LAUSR

This study is aimed at conducting a hazard-based sustainability gap analysis considering spatial threats driven by floods and landslides, that is, a multi-hazard-based prioritization of the most important cities in Gorganrood Basin, Iran. Two data-mining models were used to assess the spatial probability of flood inundation and landslide occurrence, namely, support vector machine with the radial basis function kernel (SVM-RBF) and maximum entropy (ME). As inputs, a total of 124 flooded locations and 346 landslides with ten flood/landslide predisposing factors were mapped using geoinformatics and organizational data. The random selection method was used to split the flood and landslide inventories into two sets of train and test data. Tolerance index was used to test the multicollinearity among predictors. Validation of the models was carried out using the area under the receiver operating characteristic (ROC) curve (AUC). Finally, TOPSIS was used, as a multi-criteria decision-making model, to make an internal sustainability gap analysis to prioritize the threatened and safe cities. For flood inundation, the AUC values obtained from the test set revealed that the SVM-RBF outperformed ME in terms of predictive power and generalization capacity with the respective areas of 0.831 and 0.796 under the curve. For landslide susceptibility assessment, SVM-RBF again excelled ME in predictive power with the respective values of 0.887 and 0.84. Therefore, the susceptibility maps derived from SVM-RBF, as the premier model, were used for the next stage. Extracting the flood and landslide spatial probability values to 14 city points, the TOPSIS-Solver software made a prioritization using the similarity function to the ideal solution. Accordingly, Aliabad, Minoodasht, and Azadshahr cities, with having the smallest similarity coefficients, were found to be the top three spatially threatened cities in Gorganrood Basin, while Aq Qala, Gomishan, and Gonbad-e Kavus cities were placed at the bottom as the safest cities. This study can be a pivotal point in regional risk-based planning, implementation of further pragmatic measures, and allocation of resources for improving sustainable development most wisely.