Rule-based fuzzy inference system for landslide susceptibility mapping along national highway 7 in Garhwal Himalayas, India

Abstract

The Mountainous terrain,in the Himalayas is experiencing rapid development in a bewildering manner, which makes it more susceptible to landslides. Management and mitigation of landslide hazard begin with its mapping by integrating numerous methods and Geographic Information System (GIS) tools. However, it is difficult to produce reliable landslide susceptibility maps (LSM) with traditional remote sensing and GIS methods due to complexity of the mountainous terrain environments and huge datasets. Therefore, the present study investigates the applicability of Mamdani’s fuzzy inference system (FIS) to produce LSM in Himalayan terrain in India. It is compared with commonly used frequency ratio (FR) and information value method (IVM) approaches. Several causative factors were extracted and used to prepare thematic layers, including slope, aspect, curvature, solar radiance, SPI, TWI, rainfall, soil depth and NDVI. Landslide inventory was also created using google earth images and previously published work. The accuracy estimates for FR, IVM and FIS were performed based on ROC curves. FIS was found to provide an accuracy of 77.7%, followed by IVM (72%) and FR (71%) for LSM. The current study is a prototype for further studies in the Garhwal Himalayas and similar terrains, based on the vigorous Mamdani’s techniques of fuzzy inference theory. The outcomes of this work propose that an expert’s knowledge-based FIS method can produce an accurate LSM in such a complex terrain. Planners and concerned authorities can use the results further for landslide management and mitigation.