interpolated using inverse distance weighted (IDW) method, cubically resampled, fused data. We concluded that incorporating any single concentration allocation results than solely raised Overall Accuracy by 4.14%, 5.11%, 6.83% adding respectively. Moreover, blending band (K + Th U) outstandingly boosts classification accuracy 7.77 %. performed field reconnaissance verify results. The study demonstrates effectiveness integrating airborne geophysical data, proposed approach may prove more precise sophisticated map.