Document Type : Original Research Paper
Authors
1 Department of Geospatial Information Systems , Faculty of Surveying Engineering, K. N.Toosi University of Technology, Tehran, Iran
2 Department of Physical Geography and Bolin Centre for Climate Research, Stockholm University, Stockholm, Sweden
Abstract
Barckground and Objectives: Iran's northern provinces (Golestan, Mazandaran, and Gilan) lie along the Caspian Sea and combine humid climate, steep Alborz topography, intensive groundwater extraction for agriculture, and rapid land-use change, making them simultaneously exposed to floods, landslides, and land subsidence. Despite this co-occurrence, most prior studies have addressed each hazard in isolation, providing limited insight into where these threats overlap spatially and how they should be jointly managed at the regional scale. Existing susceptibility models often rely on single machine learning algorithms without systematic hyperparameter tuning and treat their predictions as opaque outputs, limiting their value for evidence-based decision-making and undermining stakeholder trust. This research aims to develop an optimized and interpretable framework that produces joint susceptibility maps for all three hazards across this region, supporting integrated risk planning and informed land-use policy.
Methods: A hybrid model combining Support Vector Regression with the Two-phase Mutation Grey Wolf Optimizer (SVR-TMGWO) was built separately for each hazard. Twenty years of recorded flood and landslide events (2000–2020) were compiled from the Geological Survey of Iran and the national watershed-management authority, while subsidence locations were derived from Sentinel-1 InSAR analyses. Non-event points were generated randomly outside a 2000-metre buffer around recorded events at a 1:1 ratio to preserve class balance, and the dataset was partitioned into 70% training and 30% testing within K-means clusters (with the optimal K determined via Gap and Silhouette analyses) so that the feature-space distribution was balanced across both subsets. Eighteen conditioning factors spanning topographic, hydrological, environmental, anthropogenic, and soil-physical variables were prepared for each pixel. The TMGWO algorithm simultaneously tuned the three SVR hyperparameters (C, ε, γ) for each hazard, producing distinct configurations that reflect the differing physics of each process. Model accuracy was evaluated using AUC-ROC, RMSE, R², and adjusted R² on independent test data. To overcome the black-box limitation of machine learning, Shapley Additive Explanations (SHAP) were computed at both global and local scales, exposing the contribution of each conditioning factor to the prediction at the regional level and at individual locations. Finally, the three single-hazard maps were combined into an eight-class multi-hazard map identifying areas of single, dual, and triple hazard overlap.
Findings: TMGWO consistently improved test-phase AUC-ROC over the base SVR model, reaching 0.8404 for flood, 0.9329 for landslide, and 0.9642 for subsidence, while narrowing the training-test gap and indicating reduced overfitting compared with the unoptimized baseline. SHAP identified elevation as the leading driver across all three hazards but revealed contrasting secondary controls per process. The multi-hazard map showed that triple-overlap zones were spatially restricted and concentrated along the mountain-plain transition.
Conclusion: The proposed SVR-TMGWO framework, combined with SHAP interpretability, produced spatially explicit and physically meaningful susceptibility maps for three coexisting hazards in northern Iran. The resulting eight-class multi-hazard product highlights priority areas for integrated land-use planning, infrastructure protection, and early-warning prioritisation, while the SHAP outputs make the model's reasoning transparent to non-expert stakeholders. Future research should incorporate temporal dynamics through multi-temporal InSAR and climate projections, compare deep learning alternatives such as convolutional neural networks, and extend the framework to full risk assessment by including exposure and vulnerability components.
Keywords
- Multi-hazard susceptibility
- Support Vector Regression
- Grey Wolf Optimizer Explainable Machine Learning
- Northern Provinces of Iran
Main Subjects
COPYRIGHTS
© 2026 The Author(s). This is an open-access article distributed under the terms and conditions of the Creative Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
)