Natural Hazard Susceptibility Mapping Using Ubiquitous Geospatail Artificial Intelligence (Ubiquitous GeoAI) Concept: A Case Study on Forest Fire Susceptibility Mapping

Abstract

This research was conducted to prepare forest fire susceptibility mapping (FFSM) using a ubiquitous GIS and an ensemble of adaptive neuro fuzzy interface system (ANFIS) with genetic (GA) and simulated annealing (SA) algorithms (ANFIS-GA-SA) and an ensemble of radial basis function (RBF) with an imperialist competitive algorithm (ICA) (RBF-ICA) model in Chaharmahal and Bakhtiari Province, Iran. GIS data and technologies have proved helpful in many environmentally-related studies in terms of obtaining fine resolution data and investigating numerous features impacting the real-world phenomena. A field survey and MODIS satellite imagery were used to identify the forest fire areas. The outcomes of the spatial autocorrelation revealed that the distribution of fire occurrence in the research region is clustered, and the majority of the geographical dependence is connected to the factors relating to settlement distance, soil type, and rainfall.