393 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 PDFbased classification to all basin outputs produced the final national LSM of Peru, where mapped landslide occurrences were overlaid for validation and visual comparison. Figure 2 – LSM of Peru derived from the ANN model. Blue dots represent mapped landslide occurrences. 4. DISCUSSION 4.1. Comparison between Landslide Susceptibility Maps in Peru To compare the proposed quantitative ANN-based landslide susceptibility map (LSM) with existing qualitative Macro-Regional and Regional LSMs for Peru, an independent validation dataset (2021–2023) was used. This dataset was not involved in model training or testing and therefore provides an unbiased benchmark. Model performance was evaluated using a spatial accuracy ratio defined as the proportion of validation landslide events located within areas classified as high or very high susceptibility:
RkJQdWJsaXNoZXIy MTM0Mzk2