Spatial Asymmetry in Topographic Controls on Flood Intensity: A Machine Learning Investigation of the Chi River Floodplain, 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, University of Arizona, 1209 E. Second St., Tucson, AZ 85721, USA
Abstract
Understanding how landscape form influences inundation severity remains central to flood hazard assessment, yet many assumed relationships lack empirical scrutiny. We investigated whether five topographic attributes—elevation, slope, topographic wetness index, latitude, and longitude—could predict cumulative flood intensity across 541 hexagonal cells in Thailand’s Chi River floodplain. Using Random Forest regression and SHAP analysis, we identified three distinct asymmetries that challenge conventional assumptions. Elevation dominated predictions (58.5% importance) but operated through a sharp threshold near 150 m rather than a smooth gradient. Below 145 m, flood intensity was consistently high regardless of other factors; above 155 m, it was uniformly low. The flood-amplifying effect of low-lying terrain (+200 SHAP units) far outweighed the protective benefit of high ground (−100 SHAP units). More strikingly, the Topographic Wetness Index—a widely used theoretical measure of wetness potential—showed negligible correlation with observed flooding (r = 0.109) and contributed only 5.6% to predictive performance. Linear regression models captured barely 30% of the variance (R2 ≈ 0.305), whereas Random Forest explained 77.6% (R2 = 0.7765), a performance gap that quantifies the degree of non-linearity in the system. Spatial cross-validation confirmed generalizability (R2 = 0.583). The elevation threshold offers a straightforward zoning framework: high-risk areas below 145 m, transitional zones from 145 to 155 m, and low-risk areas above 155 m. We conclude that theoretical indices require empirical validation and that combining machine learning with symmetry-based reasoning can expose hidden structures in environmental systems that linear approaches miss.
Related
- Flood susceptibility in a coastal backwater floodplain: a spatially validated multi-event SAR framework for Alappuzha, India
- A process-based framework for diagnosing floodplain ecological functioning to guide riverine wetland restoration
- Assessing SWOT capabilities for monitoring floodplain water dynamics in the Paraná Basin
- The Murray-Darling Basin Floodplain Inundation Model (MDB-FIM)
- Hydrological connectivity regulates CO2 and CH4 emissions from a temperate, natural river-floodplain system
BibTeX
@article{buasri2026spatial,
title = {{Spatial Asymmetry in Topographic Controls on Flood Intensity: A Machine Learning Investigation of the Chi River Floodplain, Thailand}},
author = {Nutchanat Buasri and Patiwat Littidej and Benjamabhorn Pumhirunroj and D. C. Slack},
journal = {Symmetry},
year = {2026},
month = jul,
doi = {10.3390/sym18071231},
url = {https://doi.org/10.3390/sym18071231},
note = {CC BY},
}
RIS
TY - JOUR
TI - Spatial Asymmetry in Topographic Controls on Flood Intensity: A Machine Learning Investigation of the Chi River Floodplain, Thailand
AU - Nutchanat Buasri
AU - Patiwat Littidej
AU - Benjamabhorn Pumhirunroj
AU - D. C. Slack
PY - 2026
DA - 2026/07/21
JO - Symmetry
DO - 10.3390/sym18071231
UR - https://doi.org/10.3390/sym18071231
AB - Understanding how landscape form influences inundation severity remains central to flood hazard assessment, yet many assumed relationships lack empirical scrutiny. We investigated whether five topographic attributes—elevation, slope, topographic wetness index, latitude, and longitude—could predict cumulative flood intensity across 541 hexagonal cells in Thailand’s Chi River floodplain. Using Random Forest regression and SHAP analysis, we identified three distinct asymmetries that challenge conventional assumptions. Elevation dominated predictions (58.5% importance) but operated through a sharp threshold near 150 m rather than a smooth gradient. Below 145 m, flood intensity was consistently high regardless of other factors; above 155 m, it was uniformly low. The flood-amplifying effect of low-lying terrain (+200 SHAP units) far outweighed the protective benefit of high ground (−100 SHAP units). More strikingly, the Topographic Wetness Index—a widely used theoretical measure of wetness potential—showed negligible correlation with observed flooding (r = 0.109) and contributed only 5.6% to predictive performance. Linear regression models captured barely 30% of the variance (R2 ≈ 0.305), whereas Random Forest explained 77.6% (R2 = 0.7765), a performance gap that quantifies the degree of non-linearity in the system. Spatial cross-validation confirmed generalizability (R2 = 0.583). The elevation threshold offers a straightforward zoning framework: high-risk areas below 145 m, transitional zones from 145 to 155 m, and low-risk areas above 155 m. We conclude that theoretical indices require empirical validation and that combining machine learning with symmetry-based reasoning can expose hidden structures in environmental systems that linear approaches miss.
SN - 2073-8994
ER -