article · Remote Sensing
Mapping flood susceptibility is vital for flood risk management and mitigation planning. High-resolution synthetic aperture radar imagery was combined with machine learning models to assess flood hazards in the Metlili watershed in northwestern Morocco. Twelve environmental conditioning factors, spanning topography, hydrology, infrastructure, geology, rainfall, and vegetation, served as model inputs. Four predictive algorithms were evaluated: Random Forest, Classification and Regression Trees, Support Vector Machine, and Extreme Gradient Boosting. Using an area under the curve metric on a validation dataset, Random Forest demonstrated the highest predictive capability, followed by the tree-based, vector machine, and gradient boosting approaches. Under the best-performing model, nearly half of the watershed fell into high or very high flood susceptibility categories, with over thirty-one per cent classed as very highly susceptible. The methodology demonstrates that combining radar data with machine learning can effectively identify flood-prone zones in comparable geographical settings.
Flooding poses severe risks to human settlements, infrastructure, and local economies. Accurately identifying zones prone to inundation allows planners and decision-makers to design targeted flood mitigation strategies and allocate resources effectively. By showing that radar imagery combined with machine learning models can map hazard zones across a watershed, this research offers a practical technical approach for assessing flood vulnerability in similar environments.
This methodology represents applied and tested research suitable for environmental planning and flood risk assessment. Potential end users include regional water basin authorities, municipal planners, and disaster management organisations seeking to locate hazardous areas. While demonstrated within a specific watershed using standard machine learning software, real-world deployment for commercial consulting or municipal risk monitoring would require adapting the workflow to local data pipelines and regional infrastructure.
AI-generated from the published abstract. Always read the original work before citing.
Flood susceptibility mapping plays a crucial role in flood risk assessment and management. Accurate identification of areas prone to flooding is essential for implementing effective mitigation measures and informing decision-making processes. In this regard, the present study used high-resolution remote sensing products, i.e., synthetic aperture radar (SAR) images for flood inventory preparation and integrated four machine learning models (Random Forest: RF, Classification and Regression Trees: CART, Support Vector Machine: SVM, and Extreme Gradient Boosting: XGBoost) to predict flood susceptibility in Metlili watershed, Morocco. Initially, 12 independent variables (elevation, slope angle, aspect, plan curvature, topographic wetness index, stream power index, distance from streams, distance from roads, lithology, rainfall, land use/land cover, and normalized vegetation index) were used as conditioning factors. The flood inventory dataset was divided into 70% and 30% for training and validation purposes using a popular library, scikit-learn (i.e., train_test_split) in Python programming language. Additionally, the area under the curve (AUC) was used to evaluate the performance of the models. The accuracy assessment results showed that RF, CART, SVM, and XGBoost models predicted flood susceptibility with AUC values of 0.807, 0.780, 0.756, and 0.727, respectively. However, the RF model performed better at flood susceptibility prediction compared to the other models applied. As per this model, 22.49%, 16.02%, 12.67%, 18.10%, and 31.70% areas of the watershed are estimated as being very low, low, moderate, high, and very highly susceptible to flooding, respectively. Therefore, this study showed that the integration of machine learning models with radar data could have promising results in predicting flood susceptibility in the study area and other similar environments.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/rs16050858
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.
