Research on short-term precipitation forecasting method based on CEEMDAN-GRU algorithm
Abstract Precipitation forecasting is vital for managing disasters, urban traffic, and agriculture. This study develops an improved model for short-term precipitation forecasting by combining Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Gated Recurrent Unit (GRU)....
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83365-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559455800492032 |
|---|---|
| author | Hua Xu Zongkai Guo Yu Cao Xu Cheng Qiong Zhang Dan Chen |
| author_facet | Hua Xu Zongkai Guo Yu Cao Xu Cheng Qiong Zhang Dan Chen |
| author_sort | Hua Xu |
| collection | DOAJ |
| description | Abstract Precipitation forecasting is vital for managing disasters, urban traffic, and agriculture. This study develops an improved model for short-term precipitation forecasting by combining Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Gated Recurrent Unit (GRU). Using precipitation data from January 1, 2019, to December 31, 2022, as a sample, the model capitalizes on CEEMDAN’s superior signal decomposition capabilities and GRU’s ability to capture nonlinear dynamic patterns in time series. To assess the model’s effectiveness, comparisons were conducted with 12 benchmark models, including CEEMDAN-LSTM, EMD-GRU, EMD-LSTM, BI-LSTM, GRU, LSTM, and TCN. The results demonstrate that the CEEMDAN-GRU model achieves higher accuracy and stability in short-term precipitation forecasting. Leveraging an Adam optimizer with adaptive learning rate reduction enhances convergence and ensures reliable predictions, achieving an R²of 0.7915, MAE of 0.05382, and MSE of 0.09081. |
| format | Article |
| id | doaj-art-a43bcb5076f04dd6a48af00f7b4dbde4 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-a43bcb5076f04dd6a48af00f7b4dbde42025-01-05T12:29:37ZengNature PortfolioScientific Reports2045-23222024-12-0114111510.1038/s41598-024-83365-9Research on short-term precipitation forecasting method based on CEEMDAN-GRU algorithmHua Xu0Zongkai Guo1Yu Cao2Xu Cheng3Qiong Zhang4Dan Chen5School of Information Science and Control Engineering, Liaoning Petrochemical UniversityLiaoning Meteorological Equipment Support CenterSchool of Information Science and Control Engineering, Liaoning Petrochemical UniversitySchool of Economics and Management, Shenyang Agricultural UniversitySchool of Information Science and Control Engineering, Liaoning Petrochemical UniversitySchool of Information Science and Control Engineering, Liaoning Petrochemical UniversityAbstract Precipitation forecasting is vital for managing disasters, urban traffic, and agriculture. This study develops an improved model for short-term precipitation forecasting by combining Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Gated Recurrent Unit (GRU). Using precipitation data from January 1, 2019, to December 31, 2022, as a sample, the model capitalizes on CEEMDAN’s superior signal decomposition capabilities and GRU’s ability to capture nonlinear dynamic patterns in time series. To assess the model’s effectiveness, comparisons were conducted with 12 benchmark models, including CEEMDAN-LSTM, EMD-GRU, EMD-LSTM, BI-LSTM, GRU, LSTM, and TCN. The results demonstrate that the CEEMDAN-GRU model achieves higher accuracy and stability in short-term precipitation forecasting. Leveraging an Adam optimizer with adaptive learning rate reduction enhances convergence and ensures reliable predictions, achieving an R²of 0.7915, MAE of 0.05382, and MSE of 0.09081.https://doi.org/10.1038/s41598-024-83365-9Precipitation forecastingCEEMDAN-GRUComplete ensemble empirical mode decomposition with adaptive noiseGated recurrent unitTime series prediction |
| spellingShingle | Hua Xu Zongkai Guo Yu Cao Xu Cheng Qiong Zhang Dan Chen Research on short-term precipitation forecasting method based on CEEMDAN-GRU algorithm Scientific Reports Precipitation forecasting CEEMDAN-GRU Complete ensemble empirical mode decomposition with adaptive noise Gated recurrent unit Time series prediction |
| title | Research on short-term precipitation forecasting method based on CEEMDAN-GRU algorithm |
| title_full | Research on short-term precipitation forecasting method based on CEEMDAN-GRU algorithm |
| title_fullStr | Research on short-term precipitation forecasting method based on CEEMDAN-GRU algorithm |
| title_full_unstemmed | Research on short-term precipitation forecasting method based on CEEMDAN-GRU algorithm |
| title_short | Research on short-term precipitation forecasting method based on CEEMDAN-GRU algorithm |
| title_sort | research on short term precipitation forecasting method based on ceemdan gru algorithm |
| topic | Precipitation forecasting CEEMDAN-GRU Complete ensemble empirical mode decomposition with adaptive noise Gated recurrent unit Time series prediction |
| url | https://doi.org/10.1038/s41598-024-83365-9 |
| work_keys_str_mv | AT huaxu researchonshorttermprecipitationforecastingmethodbasedonceemdangrualgorithm AT zongkaiguo researchonshorttermprecipitationforecastingmethodbasedonceemdangrualgorithm AT yucao researchonshorttermprecipitationforecastingmethodbasedonceemdangrualgorithm AT xucheng researchonshorttermprecipitationforecastingmethodbasedonceemdangrualgorithm AT qiongzhang researchonshorttermprecipitationforecastingmethodbasedonceemdangrualgorithm AT danchen researchonshorttermprecipitationforecastingmethodbasedonceemdangrualgorithm |