Flood susceptibility mapping in the Yom River Basin, Thailand: stacking ensemble learning using multi-year flood inventory data

Accurate assessment models of flood susceptibility are crucial for informing risk management strategies related to severe threats posed by floods. This study assessed flood susceptibility in the Yom River Basin, Thailand, using conventional and ML methods. SE was compared with KNN, SVM, DT, RF, and...

Full description

Saved in:
Bibliographic Details
Main Authors: Gen Long, Sarintip Tantanee, Korakod Nusit, Pitikhate Sooraksa
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Geocarto International
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/10106049.2025.2461531
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850256166221774848
author Gen Long
Sarintip Tantanee
Korakod Nusit
Pitikhate Sooraksa
author_facet Gen Long
Sarintip Tantanee
Korakod Nusit
Pitikhate Sooraksa
author_sort Gen Long
collection DOAJ
description Accurate assessment models of flood susceptibility are crucial for informing risk management strategies related to severe threats posed by floods. This study assessed flood susceptibility in the Yom River Basin, Thailand, using conventional and ML methods. SE was compared with KNN, SVM, DT, RF, and a Stacking ensemble model (SVM, DT, RF). A point-based flood inventory was sampled from multi-year flood polygons using a method considering flood frequency and inundation size. Results showed all ML models, except KNN, outperformed SE. RF achieved AUCs of 96.0% (test) and 96.1% (verification), while Stacking achieved 99.9% (test) and 96.1% (verification). Stacking also outperformed in accuracy (0.982, 0.893), precision (0.974, 0.915), F1 (0.990, 0.866), sensitivity (0.982, 0.890), specificity (0.974, 0.920), and kappa (0.964, 0.786). These findings highlight the potential of using ensemble ML techniques to significantly improve flood susceptibility mapping and risk management in data-limited regions such as the Yom River Basin.
format Article
id doaj-art-0fc611a0edb44765a2d19679fb2341a7
institution OA Journals
issn 1010-6049
1752-0762
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Geocarto International
spelling doaj-art-0fc611a0edb44765a2d19679fb2341a72025-08-20T01:56:42ZengTaylor & Francis GroupGeocarto International1010-60491752-07622025-12-0140110.1080/10106049.2025.2461531Flood susceptibility mapping in the Yom River Basin, Thailand: stacking ensemble learning using multi-year flood inventory dataGen Long0Sarintip Tantanee1Korakod Nusit2Pitikhate Sooraksa3Civil of Engineering Department, Faculty of Engineering, Naresuan University, Phitsanulok, ThailandCenter of Excellence on Energy Technology and Environment, Faculty of Engineering, Naresuan University, Phitsanulok, ThailandCivil of Engineering Department, Faculty of Engineering, Naresuan University, Phitsanulok, ThailandDepartment of Robotics and AI, School of Engineering, King Mongkut’s Institute of Technology, Ladkrabang, Bangkok, ThailandAccurate assessment models of flood susceptibility are crucial for informing risk management strategies related to severe threats posed by floods. This study assessed flood susceptibility in the Yom River Basin, Thailand, using conventional and ML methods. SE was compared with KNN, SVM, DT, RF, and a Stacking ensemble model (SVM, DT, RF). A point-based flood inventory was sampled from multi-year flood polygons using a method considering flood frequency and inundation size. Results showed all ML models, except KNN, outperformed SE. RF achieved AUCs of 96.0% (test) and 96.1% (verification), while Stacking achieved 99.9% (test) and 96.1% (verification). Stacking also outperformed in accuracy (0.982, 0.893), precision (0.974, 0.915), F1 (0.990, 0.866), sensitivity (0.982, 0.890), specificity (0.974, 0.920), and kappa (0.964, 0.786). These findings highlight the potential of using ensemble ML techniques to significantly improve flood susceptibility mapping and risk management in data-limited regions such as the Yom River Basin.https://www.tandfonline.com/doi/10.1080/10106049.2025.2461531Flood susceptibilityflood hazardflood riskmachine learningensemble machine learninghybrid modelling
spellingShingle Gen Long
Sarintip Tantanee
Korakod Nusit
Pitikhate Sooraksa
Flood susceptibility mapping in the Yom River Basin, Thailand: stacking ensemble learning using multi-year flood inventory data
Geocarto International
Flood susceptibility
flood hazard
flood risk
machine learning
ensemble machine learning
hybrid modelling
title Flood susceptibility mapping in the Yom River Basin, Thailand: stacking ensemble learning using multi-year flood inventory data
title_full Flood susceptibility mapping in the Yom River Basin, Thailand: stacking ensemble learning using multi-year flood inventory data
title_fullStr Flood susceptibility mapping in the Yom River Basin, Thailand: stacking ensemble learning using multi-year flood inventory data
title_full_unstemmed Flood susceptibility mapping in the Yom River Basin, Thailand: stacking ensemble learning using multi-year flood inventory data
title_short Flood susceptibility mapping in the Yom River Basin, Thailand: stacking ensemble learning using multi-year flood inventory data
title_sort flood susceptibility mapping in the yom river basin thailand stacking ensemble learning using multi year flood inventory data
topic Flood susceptibility
flood hazard
flood risk
machine learning
ensemble machine learning
hybrid modelling
url https://www.tandfonline.com/doi/10.1080/10106049.2025.2461531
work_keys_str_mv AT genlong floodsusceptibilitymappingintheyomriverbasinthailandstackingensemblelearningusingmultiyearfloodinventorydata
AT sarintiptantanee floodsusceptibilitymappingintheyomriverbasinthailandstackingensemblelearningusingmultiyearfloodinventorydata
AT korakodnusit floodsusceptibilitymappingintheyomriverbasinthailandstackingensemblelearningusingmultiyearfloodinventorydata
AT pitikhatesooraksa floodsusceptibilitymappingintheyomriverbasinthailandstackingensemblelearningusingmultiyearfloodinventorydata