Application of geographical information system (GIS) using artificial neural networks (ANN) for landslide study in Langat Basin, Selangor

Abstract The landslide was recognized as the most common geologic hazard around world. assessment of relationship conditioning factors is a critical step in managing hazards and risks. Several models have been made to develop model recent years. Artificial Neural Networks (ANN) used this study identify important factors. Eight factors, including elevation, slope, aspect, curvature, lithology, soil series, Topographic Wetness Index (TWI), rainfall, were selected analyzed using Geographical Information System (GIS) approach. multilayer perceptron module one hidden layer method extracted weighted validated area under curve (AUC) method. This validation showed success rate for training testing 0.876, respectively. found curvature crucial factor affecting occurrence Langat Basin with 0.213 weight index, followed by rainfall (0.143) elevation (0.141). Finally, can be an indicator assess between these occurrences.