1 11 1,284,000 28.00 0.052727 695 Nonconvergen ce Nonconvergen ce Note: Time more than 2 hours, the value for the threshold is not going down after another iteration. Among the evaluated configurations, the ANN with one hidden layer and five neurons achieved the best balance between predictive performance and computational efficiency. This model reached an AUC of 97.37 % for training and 95.55 % for testing, which corresponds to excellent predictive quality. Convergence was achieved in approximately 6.7 hours with a minimum threshold of 0.0101, while models with a higher number of neurons frequently failed to converge or required substantially longer processing times. The selected model also demonstrated strong classification capability, with high sensitivity, specificity, and balanced precision, indicating robust discrimination between landslide and nonlandslide conditions. This configuration was therefore adopted for subsequent landslide susceptibility mapping across the 229 hydrographic units of the Peruvian territory. 3.2 Landslide Susceptibility Map (LSM) The optimal ANN model was applied independently to each of the 229 hydrographic basins in Peru using basin-specific conditioning factors (DEM, slope, aspect, curvature, SPI, TWI, and land cover). This produced continuous probability rasters (0–1) for each basin. To generate the final national Landslide Susceptibility Map (LSM), the probability outputs were classified into five classes—very low, low, medium, high, and very high—according to Peruvian standards. Classification thresholds were determined objectively using the first inflection points of the probability density function (PDF) derived from all 3.15 billion pixels at national scale. The resulting cutoffs were 0.0166, 0.3740, 0.7100, and 0.9740, defining the corresponding susceptibility intervals. Applying this PDF-based classification to all basin outputs produced the final national LSM of Peru, where mapped landslide occurrences were overlaid for validation and visual comparison.
RkJQdWJsaXNoZXIy MTM0Mzk2