article · Environmental Earth Sciences
Flash floods pose serious threats to human life and infrastructure. Research in Ibaraki prefecture, Japan, evaluated four machine learning approaches to generate flood susceptibility maps using a dataset of 224 flooded and non-flooded sites across eleven environmental factors. The predictive models were trained on seventy percent of the data and evaluated using the remaining thirty percent through receiver operating characteristic analysis. Both artificial neural network multilayer perceptron and support vector regression models demonstrated high predictive performance, scoring area under the curve values of 95.23 percent and 95.83 percent respectively. Removing plan and profile curvature terrain factors further increased the multilayer perceptron model accuracy to 96.7 percent. The resulting maps divided the territory into five hazard categories, identifying higher risk in southern areas near main watercourses and lower risk in the north.
Accurate flood susceptibility mapping helps authorities identify zones vulnerable to sudden inundation before disasters strike. By refining machine learning models and evaluating the direct impact of specific landscape features like terrain curvature, researchers can produce more reliable spatial assessments to guide land use, emergency planning, and flood mitigation measures.
This applied research demonstrates software-driven mapping tools that could aid regional planning authorities, civil protection agencies, and infrastructure developers in managing flood risks. Operating at an applied testing stage based on historical data from Ibaraki prefecture, the methodology shows high predictive accuracy, but the abstract does not indicate that operational deployment software or commercial tools have yet been established.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Flash floods stand as a substantial peril linked to climate change, imposing a severe menace to both human existence and built structures. This study aims to assess and compare the effectiveness of four distinct machine learning (ML) methodologies in the production of flood susceptibility maps (FSMs) in Ibaraki prefecture, Japan. Additionally, the investigation aims to examine the influence of excluding plan and profile curvature factors on the accuracy of the resulting maps. The dataset comprised 224 spots, consisting of 112 flooded and 112 non-flooded locations, and 11 environmental factors. The models were trained using 70% of the dataset, while the remaining 30% was utilized for model evaluation using the ROC curve method. The results indicated that both the ANN-MLP and SVR models achieved notable accuracy, with area under curve values of 95.23% and 95.83% respectively. An intriguing observation was made when the plan and profile curvature factors were excluded, as it led to an improvement in the accuracy of the ANN-MLP model, resulting in an accuracy of 96.7%. Furthermore, the generated FSMs were classified into five distinct hazard levels. The northern region of the maps predominantly exhibited very low and low hazard levels, while areas located in the southern region, closer to main streams, demonstrated considerably higher hazard levels categorized as very high and high. Ultimately, this study marks novel endeavor to investigate the impact of the curvature factor on the precision of machine learning algorithms in the creation of FSMs, which serve as fundamental tools for subsequent investigations.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s12665-024-11696-x
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
