Publisher Correction: The intelligent fault identification method based on multi-source information fusion and deep learning
Dashu Guo, Xiaoshuang Yang, Peng Peng, Lei Zhu, Handong He · Scientific Reports · 2025
The published Figures 3 and 12 and their legends appear below. Fig. 3 16 influencing factors for fault identification: ( a ) Remote sensing imagery. ( b ) elevation. ( c ) Surface cutting depth. ( d ) Relief amplitude. ( e ) Terrain roughness. ( f ) Degree of slope. ( g ) Aspect. ( h ) Slope of slope. ( i ) Slope of aspect. ( j ) elevation standard deviation. ( k ) Coefficient of elevation variation. ( l ) Curvature. ( m ) Slope length. ( n ) Lithology. ( o ) Valley line. ( p ) Topographic position index. Maps were created using ArcGIS 10.5 (Environmental Systems Research Institute, USA. https://www.esri.com/ ). Full size image Fig. 12 Fault identification results using fault identification map computed based on SVM, CART, ANN, and BN models: ( a ) SVM-based fault identification results. ( b ) CART-based fault identification results. ( c ) ANN-based fault identification results. ( d ) BN-based fault identification results. Full size image