*3.7. Validation*

In this research, the ROC curves were used for the accuracy assessment of the LSS models employed [6,10,39]. The ROC curve analysis is a common method to evaluate the goodness-of-fit and prediction power of models regarding the area under the curve (AUC) [2,67]. Ranging from 0 to 1, higher AUC values represent more reliable and accurate model performance. According to Yesilnacar [53], the qualitative relationship between AUC and the prediction accuracy of a model can be classified into the following categories: 0.5–0.6 (poor), 0.6–0.7 (average), 0.7–0.8 (good), 0.8–0.9 (very good), and 0.9–1 (excellent).

#### **4. Results**

By utilizing the spatial data and subsidence inventory generated and the methods discussed above, the mapping and assessment of land subsidence susceptibility for Shahryar County were conducted. In the following sub-sections, the results of the various parts of the methodology are thoroughly discussed.
