Applying Machine Learning Algorithms for Spatial Modeling of Flood Susceptibility Prediction over São Paulo Sub-Region

Floods are among the most destructive natural hazards globally, necessitating the identification of flood-prone areas for effective disaster risk management and sustainable urban development. Advanced data-driven techniques, including machine learning (ML), are increasingly used to map and mitigate...

Full description

Saved in:
Bibliographic Details
Main Authors: Temitope Seun Oluwadare, Marina Pannunzio Ribeiro, Dongmei Chen, Masoud Babadi Ataabadi, Saba Hosseini Tabesh, Abiodun Esau Daomi
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Land
Subjects:
Online Access:https://www.mdpi.com/2073-445X/14/5/985
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850125938579210240
author Temitope Seun Oluwadare
Marina Pannunzio Ribeiro
Dongmei Chen
Masoud Babadi Ataabadi
Saba Hosseini Tabesh
Abiodun Esau Daomi
author_facet Temitope Seun Oluwadare
Marina Pannunzio Ribeiro
Dongmei Chen
Masoud Babadi Ataabadi
Saba Hosseini Tabesh
Abiodun Esau Daomi
author_sort Temitope Seun Oluwadare
collection DOAJ
description Floods are among the most destructive natural hazards globally, necessitating the identification of flood-prone areas for effective disaster risk management and sustainable urban development. Advanced data-driven techniques, including machine learning (ML), are increasingly used to map and mitigate flood risks. However, ML applications for flood risk assessment remain limited in Sorocaba, a sub-region of São Paulo, Brazil. This study employs four ML algorithms—differential evolution (DE), naïve Bayes (NB), random forest (RF), and support vector machines (SVMs)—to develop flood susceptibility models using 16 predictor variables. Key categorical factors influencing flood susceptibility included topographical, anthropogenic, and hydrometeorological, particularly elevation, slope, NDVI, NDWI, and distance to roads. Performance metrics (F1-score and AUC) showed strong results, ranging from 0.94 to 1.00, with the DE and RF models excelling in training, testing, and external datasets. The study highlights model transferability, demonstrating applicability to other regions. Findings reveal that 41% to 50% of Sorocaba is at high flood risk. The explainable artificial intelligence technique Shapley additive explanations (SHAP) further identified moisture and the stream power index (SPI) as significant factors influencing flood occurrence. The study underscores the ML-based model’s potential in highlighting flood-vulnerable areas and guiding flood mitigation strategies, land-use planning, and infrastructure resilience.
format Article
id doaj-art-e0969bd25599436db90fbda56612b8a0
institution OA Journals
issn 2073-445X
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Land
spelling doaj-art-e0969bd25599436db90fbda56612b8a02025-08-20T02:34:01ZengMDPI AGLand2073-445X2025-05-0114598510.3390/land14050985Applying Machine Learning Algorithms for Spatial Modeling of Flood Susceptibility Prediction over São Paulo Sub-RegionTemitope Seun Oluwadare0Marina Pannunzio Ribeiro1Dongmei Chen2Masoud Babadi Ataabadi3Saba Hosseini Tabesh4Abiodun Esau Daomi5Geographic Information and Spatial Analysis Laboratory, Department of Geography and Planning, Queen’s University, Kingston, ON K7L 3N6, CanadaGeographic Information and Spatial Analysis Laboratory, Department of Geography and Planning, Queen’s University, Kingston, ON K7L 3N6, CanadaGeographic Information and Spatial Analysis Laboratory, Department of Geography and Planning, Queen’s University, Kingston, ON K7L 3N6, CanadaGeographic Information and Spatial Analysis Laboratory, Department of Geography and Planning, Queen’s University, Kingston, ON K7L 3N6, CanadaGeographic Information and Spatial Analysis Laboratory, Department of Geography and Planning, Queen’s University, Kingston, ON K7L 3N6, CanadaNational Space Research and Development Agency, Centre for Geodesy and Geodynamics, Toro 740103, NigeriaFloods are among the most destructive natural hazards globally, necessitating the identification of flood-prone areas for effective disaster risk management and sustainable urban development. Advanced data-driven techniques, including machine learning (ML), are increasingly used to map and mitigate flood risks. However, ML applications for flood risk assessment remain limited in Sorocaba, a sub-region of São Paulo, Brazil. This study employs four ML algorithms—differential evolution (DE), naïve Bayes (NB), random forest (RF), and support vector machines (SVMs)—to develop flood susceptibility models using 16 predictor variables. Key categorical factors influencing flood susceptibility included topographical, anthropogenic, and hydrometeorological, particularly elevation, slope, NDVI, NDWI, and distance to roads. Performance metrics (F1-score and AUC) showed strong results, ranging from 0.94 to 1.00, with the DE and RF models excelling in training, testing, and external datasets. The study highlights model transferability, demonstrating applicability to other regions. Findings reveal that 41% to 50% of Sorocaba is at high flood risk. The explainable artificial intelligence technique Shapley additive explanations (SHAP) further identified moisture and the stream power index (SPI) as significant factors influencing flood occurrence. The study underscores the ML-based model’s potential in highlighting flood-vulnerable areas and guiding flood mitigation strategies, land-use planning, and infrastructure resilience.https://www.mdpi.com/2073-445X/14/5/985flood spatial modelingflood susceptibility mappingmachine learningnatural hazardsflood prediction
spellingShingle Temitope Seun Oluwadare
Marina Pannunzio Ribeiro
Dongmei Chen
Masoud Babadi Ataabadi
Saba Hosseini Tabesh
Abiodun Esau Daomi
Applying Machine Learning Algorithms for Spatial Modeling of Flood Susceptibility Prediction over São Paulo Sub-Region
Land
flood spatial modeling
flood susceptibility mapping
machine learning
natural hazards
flood prediction
title Applying Machine Learning Algorithms for Spatial Modeling of Flood Susceptibility Prediction over São Paulo Sub-Region
title_full Applying Machine Learning Algorithms for Spatial Modeling of Flood Susceptibility Prediction over São Paulo Sub-Region
title_fullStr Applying Machine Learning Algorithms for Spatial Modeling of Flood Susceptibility Prediction over São Paulo Sub-Region
title_full_unstemmed Applying Machine Learning Algorithms for Spatial Modeling of Flood Susceptibility Prediction over São Paulo Sub-Region
title_short Applying Machine Learning Algorithms for Spatial Modeling of Flood Susceptibility Prediction over São Paulo Sub-Region
title_sort applying machine learning algorithms for spatial modeling of flood susceptibility prediction over sao paulo sub region
topic flood spatial modeling
flood susceptibility mapping
machine learning
natural hazards
flood prediction
url https://www.mdpi.com/2073-445X/14/5/985
work_keys_str_mv AT temitopeseunoluwadare applyingmachinelearningalgorithmsforspatialmodelingoffloodsusceptibilitypredictionoversaopaulosubregion
AT marinapannunzioribeiro applyingmachinelearningalgorithmsforspatialmodelingoffloodsusceptibilitypredictionoversaopaulosubregion
AT dongmeichen applyingmachinelearningalgorithmsforspatialmodelingoffloodsusceptibilitypredictionoversaopaulosubregion
AT masoudbabadiataabadi applyingmachinelearningalgorithmsforspatialmodelingoffloodsusceptibilitypredictionoversaopaulosubregion
AT sabahosseinitabesh applyingmachinelearningalgorithmsforspatialmodelingoffloodsusceptibilitypredictionoversaopaulosubregion
AT abiodunesaudaomi applyingmachinelearningalgorithmsforspatialmodelingoffloodsusceptibilitypredictionoversaopaulosubregion