Spatial Heterogeneity-Aware Multi-Hazard Susceptibility and Risk Mapping at Regional Scale

2026-08-08

AI Summary

This study addresses the strong co-occurrence of flood and landslide hazards and their spatially heterogeneous relationships with environmental factors, which challenge conventional models in balancing regional specificity and generalizability. A dual-strategy modeling framework integrating spatial proximity and ecological zoning is proposed to map compound flood–landslide susceptibility and relative risk in Kerala, India, and Nepal. The approach partitions the study areas into 15 km contextual units and employs two strategies: proximity-gated cross-zone training (S1) and ecozone-gated within-zone constrained training (S2). Using random forest, CRITIC weighting, and SHAP interpretability, coupled with spatial hold-out validation and multi-metric evaluation, results show S1 outperforms in most metrics (e.g., AUC-ROC of 0.886 for floods in Nepal), while S2 preserves region-specific factor contributions. The resulting nine-class compound hazard risk maps achieve a consistency of 0.711 in Nepal, with exposure and vulnerability substantially reshaping high-risk priority zones.

Abstract

Floods and landslides often co-occur, but their relationships with environmental controls vary spatially. This study develops a spatial heterogeneity-aware framework for flood-landslide susceptibility and relative-risk mapping in Kerala, India, and Nepal. It combines 15 km x 15 km grid cells with region-specific contextual zones and compares proximity-gated cross-zone training (S1) and ecology-gated zone-constrained training (S2). S1 permits geographically nearby models to be assigned across contextual boundaries, whereas S2 restricts model development and assignment to the same zone. Random Forest models for each hazard use strategy-specific predictor sets and are evaluated on spatially held-out test samples. Susceptibility surfaces are integrated with CRITIC-weighted exposure and vulnerability indices to produce hazard-specific and nine-class bivariate relative-risk maps. S1 achieved higher mean accuracy, precision, recall, F1-score, AUC-ROC, and PR-AUC for both hazards and regions. The largest difference occurred for Nepal flood susceptibility, where AUC-ROC increased from 0.728 under S2 to 0.886 under S1 and PR-AUC from 0.512 to 0.823. S2 produced lower Brier scores for both Nepal hazards and retained zone-specific differences in predictor selection, SHAP rankings, and response patterns, particularly in Kerala. Both strategies reproduced flood-prone lowland and landslide-prone upland patterns but differed in susceptibility and risk classes. Bivariate risk-map agreement was 0.521 in Kerala and 0.711 in Nepal, with allocation disagreement exceeding quantity disagreement in all S1-S2 comparisons. Susceptibility-to-risk correspondence remained below 0.350, showing that exposure and vulnerability changed priority locations. Overall, cross-zone learning strengthens regional discrimination, while zone-constrained learning preserves environmental differences, supporting their integration.

Problem

• spatial heterogeneity
• multi-hazard
• susceptibility mapping
• risk assessment
• flood-landslide co-occurrence

Innovation

• spatial heterogeneity
• multi-hazard susceptibility
• cross-zone learning
• zone-constrained modeling
• relative-risk mapping