Data-driven forecasting and modeling of runoff flow to reduce flood risk using a novel hybrid wavelet-neural network based on feature extraction

The reliable forecasting of river flow plays a key role in reducing the risk of floods. Regarding nonlinear and variable characteristics of hydraulic processes, the use of data-driven and hybrid methods has become more noticeable. Thus, this paper proposes a novel hybrid wavelet-neural network (WNN)...

Full description

Bibliographic Details
Main Authors: Malekpour Heydari, Salimeh, Mohd Aris, Teh Noranis, Yaakob, Razali, Hamdan, Hazlina
Format: Article
Published: Multidisciplinary Digital Publishing Institute 2021
Online Access:http://psasir.upm.edu.my/id/eprint/96598/
_version_ 1848862404283203584
author Malekpour Heydari, Salimeh
Mohd Aris, Teh Noranis
Yaakob, Razali
Hamdan, Hazlina
author_facet Malekpour Heydari, Salimeh
Mohd Aris, Teh Noranis
Yaakob, Razali
Hamdan, Hazlina
author_sort Malekpour Heydari, Salimeh
building UPM Institutional Repository
collection Online Access
description The reliable forecasting of river flow plays a key role in reducing the risk of floods. Regarding nonlinear and variable characteristics of hydraulic processes, the use of data-driven and hybrid methods has become more noticeable. Thus, this paper proposes a novel hybrid wavelet-neural network (WNN) method with feature extraction to forecast river flow. To do this, initially, the collected data are analyzed by the wavelet method. Then, the number of inputs to the ANN is determined using feature extraction, which is based on energy, standard deviation, and maximum values of the analyzed data. The proposed method has been analyzed by different input and various structures for daily, weekly, and monthly flow forecasting at Ellen Brook river station, western Australia. Furthermore, the mean squares error (MSE), root mean square error (RMSE), and the Nash-Sutcliffe efficiency (NSE) is used to evaluate the performance of the suggested method. Furthermore, the obtained findings were compared to those of other models and methods in order to examine the performance and efficiency of the feature extraction process. It was discovered that the proposed feature extraction model outperformed their counterparts, especially when it came to long-term forecasting.
first_indexed 2025-11-15T13:16:29Z
format Article
id upm-96598
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T13:16:29Z
publishDate 2021
publisher Multidisciplinary Digital Publishing Institute
recordtype eprints
repository_type Digital Repository
spelling upm-965982023-01-11T08:24:43Z http://psasir.upm.edu.my/id/eprint/96598/ Data-driven forecasting and modeling of runoff flow to reduce flood risk using a novel hybrid wavelet-neural network based on feature extraction Malekpour Heydari, Salimeh Mohd Aris, Teh Noranis Yaakob, Razali Hamdan, Hazlina The reliable forecasting of river flow plays a key role in reducing the risk of floods. Regarding nonlinear and variable characteristics of hydraulic processes, the use of data-driven and hybrid methods has become more noticeable. Thus, this paper proposes a novel hybrid wavelet-neural network (WNN) method with feature extraction to forecast river flow. To do this, initially, the collected data are analyzed by the wavelet method. Then, the number of inputs to the ANN is determined using feature extraction, which is based on energy, standard deviation, and maximum values of the analyzed data. The proposed method has been analyzed by different input and various structures for daily, weekly, and monthly flow forecasting at Ellen Brook river station, western Australia. Furthermore, the mean squares error (MSE), root mean square error (RMSE), and the Nash-Sutcliffe efficiency (NSE) is used to evaluate the performance of the suggested method. Furthermore, the obtained findings were compared to those of other models and methods in order to examine the performance and efficiency of the feature extraction process. It was discovered that the proposed feature extraction model outperformed their counterparts, especially when it came to long-term forecasting. Multidisciplinary Digital Publishing Institute 2021 Article PeerReviewed Malekpour Heydari, Salimeh and Mohd Aris, Teh Noranis and Yaakob, Razali and Hamdan, Hazlina (2021) Data-driven forecasting and modeling of runoff flow to reduce flood risk using a novel hybrid wavelet-neural network based on feature extraction. Sustainability, 13 (20). pp. 1-16. ISSN 2071-1050 https://www.mdpi.com/2071-1050/13/20/11537 10.3390/su132011537
spellingShingle Malekpour Heydari, Salimeh
Mohd Aris, Teh Noranis
Yaakob, Razali
Hamdan, Hazlina
Data-driven forecasting and modeling of runoff flow to reduce flood risk using a novel hybrid wavelet-neural network based on feature extraction
title Data-driven forecasting and modeling of runoff flow to reduce flood risk using a novel hybrid wavelet-neural network based on feature extraction
title_full Data-driven forecasting and modeling of runoff flow to reduce flood risk using a novel hybrid wavelet-neural network based on feature extraction
title_fullStr Data-driven forecasting and modeling of runoff flow to reduce flood risk using a novel hybrid wavelet-neural network based on feature extraction
title_full_unstemmed Data-driven forecasting and modeling of runoff flow to reduce flood risk using a novel hybrid wavelet-neural network based on feature extraction
title_short Data-driven forecasting and modeling of runoff flow to reduce flood risk using a novel hybrid wavelet-neural network based on feature extraction
title_sort data-driven forecasting and modeling of runoff flow to reduce flood risk using a novel hybrid wavelet-neural network based on feature extraction
url http://psasir.upm.edu.my/id/eprint/96598/
http://psasir.upm.edu.my/id/eprint/96598/
http://psasir.upm.edu.my/id/eprint/96598/