FL-MHSM: Spatially-adaptive Fusion and Ensemble Learning for Flood-Landslide Multi-Hazard Susceptibility Mapping at Regional Scale

2026-04-17

AI Summary

Traditional multi-hazard susceptibility mapping often neglects inter-hazard dependencies, spatial heterogeneity, and uncertainty. This study proposes a deep learning workflow for joint flood–landslide susceptibility mapping, integrating two-level spatial partitioning, probabilistic early fusion (EF), tree-based late fusion (LF), and a soft-gated mixture-of-experts (MoE) architecture. The approach innovatively incorporates a spatially adaptive fusion mechanism and an MoE framework, preserving spatial heterogeneity while enabling large-scale parallel prediction and interpretable analysis. Experiments in Kerala, India, and Nepal demonstrate that the MoE model achieves superior performance (AUC-ROC: 0.905 for floods, 0.914 for landslides) and reveals spatially varying patterns of dominant contributing factors.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Multi-modal Vision
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Existing multi-hazard susceptibility mapping (MHSM) studies often rely on spatially uniform models, treat hazards independently, and provide limited representation of cross-hazard dependence and uncertainty. To address these limitations, this study proposes a deep learning (DL) workflow for joint flood-landslide multi-hazard susceptibility mapping (FL-MHSM) that combines two-level spatial partitioning, probabilistic Early Fusion (EF), a tree-based Late Fusion (LF) baseline, and a soft-gating Mixture of Experts (MoE) model, with MoE serving as final predictive model. The proposed design preserves spatial heterogeneity through zonal partitions and enables data-parallel large-area prediction using overlapping lattice grids. In Kerala, EF remained competitive with LF, improving flood recall from 0.816 to 0.840 and reducing Brier score from 0.092 to 0.086, while MoE provided strongest performance for flood susceptibility, achieving an AUC-ROC of 0.905, recall of 0.930, and F1-score of 0.722. In Nepal, EF similarly improved flood recall from 0.820 to 0.858 and reduced Brier score from 0.057 to 0.049 relative to LF, while MoE outperformed both EF and LF for landslide susceptibility, achieving an AUC-ROC of 0.914, recall of 0.901, and F1-score of 0.559. GeoDetector analysis of MoE outputs further showed that dominant factors varied more across zones in Kerala, where susceptibility was shaped by different combinations of topographic, land-cover, and drainage-related controls, while Nepal showed a more consistent influence of topographic and glacier-related factors across zones. These findings show that EF and LF provide complementary predictive behavior, and that their spatially adaptive integration through MoE yields robust overall predictive performance for FL-MHSM while supporting interpretable characterization of multi-hazard susceptibility in spatially heterogeneous landscapes.

Problem

• multi-hazard susceptibility mapping
• spatial heterogeneity
• flood-landslide interaction
• cross-hazard dependence
• uncertainty representation

Innovation

• spatially-adaptive fusion
• multi-hazard susceptibility mapping
• Mixture of Experts (MoE)
• early-late fusion
• deep learning