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

• URL: http://arxiv.org/abs/2604.16265v1
• Date: Fri, 17 Apr 2026 17:23:55 GMT
• Title: FL-MHSM: Spatially-adaptive Fusion and Ensemble Learning for Flood-Landslide Multi-Hazard Susceptibility Mapping at Regional Scale
• Abstract summary: This study proposes a deep learning (DL) workflow for joint flood-landslide multi-hazard susceptibility mapping (FL-MHSM)<n>It 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.<n>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.<n>MoE provided strongest performance for flood susceptibility, achieving an AUC-ROC of 0.905, recall of 0.930, and
• Score: 1.3607388598209322
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Spatial Heterogeneity-Aware Multi-Hazard Susceptibility and Risk Mapping at Regional Scale [1.108292291257035]
  This study develops a spatial-aware framework for flood-landslide susceptibility and relative-risk mapping in Kerala, India, and Nepal.<n>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)<n>S1 achieved higher mean accuracy, precision, recall, F1-score, AUC-ROC, and PR-AUC for both hazards and regions.<n>S2 produced lower Brier scores for both Nepal hazards and retained zone-specific differences in predictor selection, SHAP rankings, and response
  arXiv  Detail & Related papers  (2026-08-08T20:16:43Z)
• Is sub-metre resolution necessary for cocoa mapping? A landscape-stratified evaluation of very high resolution imagery, decametric Earth Observation inputs, and operational products in Cote d'Ivoire [0.5515988776731707]
  Very high resolution (VHR) imagery provides a meaningful advantage in cocoa mapping.<n>Foundation-model embeddings offer a scalable alternative for large-area mapping.<n>Targeted VHR acquisition may be particularly beneficial in complex cocoa landscapes.
  arXiv  Detail & Related papers  (2026-07-09T21:15:03Z)
• Predicting Pseudo-nitzschia harmful algal blooms along the Portuguese Coast using satellite-derived predictors [69.38367341895632]
  Pseudo-nitzschia diatoms pose recurrent risks to coastal ecosystems and harvesting along the Portuguese Atlantic coast.<n>We develop and evaluate a machine-learning framework to predict harmful algal bloom occurrence using exclusively satellite-derived predictors.
  arXiv  Detail & Related papers  (2026-07-08T18:14:24Z)
• OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization [58.03221830946145]
  We propose OmniISR, a unified framework that fuses pure CL, pure FL, and hybrid CL-FL training modes.<n>We show that OmniISR consistently improves model performance in both centralized and federated paradigms.
  arXiv  Detail & Related papers  (2026-05-19T04:13:27Z)
• Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage [65.51149575007149]
  We present Fun-DDPS, a generative framework that combines function-space diffusion models with differentiable neural operator surrogates for both forward and inverse modeling.<n>Fun-DDPS produces physically consistent realizations free from the high-frequency artifacts observed in joint-state baselines.
  arXiv  Detail & Related papers  (2026-02-12T18:58:12Z)
• Breaking the Regional Barrier: Inductive Semantic Topology Learning for Worldwide Air Quality Forecasting [99.4484686548807]
  We propose OmniAir, a semantic topology learning framework tailored for global station-level prediction.<n>Our approach effectively captures long-range non-Euclidean correlations and physical diffusion patterns across unevenly distributed global networks.<n>Experiments show that OmniAir achieves state-of-the-art performance against 18 baselines, maintaining high efficiency and scalability with speeds nearly 10 times faster than existing models.
  arXiv  Detail & Related papers  (2026-01-29T15:58:07Z)
• From Landslide Conditioning Factors to Satellite Embeddings: Evaluating the Utilisation of Google AlphaEarth for Landslide Susceptibility Mapping using Deep Learning [1.6571781613404601]
  This study evaluated the potential of Google AlphaEarth embeddings as alternative predictors for landslide susceptibility mapping.<n>AE-based models consistently outperformed LCFs across all regions and models, yielding higher F1-scores, AUC values, and more stable error distributions.
  arXiv  Detail & Related papers  (2026-01-12T07:17:43Z)
• Pix2Geomodel: A Next-Generation Reservoir Geomodeling with Property-to-Property Translation [2.004012818482403]
  This study introduces Pix2Geomodel, a novel conditional generative adversarial network (cGAN) framework based on Pix2Pix.<n>It is designed to predict reservoir properties (facies, porosity, permeability, and water saturation) from the Rotliegend reservoir of the Groningen gas field.<n>Results demonstrated high accuracy for facies (PA 0.88, FWIoU 0.85) and water saturation (PA 0.96, FWIoU 0.95), with moderate success for porosity (PA 0.70, FWIoU 0.55) and permeability (PA 0.74, FWIoU 0.60), and robust translation performance
  arXiv  Detail & Related papers  (2025-06-21T15:58:27Z)
• ReconMOST: Multi-Layer Sea Temperature Reconstruction with Observations-Guided Diffusion [48.540756751934836]
  ReconMOST is a data-driven guided diffusion model framework for multi-layer sea temperature reconstruction.<n>Our method extends ML-based SST reconstruction to a global, multi-layer setting, handling over 92.5% missing data.
  arXiv  Detail & Related papers  (2025-06-12T06:27:22Z)
• Field-scale soil moisture estimated from Sentinel-1 SAR data using a knowledge-guided deep learning approach [6.595840767689357]
  This research presents preliminary efforts for developing a knowledge-guided deep learning approach.<n>It integrates the water cloud model (WCM) principles into a long short-term memory (LSTM) model.<n>Our proposed approach builds upon the soil backscatter coefficients isolated from the total backscatter, together with Landsat-resolution vegetation information and surface characteristics.<n>Results showed the proposed approach reduced SM retrieval by 0.02 m$3$/m$3$ and achieved correlation coefficients (R) of up to 0.64 in areas with varying vegetation cover and surface conditions.
  arXiv  Detail & Related papers  (2025-05-01T03:12:25Z)
• Empirical Upscaling of Point-scale Soil Moisture Measurements for Spatial Evaluation of Model Simulations and Satellite Retrievals [6.595840767689357]
  In this study, we presented an upscaling approach that combines fusion with machine learning to extrapolate point-scale SM measurements to a 100 mpixel resolution. We conducted a four-fold cross-validation, which consistently demonstrated comparable correlation performance across folds, ranging from 0.6 to 0.9. The proposed approach was further validated based on a cross-cluster strategy by using two spatial subsets within the study area.
  arXiv  Detail & Related papers  (2024-04-08T06:49:59Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• Landslide Susceptibility Prediction Modeling Based on Self-Screening Deep Learning Model [9.7723814375467]
  A self-screening graph convolutional network and long short-term memory network (SGCN-LSTM) is proposed in this paper. The landslide samples with large errors outside the set threshold interval are eliminated by self-screening network. The nonlinear relationship between environmental factors can be extracted from both spatial nodes and time series.
  arXiv  Detail & Related papers  (2023-04-12T10:31:03Z)
• Pseudo-Spherical Contrastive Divergence [119.28384561517292]
  We propose pseudo-spherical contrastive divergence (PS-CD) to generalize maximum learning likelihood of energy-based models. PS-CD avoids the intractable partition function and provides a generalized family of learning objectives.
  arXiv  Detail & Related papers  (2021-11-01T09:17:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.