Chafjiri, Ali S., Gheibi, Mohammad, Chahkandi, Benyamin, Eghbalian, Hamid, Waclawek, Stanislaw, Fathollahi-Fard, Amir M. and Behzadian, Kourosh ORCID: https://orcid.org/0000-0002-1459-8408 (2024) Enhancing flood risk mitigation by advanced data-driven approach. Heliyon.

Preview

PDF Chafjiri et al 2024.pdf - Published Version Available under License Creative Commons Attribution. Download (11MB) | Preview

Abstract

Flood events in the Sefidrud River basin have historically caused significant damage to infrastructure, agriculture, and human settlements, highlighting the urgent need for improved flood prediction capabilities. Traditional hydrological models have shown limitations in capturing the
complex, non-linear relationships inherent in flood dynamics. This study addresses these challenges
by leveraging advanced machine learning techniques to develop more accurate and reliable flood estimation models for the region. The study applied Random Forest (RF), Bagging, SMOreg, Multilayer Perceptron (MLP), and Adaptive Neuro-Fuzzy Inference System (ANFIS) models using historical hydrological data spanning 50 years. The methods involved splitting the data into training (50–70 %) and validation sets, processed using WEKA 3.9 software. The evaluation revealed that the nonlinear ensemble RF model achieved the highest accuracy with a correlation of 0.868 and an root mean squared error (RMSE) of 0.104. Both RF and MLP
significantly outperformed the linear SMOreg approach, demonstrating the suitability of modern machine learning techniques. Additionally, the ANFIS model achieved an exceptional R-squared accuracy of 0.99. The findings underscore the potential of data-driven models for accurate flood estimating, providing a valuable benchmark for algorithm selection in flood risk management.

Item Type:	Article
Identifier:	10.1016/j.heliyon.2024.e37758
Subjects:	Construction and engineering > Civil and environmental engineering
Depositing User:	Kourosh Behzadian
Date Deposited:	23 Sep 2024 10:11
Last Modified:	23 Sep 2024 10:15
URI:	https://repository.uwl.ac.uk/id/eprint/12708

Downloads

Actions (login required)

View Item