Accurate discharge and water level forecasting using ensemble learning with genetic algorithm and singular spectrum analysis-based denoising
Abstract Forecasting discharge (Q) and water level (H) are essential factors in hydrological research and flood prediction. In recent years, deep learning has emerged as a viable technique for capturing the non-linear relationship of historical data to generate highly accurate prediction results. De...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-22057-8 |
| _version_ | 1798016868124983296 |
|---|---|
| author | Anh Duy Nguyen Phi Le Nguyen Viet Hung Vu Quoc Viet Pham Viet Huy Nguyen Minh Hieu Nguyen Thanh Hung Nguyen Kien Nguyen |
| author_facet | Anh Duy Nguyen Phi Le Nguyen Viet Hung Vu Quoc Viet Pham Viet Huy Nguyen Minh Hieu Nguyen Thanh Hung Nguyen Kien Nguyen |
| author_sort | Anh Duy Nguyen |
| collection | DOAJ |
| description | Abstract Forecasting discharge (Q) and water level (H) are essential factors in hydrological research and flood prediction. In recent years, deep learning has emerged as a viable technique for capturing the non-linear relationship of historical data to generate highly accurate prediction results. Despite the success in various domains, applying deep learning in Q and H prediction is hampered by three critical issues: a shortage of training data, the occurrence of noise in the collected data, and the difficulty in adjusting the model’s hyper-parameters. This work proposes a novel deep learning-based Q–H prediction model that overcomes all the shortcomings encountered by existing approaches. Specifically, to address data scarcity and increase prediction accuracy, we design an ensemble learning architecture that takes advantage of multiple deep learning techniques. Furthermore, we leverage the Singular-Spectrum Analysis (SSA) to remove noise and outliers from the original data. Besides, we exploit the Genetic Algorithm (GA) to propose a novel mechanism that can automatically determine the prediction model’s optimal hyper-parameters. We conducted extensive experiments on two datasets collected from Vietnam’s Red and Dakbla rivers. The results show that our proposed solution outperforms current techniques across a wide range of metrics, including NSE, MSE, MAE, and MAPE. Specifically, by exploiting the ensemble learning technique, we can improve the NSE by at least $$2\%$$ 2 % . Moreover, with the aid of the SSA-based data preprocessing technique, the NSE is further enhanced by more than $$5\%$$ 5 % . Finally, thanks to GA-based optimization, our proposed model increases the NSE by at least $$6\%$$ 6 % and up to $$40\%$$ 40 % in the best case. |
| first_indexed | 2024-04-11T15:57:31Z |
| format | Article |
| id | doaj.art-0991ebb42e74494ea776e3c05dff9e04 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T15:57:31Z |
| publishDate | 2022-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-0991ebb42e74494ea776e3c05dff9e042022-12-22T04:15:06ZengNature PortfolioScientific Reports2045-23222022-11-0112112510.1038/s41598-022-22057-8Accurate discharge and water level forecasting using ensemble learning with genetic algorithm and singular spectrum analysis-based denoisingAnh Duy Nguyen0Phi Le Nguyen1Viet Hung Vu2Quoc Viet Pham3Viet Huy Nguyen4Minh Hieu Nguyen5Thanh Hung Nguyen6Kien Nguyen7School of Information and Communication Technology, Hanoi University of Science and TechnologySchool of Information and Communication Technology, Hanoi University of Science and TechnologySchool of Information and Communication Technology, Hanoi University of Science and TechnologySchool of Information and Communication Technology, Hanoi University of Science and TechnologySchool of Information and Communication Technology, Hanoi University of Science and TechnologySchool of Information and Communication Technology, Hanoi University of Science and TechnologySchool of Information and Communication Technology, Hanoi University of Science and TechnologyInstitute for Advanced Academic Research, Chiba UniversityAbstract Forecasting discharge (Q) and water level (H) are essential factors in hydrological research and flood prediction. In recent years, deep learning has emerged as a viable technique for capturing the non-linear relationship of historical data to generate highly accurate prediction results. Despite the success in various domains, applying deep learning in Q and H prediction is hampered by three critical issues: a shortage of training data, the occurrence of noise in the collected data, and the difficulty in adjusting the model’s hyper-parameters. This work proposes a novel deep learning-based Q–H prediction model that overcomes all the shortcomings encountered by existing approaches. Specifically, to address data scarcity and increase prediction accuracy, we design an ensemble learning architecture that takes advantage of multiple deep learning techniques. Furthermore, we leverage the Singular-Spectrum Analysis (SSA) to remove noise and outliers from the original data. Besides, we exploit the Genetic Algorithm (GA) to propose a novel mechanism that can automatically determine the prediction model’s optimal hyper-parameters. We conducted extensive experiments on two datasets collected from Vietnam’s Red and Dakbla rivers. The results show that our proposed solution outperforms current techniques across a wide range of metrics, including NSE, MSE, MAE, and MAPE. Specifically, by exploiting the ensemble learning technique, we can improve the NSE by at least $$2\%$$ 2 % . Moreover, with the aid of the SSA-based data preprocessing technique, the NSE is further enhanced by more than $$5\%$$ 5 % . Finally, thanks to GA-based optimization, our proposed model increases the NSE by at least $$6\%$$ 6 % and up to $$40\%$$ 40 % in the best case.https://doi.org/10.1038/s41598-022-22057-8 |
| spellingShingle | Anh Duy Nguyen Phi Le Nguyen Viet Hung Vu Quoc Viet Pham Viet Huy Nguyen Minh Hieu Nguyen Thanh Hung Nguyen Kien Nguyen Accurate discharge and water level forecasting using ensemble learning with genetic algorithm and singular spectrum analysis-based denoising Scientific Reports |
| title | Accurate discharge and water level forecasting using ensemble learning with genetic algorithm and singular spectrum analysis-based denoising |
| title_full | Accurate discharge and water level forecasting using ensemble learning with genetic algorithm and singular spectrum analysis-based denoising |
| title_fullStr | Accurate discharge and water level forecasting using ensemble learning with genetic algorithm and singular spectrum analysis-based denoising |
| title_full_unstemmed | Accurate discharge and water level forecasting using ensemble learning with genetic algorithm and singular spectrum analysis-based denoising |
| title_short | Accurate discharge and water level forecasting using ensemble learning with genetic algorithm and singular spectrum analysis-based denoising |
| title_sort | accurate discharge and water level forecasting using ensemble learning with genetic algorithm and singular spectrum analysis based denoising |
| url | https://doi.org/10.1038/s41598-022-22057-8 |
| work_keys_str_mv | AT anhduynguyen accuratedischargeandwaterlevelforecastingusingensemblelearningwithgeneticalgorithmandsingularspectrumanalysisbaseddenoising AT philenguyen accuratedischargeandwaterlevelforecastingusingensemblelearningwithgeneticalgorithmandsingularspectrumanalysisbaseddenoising AT viethungvu accuratedischargeandwaterlevelforecastingusingensemblelearningwithgeneticalgorithmandsingularspectrumanalysisbaseddenoising AT quocvietpham accuratedischargeandwaterlevelforecastingusingensemblelearningwithgeneticalgorithmandsingularspectrumanalysisbaseddenoising AT viethuynguyen accuratedischargeandwaterlevelforecastingusingensemblelearningwithgeneticalgorithmandsingularspectrumanalysisbaseddenoising AT minhhieunguyen accuratedischargeandwaterlevelforecastingusingensemblelearningwithgeneticalgorithmandsingularspectrumanalysisbaseddenoising AT thanhhungnguyen accuratedischargeandwaterlevelforecastingusingensemblelearningwithgeneticalgorithmandsingularspectrumanalysisbaseddenoising AT kiennguyen accuratedischargeandwaterlevelforecastingusingensemblelearningwithgeneticalgorithmandsingularspectrumanalysisbaseddenoising |