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.

翻译：现有针对多灾种易感性制图（MHSM）的研究通常依赖空间均匀模型，将各灾种视为独立事件，且对灾种间依赖关系及不确定性的表征能力有限。为克服上述局限，本研究提出了一种面向洪涝-滑坡联合多灾种易感性制图（FL-MHSM）的深度学习（DL）工作流，该工作流融合了两级空间分区、概率早期融合（EF）、基于树模型的晚期融合（LF）基线方法，以及基于软门控机制的混合专家模型（MoE），并以MoE作为最终预测模型。所提设计通过分区的方式保留了空间异质性，并利用重叠格网网格实现了大规模区域的数据并行预测。在喀拉拉邦（Kerala）的实验中，EF保持了与LF相当的性能，将洪涝召回率从0.816提升至0.840，并将Brier分数从0.092降低至0.086，而MoE在洪涝易感性预测上表现最优，获得了0.905的AUC-ROC、0.930的召回率和0.722的F1分数。在尼泊尔的实验中，相较于LF，EF同样将洪涝召回率从0.820提升至0.858，并将Brier分数从0.057降低至0.049，同时MoE在滑坡易感性预测上优于EF和LF，获得了0.914的AUC-ROC、0.901的召回率和0.559的F1分数。基于GeoDetector方法对MoE输出的进一步分析表明，喀拉拉邦的不同区域内主导影响因子更具差异性，其易感性由地形、土地覆盖和排水相关控制因素的不同组合共同塑造；而尼泊尔各地形区内则呈现出地形因子与冰川相关因子更为一致的显著影响。上述发现表明，EF和LF具有互补的预测行为，通过MoE进行空间自适应集成，可在支持空间异质性景观中多灾种易感性可解释表征的同时，为FL-MHSM提供稳健的整体预测性能。