F10.7 Daily Forecast Using LSTM Combined With VMD Method
Abstract The F10.7 solar radiation flux is a well‐known parameter that is closely linked to solar activity, serving as a key index for measuring the level of solar activity. In this study, the Variational Mode Decomposition (VMD) and Long Short‐term Memory (LSTM) network are combined to construct a...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2023SW003552 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536481606238208 |
|---|---|
| author | Yuhang Hao Jianyong Lu Guangshuai Peng Ming Wang Jingyuan Li Guanchun Wei |
| author_facet | Yuhang Hao Jianyong Lu Guangshuai Peng Ming Wang Jingyuan Li Guanchun Wei |
| author_sort | Yuhang Hao |
| collection | DOAJ |
| description | Abstract The F10.7 solar radiation flux is a well‐known parameter that is closely linked to solar activity, serving as a key index for measuring the level of solar activity. In this study, the Variational Mode Decomposition (VMD) and Long Short‐term Memory (LSTM) network are combined to construct a VMD‐LSTM model for predicting F10.7 values. The F10.7 sequence is decomposed into several intrinsic mode functions (IMF) by VMD, then the LSTM neural network is utilized to forecast each IMF. All IMF prediction results are aggregated to obtain the final F10.7 value. The data sets from 1957 to 2008 are used for training and the data sets from 2009 to 2019 are used for testing. The results show that the VMD‐LSTM model achieves an annual average root mean square error of only 4.47 sfu and an annual average correlation coefficient (R) of 0.99 during solar cycle 24, which is significantly better than the accuracy of the LSTM model (W. Zhang et al., 2022, https://doi.org/10.3390/universe8010030), the AR model (Du, 2020, https://doi.org/10.1007/s11207-020-01689-x), and the BP model (Xiao et al., 2017, https://doi.org/10.11728/cjss2017.01.001). The VMD‐LSTM model exhibits strong predictive capability for the F10.7 index during solar cycle 24. |
| format | Article |
| id | doaj-art-50810df32e4043a999234bbd8a8a60d8 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-50810df32e4043a999234bbd8a8a60d82025-01-14T16:26:56ZengWileySpace Weather1542-73902024-01-01221n/an/a10.1029/2023SW003552F10.7 Daily Forecast Using LSTM Combined With VMD MethodYuhang Hao0Jianyong Lu1Guangshuai Peng2Ming Wang3Jingyuan Li4Guanchun Wei5Institute of Space Weather School of Atmospheric Physics Nanjing University of Information Science and Technology Nanjing ChinaInstitute of Space Weather School of Atmospheric Physics Nanjing University of Information Science and Technology Nanjing ChinaInstitute of Space Weather School of Atmospheric Physics Nanjing University of Information Science and Technology Nanjing ChinaInstitute of Space Weather School of Atmospheric Physics Nanjing University of Information Science and Technology Nanjing ChinaInstitute of Space Weather School of Atmospheric Physics Nanjing University of Information Science and Technology Nanjing ChinaInstitute of Space Weather School of Atmospheric Physics Nanjing University of Information Science and Technology Nanjing ChinaAbstract The F10.7 solar radiation flux is a well‐known parameter that is closely linked to solar activity, serving as a key index for measuring the level of solar activity. In this study, the Variational Mode Decomposition (VMD) and Long Short‐term Memory (LSTM) network are combined to construct a VMD‐LSTM model for predicting F10.7 values. The F10.7 sequence is decomposed into several intrinsic mode functions (IMF) by VMD, then the LSTM neural network is utilized to forecast each IMF. All IMF prediction results are aggregated to obtain the final F10.7 value. The data sets from 1957 to 2008 are used for training and the data sets from 2009 to 2019 are used for testing. The results show that the VMD‐LSTM model achieves an annual average root mean square error of only 4.47 sfu and an annual average correlation coefficient (R) of 0.99 during solar cycle 24, which is significantly better than the accuracy of the LSTM model (W. Zhang et al., 2022, https://doi.org/10.3390/universe8010030), the AR model (Du, 2020, https://doi.org/10.1007/s11207-020-01689-x), and the BP model (Xiao et al., 2017, https://doi.org/10.11728/cjss2017.01.001). The VMD‐LSTM model exhibits strong predictive capability for the F10.7 index during solar cycle 24.https://doi.org/10.1029/2023SW003552 |
| spellingShingle | Yuhang Hao Jianyong Lu Guangshuai Peng Ming Wang Jingyuan Li Guanchun Wei F10.7 Daily Forecast Using LSTM Combined With VMD Method Space Weather |
| title | F10.7 Daily Forecast Using LSTM Combined With VMD Method |
| title_full | F10.7 Daily Forecast Using LSTM Combined With VMD Method |
| title_fullStr | F10.7 Daily Forecast Using LSTM Combined With VMD Method |
| title_full_unstemmed | F10.7 Daily Forecast Using LSTM Combined With VMD Method |
| title_short | F10.7 Daily Forecast Using LSTM Combined With VMD Method |
| title_sort | f10 7 daily forecast using lstm combined with vmd method |
| url | https://doi.org/10.1029/2023SW003552 |
| work_keys_str_mv | AT yuhanghao f107dailyforecastusinglstmcombinedwithvmdmethod AT jianyonglu f107dailyforecastusinglstmcombinedwithvmdmethod AT guangshuaipeng f107dailyforecastusinglstmcombinedwithvmdmethod AT mingwang f107dailyforecastusinglstmcombinedwithvmdmethod AT jingyuanli f107dailyforecastusinglstmcombinedwithvmdmethod AT guanchunwei f107dailyforecastusinglstmcombinedwithvmdmethod |