Volume 2, Issue 2 — Year 2025 — Article e100042

Narges Mohammadian¹; Shabnam Rad²; Chia-hao Fen³; David Wang⁴; Mahdi Yeganeh⁵

1. Soil Science Department, University of Tabriz, Tabriz 5166616471, Iran
2. Department of Environmental Science, Tunghai University, Taichung 407224, Taiwan
3. Department of Environmental Science, Tunghai University, Taichung 407224, Taiwan
4. Department of Civil Engineering, I-Shou University, Kaohsiung 84001, Taiwan
5. Department of Civil Engineering, I-Shou University, Kaohsiung 84001, Taiwan

Flood energy attenuation in vegetated rivers is a critical factor in flood management and riverine ecosystem stability. This study develops an Artificial Neural Network (ANN) model to predict flood energy reduction using a dataset of 760 rivers in Iran. The dataset was divided into 70% for training and 30% for testing. A multi-layer perceptron (MLP) ANN was implemented in Python to establish the relationship between key hydraulic and vegetation parameters and energy dissipation. The input variables included the Froude number (Fr), vegetation density and thickness (Dv), and relative backwater rise (Δr), while the output parameter was energy reduction (ΔE). The model’s performance was evaluated using statistical metrics, achieving a high correlation (R² = 0.92) and a low mean absolute error (MAE = 0.025 and RMSE = 0.012), demonstrating the ANN’s strong predictive capability. Results indicate that vegetation characteristics significantly influence energy dissipation, with denser and thicker vegetation leading to greater flood energy reduction. Sensitivity analysis further highlighted the dominant role of Δr in determining energy loss. The ANN model outperformed traditional empirical methods in accuracy, proving its reliability for practical applications in flood risk assessment. These findings suggest that ANN-based modeling can be a valuable tool for hydrologists and engineers in optimizing river management strategies. Future research should focus on expanding the dataset and integrating additional hydraulic parameters to further refine prediction accuracy.

Flood energy, Vegetated rivers, Artificial neural networks, Flood prediction, Hydraulic modeling