Machine learning and remote sensing-based lithological mapping of the Duwi Shear-Belt area, Central Eastern Desert, Egypt

• Published in: Scientific reports 2024-07, Vol.14 (1), p.17010-23, Article 17010
• Main Authors: Ghoneim, Sobhi M., Hamimi, Zakaria, Abdelrahman, Kamal, Khalifa, Mohamed A., Shabban, Mohamed, Abdelmaksoud, Ashraf S.
• Format: Article
• Language: English
• Subjects: 704/2151; 704/2151/213; 704/2151/431; Classification; Deserts; Discrimination; Duwi shear belt (DSB); Field study; Fieldwork; Geologic mapping; Humanities and Social Sciences; Landsat; Learning algorithms; Lithological mapping; Lithology; Machine learning; Mapping; multidisciplinary; Principal components analysis; Remote sensing; Rocks; Science; Science (multidisciplinary); Sediments; Support vector machine (SVM); Support vector machines
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-66199-3

Machine learning and remote sensing techniques are widely accepted as valuable, cost-effective tools in lithological discrimination and mineralogical investigations. The current study represents an attempt to use machine learning classification along with several remote sensing techniques being applied to Landsat-8/9 satellite data to discriminate the various outcropping lithological rock units at the Duwi Shear Belt (DSB) area in the Central Eastern Desert of Egypt. Multi-class machine learning classification, multiple conventional remote sensing mapping techniques, spectral separability analysis based on the Jeffries-Matusita (J-M) distance measure, fieldwork, and petrographic investigations were integrated to enhance the lithological discrimination of the exposed rock units at DSB area. The well-recognized machine learning classifier (Support Vector Machine—SVM) was adopted in this study, with training data determined carefully based on enhancing the lithological discrimination attained from various remote sensing techniques of False Color Composites (FCC), Principal Component Analysis (PCA), and Minimum Noise Fraction (MNF), along with the fieldwork data and the previously published geologic maps. High overall accuracy of the SVM classification was obtained, however, inspection of the individual rock unit classes’ accuracies revealed lower accuracy for certain types of rock units which were also found associated with lower separability scores as well. Among the least separable rock units were; metagabbro rocks that showed high spectral similarity with the volcaniclastic metasediments rocks, and the metaultramafics of the ophiolitic mélange showed spectral attitude of high correlation to that of the Hammamat volcanosedimentary rocks. Target-oriented Color Ratio Composites (CRC) technique was implemented to better discriminate these hardly separable rock units. A final integrated geological map was obtained comprising the various discriminated Neoproterozoic basement rock units of the DSB area. The successfully mapped litho-units include; Meatiq Group (amphibolites, gneissic granitoids, and mylonitized granitoids), ophiolitic mélange (metaultramafics, metagabbro-amphibolites, and volcaniclastic metasediments), Dokhan volcanics, Hammamat sediments, and granites. An adequate description of these rock units was also given in light of the conducted intense fieldwork and petrographic investigations.