Spatio-Temporal Machine Learning for Flood Risk Assessment Under SSP Scenarios: A Case Study of Maha Sarakham, Thailand
- 1Research Unit of Geoinformatics for Spatial Management, Department of Geoinformatics, Faculty of Informatics, Mahasarakham University, Maha Sarakham 44150, Thailand
- 2Program in Animal Science, Faculty of Agricultural Technology, Sakon Nakhon Rajabhat University, Sakon Nakhon 47000, Thailand
- 3Department of Civil & Architectural Engineering & Mechanics, 1209 E. Second St., P.O. Box 210072, Tucson, AZ 85721, USA
Abstract
Flooding is a destructive natural hazard intensified by climate change, posing challenges to sustainable disaster risk management. This study developed and evaluated machine learning models for flood severity prediction within a hexagonal grid system (H3, resolution 8) under rainy season conditions in Maha Sarakham, Thailand. Four models Random Forest (RF), XGBoost, Gradient Boosting (GB), and Support Vector Machine (SVM) were trained using 11 environmental variables across historical years (2018, 2021, 2022) and tested on a projected year (2025) under SSP scenarios. XGBoost demonstrated the most stable performance (accuracy > 0.95 across all years), while SVM achieved high historical accuracy (0.970 average) but failed to detect positive flood cases in 2025 (recall = 0), highlighting the importance of temporal validation. Topographic variables were the most consistent predictors, but NSMI (soil moisture) emerged as the top SHAP predictor in 2025 (r = 0.52), suggesting a shift in flood-generating mechanisms under climate change. A polarization pattern was observed: flood-affected area declined to 6.8% in 2025 (79% reduction from 2022), yet maximum flood point counts remained high at 14.0, indicating more concentrated but intense flooding. Under SSP projections, using the historical baseline (27.5%), SSP1-2.6 (45.2%) and SSP2-4.5 (45.0%) indicate increased flood risk relative to the historical baseline through 2040. The SSP5-8.5 projection (3.4%) is identified as a model extrapolation artifact through formal out-of-distribution assessment (Mahalanobis distance = 8.72, p < 0.001) and is therefore excluded from policy recommendations. Although GRU and LSTM achieved marginally higher AUC values in retrospective validation, we recommend XGBoost for operational forecasting due to its temporal stability, computational efficiency, and interpretability. We further recommend integrating real-time soil moisture monitoring into early warning systems and shifting to hotspot-targeted adaptation strategies.
Related
- Future Mediterranean agrivoltaics: prospective life cycle assessment under climatic and socio-economic scenarios
- Deep learning-based downscaling of PM2.5, NO2 and O3 over Europe across emission-reduction scenarios
- A machine learning model for early season wildfire risk in Ghana’s Guinea savannah assessing discrimination, operational prevalence, spatial transferability, and CMIP6 climate scenarios
- Seasonal variation and human health risk assessment of heavy metals in settled indoor dust from an informal e-waste recycling community in Thailand.
- Spatial Asymmetry in Topographic Controls on Flood Intensity: A Machine Learning Investigation of the Chi River Floodplain, Thailand
BibTeX
@article{prasertsri2026spatiotemporal,
title = {{Spatio-Temporal Machine Learning for Flood Risk Assessment Under SSP Scenarios: A Case Study of Maha Sarakham, Thailand}},
author = {Narueset Prasertsri and Patiwat Littidej and Benjamabhorn Pumhirunroj and D. C. Slack},
journal = {Sustainability},
year = {2026},
month = jul,
doi = {10.3390/su18157550},
url = {https://doi.org/10.3390/su18157550},
note = {CC BY},
}
RIS
TY - JOUR
TI - Spatio-Temporal Machine Learning for Flood Risk Assessment Under SSP Scenarios: A Case Study of Maha Sarakham, Thailand
AU - Narueset Prasertsri
AU - Patiwat Littidej
AU - Benjamabhorn Pumhirunroj
AU - D. C. Slack
PY - 2026
DA - 2026/07/24
JO - Sustainability
DO - 10.3390/su18157550
UR - https://doi.org/10.3390/su18157550
AB - Flooding is a destructive natural hazard intensified by climate change, posing challenges to sustainable disaster risk management. This study developed and evaluated machine learning models for flood severity prediction within a hexagonal grid system (H3, resolution 8) under rainy season conditions in Maha Sarakham, Thailand. Four models Random Forest (RF), XGBoost, Gradient Boosting (GB), and Support Vector Machine (SVM) were trained using 11 environmental variables across historical years (2018, 2021, 2022) and tested on a projected year (2025) under SSP scenarios. XGBoost demonstrated the most stable performance (accuracy > 0.95 across all years), while SVM achieved high historical accuracy (0.970 average) but failed to detect positive flood cases in 2025 (recall = 0), highlighting the importance of temporal validation. Topographic variables were the most consistent predictors, but NSMI (soil moisture) emerged as the top SHAP predictor in 2025 (r = 0.52), suggesting a shift in flood-generating mechanisms under climate change. A polarization pattern was observed: flood-affected area declined to 6.8% in 2025 (79% reduction from 2022), yet maximum flood point counts remained high at 14.0, indicating more concentrated but intense flooding. Under SSP projections, using the historical baseline (27.5%), SSP1-2.6 (45.2%) and SSP2-4.5 (45.0%) indicate increased flood risk relative to the historical baseline through 2040. The SSP5-8.5 projection (3.4%) is identified as a model extrapolation artifact through formal out-of-distribution assessment (Mahalanobis distance = 8.72, p < 0.001) and is therefore excluded from policy recommendations. Although GRU and LSTM achieved marginally higher AUC values in retrospective validation, we recommend XGBoost for operational forecasting due to its temporal stability, computational efficiency, and interpretability. We further recommend integrating real-time soil moisture monitoring into early warning systems and shifting to hotspot-targeted adaptation strategies.
SN - 2071-1050
ER -