A Comparison of an Adaptive Neuro-Fuzzy and Frequency Ratio Model to Landslide-Susceptibility Mapping along Forest Road Networks

In this research, we used the integration of frequency ratio and adaptive neuro-fuzzy modeling (ANFIS) to predict landslide susceptibility along forest road networks in Hyrcanian Forest, northern Iran. We began our study by first mapping locations during an extensive field survey. addition, then selected landslide-conditioning factors, such as slope, aspect, altitude, rainfall, geology, soil, age, slip position from available Geographic Information System (GIS) data. Following this, developed Adaptive Neuro-Fuzzy Inference models with two different membership functions (MFs) order generate maps. applied a model compared results probabilistic ANFIS model. Finally, calculated map accuracy evaluating receiver-operating characteristics (ROC). The validation yielded 70.7% using triangular MF model, 67.8% Gaussian 68.8% Our indicated that is effective tool for regional assessment, maps produced area can be natural hazard management landslide-prone region.