Boosting flood routing prediction performance through a hybrid approach using empirical mode decomposition and neural networks: a case study of the Mera River in Ankara
Flood routing is vital in helping to reduce the impact of floods on people and communities by allowing timely and appropriate responses. In this study, the empirical mode decomposition (EMD) signal decomposition technique is combined with cascade forward backpropagation neural network (CFBNN) and fe...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IWA Publishing
2023-11-01
|
| Series: | Water Supply |
| Subjects: | |
| Online Access: | http://ws.iwaponline.com/content/23/11/4403 |
| _version_ | 1797428368980836352 |
|---|---|
| author | Okan Mert katipoğlu Metin Sarıgöl |
| author_facet | Okan Mert katipoğlu Metin Sarıgöl |
| author_sort | Okan Mert katipoğlu |
| collection | DOAJ |
| description | Flood routing is vital in helping to reduce the impact of floods on people and communities by allowing timely and appropriate responses. In this study, the empirical mode decomposition (EMD) signal decomposition technique is combined with cascade forward backpropagation neural network (CFBNN) and feed-forward backpropagation neural network (FFBNN) machine learning (ML) techniques to model 2014 floods in Ankara, Mera River. The data are split in order to avoid the underfitting and overfitting problems of the algorithm. While establishing the algorithm, 70% of the data were divided into training, 15% testing and 15% validation. Graphical indicators and statistical parameters were used for the analysis of model performance. As a result, the EMD signal decomposition technique has been found to improve the performance of ML models. In addition, the EMD-FFBNN hybrid model showed the most accurate estimation results in the flood routing calculation. The study's outputs can assist in designing flood control structures such as levees and dams to help reduce flood risk.
HIGHLIGHTS
It has been proven that machine learning techniques can be used effectively in flood routing forecasting.;
It can assist in flood management strategies and mitigation in risky areas with flood routing forecasts.;
Signal separation techniques have been shown to increase the success of flood translation estimation.;
The EMD-FFBNN hybrid model showed the most accurate results in flood routing calculation.; |
| first_indexed | 2024-03-09T08:57:54Z |
| format | Article |
| id | doaj.art-2f1410a54098417282c0c91f41061a1d |
| institution | Directory Open Access Journal |
| issn | 1606-9749 1607-0798 |
| language | English |
| last_indexed | 2024-03-09T08:57:54Z |
| publishDate | 2023-11-01 |
| publisher | IWA Publishing |
| record_format | Article |
| series | Water Supply |
| spelling | doaj.art-2f1410a54098417282c0c91f41061a1d2023-12-02T12:33:41ZengIWA PublishingWater Supply1606-97491607-07982023-11-0123114403441510.2166/ws.2023.288288Boosting flood routing prediction performance through a hybrid approach using empirical mode decomposition and neural networks: a case study of the Mera River in AnkaraOkan Mert katipoğlu0Metin Sarıgöl1 Faculty of Engineering and Architecture, Department of Civil Engineering, Erzincan Binali Yıldırım University, Erzincan, Türkiye Design Department, Erzincan Uzumlu Vocational School, Erzincan Binali Yildirim University, Erzincan, Türkiye Flood routing is vital in helping to reduce the impact of floods on people and communities by allowing timely and appropriate responses. In this study, the empirical mode decomposition (EMD) signal decomposition technique is combined with cascade forward backpropagation neural network (CFBNN) and feed-forward backpropagation neural network (FFBNN) machine learning (ML) techniques to model 2014 floods in Ankara, Mera River. The data are split in order to avoid the underfitting and overfitting problems of the algorithm. While establishing the algorithm, 70% of the data were divided into training, 15% testing and 15% validation. Graphical indicators and statistical parameters were used for the analysis of model performance. As a result, the EMD signal decomposition technique has been found to improve the performance of ML models. In addition, the EMD-FFBNN hybrid model showed the most accurate estimation results in the flood routing calculation. The study's outputs can assist in designing flood control structures such as levees and dams to help reduce flood risk. HIGHLIGHTS It has been proven that machine learning techniques can be used effectively in flood routing forecasting.; It can assist in flood management strategies and mitigation in risky areas with flood routing forecasts.; Signal separation techniques have been shown to increase the success of flood translation estimation.; The EMD-FFBNN hybrid model showed the most accurate results in flood routing calculation.;http://ws.iwaponline.com/content/23/11/4403ankaracascade forward backpropagationempirical mode decompositionfeed-forward backpropagationflood routingmachine learning |
| spellingShingle | Okan Mert katipoğlu Metin Sarıgöl Boosting flood routing prediction performance through a hybrid approach using empirical mode decomposition and neural networks: a case study of the Mera River in Ankara Water Supply ankara cascade forward backpropagation empirical mode decomposition feed-forward backpropagation flood routing machine learning |
| title | Boosting flood routing prediction performance through a hybrid approach using empirical mode decomposition and neural networks: a case study of the Mera River in Ankara |
| title_full | Boosting flood routing prediction performance through a hybrid approach using empirical mode decomposition and neural networks: a case study of the Mera River in Ankara |
| title_fullStr | Boosting flood routing prediction performance through a hybrid approach using empirical mode decomposition and neural networks: a case study of the Mera River in Ankara |
| title_full_unstemmed | Boosting flood routing prediction performance through a hybrid approach using empirical mode decomposition and neural networks: a case study of the Mera River in Ankara |
| title_short | Boosting flood routing prediction performance through a hybrid approach using empirical mode decomposition and neural networks: a case study of the Mera River in Ankara |
| title_sort | boosting flood routing prediction performance through a hybrid approach using empirical mode decomposition and neural networks a case study of the mera river in ankara |
| topic | ankara cascade forward backpropagation empirical mode decomposition feed-forward backpropagation flood routing machine learning |
| url | http://ws.iwaponline.com/content/23/11/4403 |
| work_keys_str_mv | AT okanmertkatipoglu boostingfloodroutingpredictionperformancethroughahybridapproachusingempiricalmodedecompositionandneuralnetworksacasestudyofthemerariverinankara AT metinsarıgol boostingfloodroutingpredictionperformancethroughahybridapproachusingempiricalmodedecompositionandneuralnetworksacasestudyofthemerariverinankara |