Advanced Machine Learning Ensembles for Improved Precipitation Forecasting: The Modified Stacking Ensemble Strategy in China
Accurate and reliable precipitation forecasting is vital for effective water resource management and disaster mitigation, especially in geographically diverse and climatically complex regions like China. This study proposes an advanced methodology for medium- and long-term hydrological forecasting b...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10839126/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542584115822592 |
|---|---|
| author | Tiantian Tang Yifan Wu Yujie Li Lexi Xu Xinyi Shi Haitao Zhao Guan Gui |
| author_facet | Tiantian Tang Yifan Wu Yujie Li Lexi Xu Xinyi Shi Haitao Zhao Guan Gui |
| author_sort | Tiantian Tang |
| collection | DOAJ |
| description | Accurate and reliable precipitation forecasting is vital for effective water resource management and disaster mitigation, especially in geographically diverse and climatically complex regions like China. This study proposes an advanced methodology for medium- and long-term hydrological forecasting by integrating multiple machine learning models through a modified stacking ensemble strategy (MSES). We developed and compared five deterministic precipitation forecasting models, including elastic net regression (ENR), support vector regression, random forest, extreme gradient boosting, and light gradient boosting to provide forecasts with lead times ranging from 0 to 5 months at a spatial resolution of 0.5<inline-formula><tex-math notation="LaTeX">$^\circ$</tex-math></inline-formula>. The MSES was then evaluated against the traditional Bayesian model averaging (BMA) approach. Our comprehensive evaluation, based on deterministic forecasting metrics such as the anomaly correlation coefficient (ACC), mean squared skill score (MSSS), and Graded Precipitation Score (Pg), demonstrated the MSES outperformed individual models and the BMA method. The MSES achieved ACC scores between 0.6 and 0.9 for lead time (LT) <inline-formula><tex-math notation="LaTeX">$= 0$</tex-math></inline-formula> month, with an average of around 0.8 for LT <inline-formula><tex-math notation="LaTeX">$= 2$</tex-math></inline-formula> months. The MSSS for MSES was above 0.5 in more than half of the evaluations, and the Pg score was consistently above 80, indicating high accuracy in precipitation magnitude prediction. These findings highlight the promise of advanced machine learning strategies like MSES in improving the accuracy and robustness of precipitation forecasts, addressing critical needs in water resource management and disaster mitigation in China. |
| format | Article |
| id | doaj-art-6e330f30b45b4f4e8651c60de6dc23a0 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-6e330f30b45b4f4e8651c60de6dc23a02025-02-04T00:00:19ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01184242425410.1109/JSTARS.2025.352847510839126Advanced Machine Learning Ensembles for Improved Precipitation Forecasting: The Modified Stacking Ensemble Strategy in ChinaTiantian Tang0https://orcid.org/0000-0002-8596-1227Yifan Wu1Yujie Li2Lexi Xu3https://orcid.org/0000-0003-4338-7252Xinyi Shi4Haitao Zhao5https://orcid.org/0000-0002-3539-3532Guan Gui6https://orcid.org/0000-0003-3888-2881College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, ChinaCollege of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, ChinaZhejiang Design Institute of Water Conservancy and Hydroelectric Power, Hangzhou, ChinaResearch Institute, China United Network Communications Corporation, Beijing, ChinaAI Research Center, Nanjing Great Information Technology Company Ltd., Nanjing, ChinaCollege of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, ChinaCollege of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, ChinaAccurate and reliable precipitation forecasting is vital for effective water resource management and disaster mitigation, especially in geographically diverse and climatically complex regions like China. This study proposes an advanced methodology for medium- and long-term hydrological forecasting by integrating multiple machine learning models through a modified stacking ensemble strategy (MSES). We developed and compared five deterministic precipitation forecasting models, including elastic net regression (ENR), support vector regression, random forest, extreme gradient boosting, and light gradient boosting to provide forecasts with lead times ranging from 0 to 5 months at a spatial resolution of 0.5<inline-formula><tex-math notation="LaTeX">$^\circ$</tex-math></inline-formula>. The MSES was then evaluated against the traditional Bayesian model averaging (BMA) approach. Our comprehensive evaluation, based on deterministic forecasting metrics such as the anomaly correlation coefficient (ACC), mean squared skill score (MSSS), and Graded Precipitation Score (Pg), demonstrated the MSES outperformed individual models and the BMA method. The MSES achieved ACC scores between 0.6 and 0.9 for lead time (LT) <inline-formula><tex-math notation="LaTeX">$= 0$</tex-math></inline-formula> month, with an average of around 0.8 for LT <inline-formula><tex-math notation="LaTeX">$= 2$</tex-math></inline-formula> months. The MSSS for MSES was above 0.5 in more than half of the evaluations, and the Pg score was consistently above 80, indicating high accuracy in precipitation magnitude prediction. These findings highlight the promise of advanced machine learning strategies like MSES in improving the accuracy and robustness of precipitation forecasts, addressing critical needs in water resource management and disaster mitigation in China.https://ieeexplore.ieee.org/document/10839126/Ensemble methodsmachine learningmultimodel machine learning integrationprecipitation forecasting |
| spellingShingle | Tiantian Tang Yifan Wu Yujie Li Lexi Xu Xinyi Shi Haitao Zhao Guan Gui Advanced Machine Learning Ensembles for Improved Precipitation Forecasting: The Modified Stacking Ensemble Strategy in China IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Ensemble methods machine learning multimodel machine learning integration precipitation forecasting |
| title | Advanced Machine Learning Ensembles for Improved Precipitation Forecasting: The Modified Stacking Ensemble Strategy in China |
| title_full | Advanced Machine Learning Ensembles for Improved Precipitation Forecasting: The Modified Stacking Ensemble Strategy in China |
| title_fullStr | Advanced Machine Learning Ensembles for Improved Precipitation Forecasting: The Modified Stacking Ensemble Strategy in China |
| title_full_unstemmed | Advanced Machine Learning Ensembles for Improved Precipitation Forecasting: The Modified Stacking Ensemble Strategy in China |
| title_short | Advanced Machine Learning Ensembles for Improved Precipitation Forecasting: The Modified Stacking Ensemble Strategy in China |
| title_sort | advanced machine learning ensembles for improved precipitation forecasting the modified stacking ensemble strategy in china |
| topic | Ensemble methods machine learning multimodel machine learning integration precipitation forecasting |
| url | https://ieeexplore.ieee.org/document/10839126/ |
| work_keys_str_mv | AT tiantiantang advancedmachinelearningensemblesforimprovedprecipitationforecastingthemodifiedstackingensemblestrategyinchina AT yifanwu advancedmachinelearningensemblesforimprovedprecipitationforecastingthemodifiedstackingensemblestrategyinchina AT yujieli advancedmachinelearningensemblesforimprovedprecipitationforecastingthemodifiedstackingensemblestrategyinchina AT lexixu advancedmachinelearningensemblesforimprovedprecipitationforecastingthemodifiedstackingensemblestrategyinchina AT xinyishi advancedmachinelearningensemblesforimprovedprecipitationforecastingthemodifiedstackingensemblestrategyinchina AT haitaozhao advancedmachinelearningensemblesforimprovedprecipitationforecastingthemodifiedstackingensemblestrategyinchina AT guangui advancedmachinelearningensemblesforimprovedprecipitationforecastingthemodifiedstackingensemblestrategyinchina |