Determining Flood Zonation Maps, Using New Ensembles of Multi-Criteria Decision-Making, Bivariate Statistics, and Artificial Neural Network

Golestan Province is one of the most vulnerable areas to catastrophic flood events in Iran. The severity this region has grown dramatically during last decades, demanding a major investigation. Accordingly, an authentic map providing detailed information on floods required reduce future disasters. Three ensemble models produced by combination Evaluation Based Distance from Average Solution (EDAS) and Multilayer Perceptron Neural Network (MLP) with Frequency Ratio (FR), Weights Evidence (WOE) are used quantify susceptibility Province, north Ten effective criteria, namely altitude, slope degree, aspect, plan curvature, distance rivers, Topographic Wetness Index (TWI), rainfall, soil type, geology, land use, considered for modeling process. zonation maps validated receiver operating curve (ROC). results show that precise model MLP-FR (AUROC = 0.912), followed EDAS-FR-AHP 0.875), EDAS-WOE-AHP 0.845). high accuracies all methods applied illustrate their capability predicting studies.