396 algorithms, including sensitivity values up to 0.73 and specificity values up to 0.84. Rosi et al. (2023) comprehensively employed a Random Forest model to conduct a large-scale landslide susceptibility analysis in Central Asia. Their model exhibited high stability, achieving a mean AUC of 93.12% across five independent training iterations, although classification accuracy metrics were not reported. Table 3 places the results of the present study within this broader context. The proposed ANN model achieved the highest AUC value (95.55%) among the reviewed studies, despite its relatively simple architecture. Most landslide susceptibility studies are developed and validated at a fixed spatial resolution, with limited assessment of model behaviour under changes in DEM scale. Qualitative heuristic maps in Peru (Villacorta et al., 2012; Luque et al., 2021) are intrinsically tied to predefined cartographic scales and thematic generalization, restricting their transferability to local applications without recalibration, while recent machine learning approaches. Kumar et al., 2023; Rosi et al., 2023 typically evaluate performance at a single resolution without testing spatial scalability. The down-scaling experiment conducted in this study demonstrates that the proposed ANN framework preserves predictive consistency when applied to higher-resolution DEMs at basin scale. This robustness is theoretically supported by the self-affine nature of topographic surfaces, whereby morphometric variables such as slope, curvature, and hydrological indices maintain scale-consistent statistical relationships while increasing geometric detail with resolution. Because the ANN approximates a continuous non-linear mapping between terrain attributes and landslide probability, enhancing spatial resolution refines the representation of predictor variables without altering the learned functional structure. The improved spatial alignment observed at local scale therefore reflects increased topographic fidelity rather than structural model modification, confirming the multi-scale applicability and operational scalability of the proposed methodology. 5. CONCLUSION The evaluation of the Artificial Neural Network (ANN) model demonstrates a substantial improvement in landslide susceptibility mapping accuracy compared to existing Regional and MacroRegional models in Peru. Receiver Operating Characteristic (ROC) analysis yielded an Area Under the Curve (AUC) of 95.50%, confirming excellent predictive capability. When tested against an independent validation dataset, the ANN-based map correctly classified 73.74% of landslide occurrences within the high and very high susceptibility classes, significantly outperforming the Macro-Regional (37.25%) and Regional (48.26%) models. Qualitative spatial analyses further confirmed the robustness of the ANN framework, revealing a physically coherent and geomorphologically consistent distribution of susceptibility classes that closely matches documented landslide patterns across the Peruvian territory. These results demonstrate the effectiveness of Artificial Neural Networks for national-scale susceptibility mapping in complex mountainous terrains. By capturing non-linear interactions among morphometric and hydrological predictors, the proposed framework overcomes the limitations of heuristic weighting approaches while maintaining methodological simplicity and computational stability. Although developed at national scale, the methodology is inherently adaptable to multiple spatial resolutions, including mining, transport, and infrastructure applications. Beyond hazard assessment, the ANN framework provides direct operational value for the mining sector by enabling early identification of high-susceptibility zones affecting haul roads, waste dumps, tailings storage facilities, and access platforms. Its resolution-adaptive behavior supports proactive geotechnical planning, optimized infrastructure layout, and reduced disruption risk, contributing to lower operational delays and improved economic resilience.
RkJQdWJsaXNoZXIy MTM0Mzk2