Development of improved deep learning models for multi-step ahead forecasting of daily river water temperature
Precise river water temperature (WT) forecasts are essential for monitoring water quality. This study addresses the limited use of signal decomposition in hybrid WT prediction models by proposing three methods: namely ensemble empirical mode decomposition (EEMD) on AdaBoost, long short-term memory (...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Engineering Applications of Computational Fluid Mechanics |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/19942060.2025.2450477 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583619187572736 |
|---|---|
| author | Mehdi Gheisari Jana Shafi Saeed Kosari Samaneh Amanabadi Saeid Mehdizadeh Christian Fernandez Campusano Hemn Barzan Abdalla |
| author_facet | Mehdi Gheisari Jana Shafi Saeed Kosari Samaneh Amanabadi Saeid Mehdizadeh Christian Fernandez Campusano Hemn Barzan Abdalla |
| author_sort | Mehdi Gheisari |
| collection | DOAJ |
| description | Precise river water temperature (WT) forecasts are essential for monitoring water quality. This study addresses the limited use of signal decomposition in hybrid WT prediction models by proposing three methods: namely ensemble empirical mode decomposition (EEMD) on AdaBoost, long short-term memory (LSTM), and gated recurrent unit (GRU). These models integrate ensemble empirical mode decomposition (EEMD) with machine learning techniques for forecasting WT across multiple time horizons (one, three, and five days). The performance of implemented models were tested on two river stations located on the Clackamas River (USGS 14211010) and Willamette River (USGS 14211720). Some error measures comprising root mean square (RMSE), mean absolute error (MAE), coefficient of determination (R2), uncertainty coefficient in 95% confidence level (U95%), and mean absolute percentage error (MAPE) were applied in assessing the models’ performances. The performance of the proposed merged methods, including EEMD-AdaBoost, EEMD-LSTM, and EEMD-GRU, were compared with their simple forms. The outcomes illustrated that the hybrid models performed better than the relevant individual methods; however, the river WT forecasts of EEMD-LSTM and EEMD-GRU were found to be much closer to the observed data than those of the EEMD-AdaBoost method. The better accuracy of hybrid models compared to their corresponding simple ones can be explained by considering the potential of EEMD in separating intrinsic patterns and reducing the noises, leading to reliable forecasts of river WT time series. A performance comparison of the simple models also denoted the superiority of LSTM and GRU over the AdaBoost. The superior river WT forecasts at both stations during the testing stage were concluded for one day ahead at EEMD-GRU model (USGS 14211010: RMSE = 0.1929 ℃, MAE = 0.1489 ℃, R2 = 0.9988, U95% = 0.3745, MAPE = 1.3608%; USGS 14211720: RMSE = 0.1918 ℃, MAE = 0.1558 ℃, R2 = 0.9990, U95% = 0.3690, MAPE = 1.1790%). |
| format | Article |
| id | doaj-art-c8cbed6de5104ed09b8268eea897149e |
| institution | Kabale University |
| issn | 1994-2060 1997-003X |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Engineering Applications of Computational Fluid Mechanics |
| spelling | doaj-art-c8cbed6de5104ed09b8268eea897149e2025-01-28T09:46:15ZengTaylor & Francis GroupEngineering Applications of Computational Fluid Mechanics1994-20601997-003X2025-12-0119110.1080/19942060.2025.2450477Development of improved deep learning models for multi-step ahead forecasting of daily river water temperatureMehdi Gheisari0Jana Shafi1Saeed Kosari2Samaneh Amanabadi3Saeid Mehdizadeh4Christian Fernandez Campusano5Hemn Barzan Abdalla6Institute of Artificial Intelligence, Shaoxing University, Zhejiang, People’s Republic of ChinaDepartment of Computer Engineering and Information, College of Engineering in Wadi Alddawasir, Prince Sattam Bin Abdulaziz University, Wadi Alddawasir, Saudi ArabiaInstitute of Computing Science and Technology, Guangzhou University, Guangzhou, People’s Republic of ChinaFaculty of Agriculture and Natural Resources, Department of Soil Science, Science and Research Branch, Islamic Azad University, Tehran, IranWater Engineering Department, Urmia University, Urmia, IranDepartment of Electrical Engineering, University of Santiago of Chile (USACH), Santiago, ChileDepartment of Computer Science, Wenzhou-Kean University, Wenzhou, People’s Republic of ChinaPrecise river water temperature (WT) forecasts are essential for monitoring water quality. This study addresses the limited use of signal decomposition in hybrid WT prediction models by proposing three methods: namely ensemble empirical mode decomposition (EEMD) on AdaBoost, long short-term memory (LSTM), and gated recurrent unit (GRU). These models integrate ensemble empirical mode decomposition (EEMD) with machine learning techniques for forecasting WT across multiple time horizons (one, three, and five days). The performance of implemented models were tested on two river stations located on the Clackamas River (USGS 14211010) and Willamette River (USGS 14211720). Some error measures comprising root mean square (RMSE), mean absolute error (MAE), coefficient of determination (R2), uncertainty coefficient in 95% confidence level (U95%), and mean absolute percentage error (MAPE) were applied in assessing the models’ performances. The performance of the proposed merged methods, including EEMD-AdaBoost, EEMD-LSTM, and EEMD-GRU, were compared with their simple forms. The outcomes illustrated that the hybrid models performed better than the relevant individual methods; however, the river WT forecasts of EEMD-LSTM and EEMD-GRU were found to be much closer to the observed data than those of the EEMD-AdaBoost method. The better accuracy of hybrid models compared to their corresponding simple ones can be explained by considering the potential of EEMD in separating intrinsic patterns and reducing the noises, leading to reliable forecasts of river WT time series. A performance comparison of the simple models also denoted the superiority of LSTM and GRU over the AdaBoost. The superior river WT forecasts at both stations during the testing stage were concluded for one day ahead at EEMD-GRU model (USGS 14211010: RMSE = 0.1929 ℃, MAE = 0.1489 ℃, R2 = 0.9988, U95% = 0.3745, MAPE = 1.3608%; USGS 14211720: RMSE = 0.1918 ℃, MAE = 0.1558 ℃, R2 = 0.9990, U95% = 0.3690, MAPE = 1.1790%).https://www.tandfonline.com/doi/10.1080/19942060.2025.2450477River water temperatureforecastinghybrid modelsdeep learningtime horizonensemble empirical mode decomposition |
| spellingShingle | Mehdi Gheisari Jana Shafi Saeed Kosari Samaneh Amanabadi Saeid Mehdizadeh Christian Fernandez Campusano Hemn Barzan Abdalla Development of improved deep learning models for multi-step ahead forecasting of daily river water temperature Engineering Applications of Computational Fluid Mechanics River water temperature forecasting hybrid models deep learning time horizon ensemble empirical mode decomposition |
| title | Development of improved deep learning models for multi-step ahead forecasting of daily river water temperature |
| title_full | Development of improved deep learning models for multi-step ahead forecasting of daily river water temperature |
| title_fullStr | Development of improved deep learning models for multi-step ahead forecasting of daily river water temperature |
| title_full_unstemmed | Development of improved deep learning models for multi-step ahead forecasting of daily river water temperature |
| title_short | Development of improved deep learning models for multi-step ahead forecasting of daily river water temperature |
| title_sort | development of improved deep learning models for multi step ahead forecasting of daily river water temperature |
| topic | River water temperature forecasting hybrid models deep learning time horizon ensemble empirical mode decomposition |
| url | https://www.tandfonline.com/doi/10.1080/19942060.2025.2450477 |
| work_keys_str_mv | AT mehdigheisari developmentofimproveddeeplearningmodelsformultistepaheadforecastingofdailyriverwatertemperature AT janashafi developmentofimproveddeeplearningmodelsformultistepaheadforecastingofdailyriverwatertemperature AT saeedkosari developmentofimproveddeeplearningmodelsformultistepaheadforecastingofdailyriverwatertemperature AT samanehamanabadi developmentofimproveddeeplearningmodelsformultistepaheadforecastingofdailyriverwatertemperature AT saeidmehdizadeh developmentofimproveddeeplearningmodelsformultistepaheadforecastingofdailyriverwatertemperature AT christianfernandezcampusano developmentofimproveddeeplearningmodelsformultistepaheadforecastingofdailyriverwatertemperature AT hemnbarzanabdalla developmentofimproveddeeplearningmodelsformultistepaheadforecastingofdailyriverwatertemperature |