PL EN
Enhancing urban flood hazard assessment: a comparative analysis of frequency ratio and xgboost models for precision risk mapping
 
More details
Hide details
1
Data Science for Sustainable Earth Laboratory (Data4Earth), Faculty of Sciences and Technics, Sultan Moulay Slimane University, 23000 Beni Mellal, Morocco
 
 
Corresponding author
Mohamed El Haou   

Data Science for Sustainable Earth Laboratory (Data4Earth), Faculty of Sciences and Technics, Sultan Moulay Slimane University, 23000 Beni Mellal, Morocco
 
 
Ecol. Eng. Environ. Technol. 2025; 3:265-284
 
KEYWORDS
TOPICS
ABSTRACT
Urban flood hazard prediction should effectively balance accuracy and interpretability. This paper compares the performances of the Frequency Ratio method, a simple statistical technique, and XGBoost, a state-of-the-art machine learning algorithm for flood Hazard mapping in Beni Mellal (Morocco). The dataset was derived from preprocessed and standardized Sentinel-2 and Landsat 8 images, a Digital Elevation Model, and geological and soil maps. A flood inventory map was produced, it was then divided into training and testing subsets in the ratio of 70:30 for model calibration and validation, respectively. The FR method highlights key geographical variables such as slope, proximity to rivers, and vegetation indices to deliver rapid, interpretable flood risk assessments. In contrast, XGBoost captures complex, nonlinear relationships by integrating natural and anthropogenic factors for precise risk mapping. The results indicate that while FR is efficient for preliminary assessments in data-scarce environments, XGBoost significantly outperforms it in accuracy, reliability, and detailed hazard differentiation. XGBoost achieved an Area Under the Curve (AUC) of 90.71% in testing datasets compared to 86.1% for FR. Flood distribution analysis showed that FR identified 21.3% of the study area as low-risk and 11.3% as very high-risk, suitable for broad evaluations. XGBoost, however, mapped 73.0% as very low-risk and 12.0% as very high-risk, making it valuable for resource-efficient interventions. This study highlights the complementary strengths of both approaches and advocates for integrating FR’s rapid insights with XGBoost’s precision. Together, they provide a robust framework for comprehensive flood hazard management in semi-arid regions, balancing strategic planning with localized interventions.
Journals System - logo
Scroll to top