Three-day Forecasting of Solar Wind Speed Using SDO/AIA Extreme-ultraviolet Images by a Deep-learning Model
In this study, we forecast solar wind speed for the next 3 days with a 6 hr cadence using a deep-learning model. For this we use Solar Dynamics Observatory/Atmospheric Imaging Assembly 211 and 193 Å images together with solar wind speeds for the last 5 days as input data. The total period of the dat...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | The Astrophysical Journal Supplement Series |
| Subjects: | |
| Online Access: | https://doi.org/10.3847/1538-4365/ace59a |
| _version_ | 1797697935302983680 |
|---|---|
| author | Jihyeon Son Suk-Kyung Sung Yong-Jae Moon Harim Lee Hyun-Jin Jeong |
| author_facet | Jihyeon Son Suk-Kyung Sung Yong-Jae Moon Harim Lee Hyun-Jin Jeong |
| author_sort | Jihyeon Son |
| collection | DOAJ |
| description | In this study, we forecast solar wind speed for the next 3 days with a 6 hr cadence using a deep-learning model. For this we use Solar Dynamics Observatory/Atmospheric Imaging Assembly 211 and 193 Å images together with solar wind speeds for the last 5 days as input data. The total period of the data is from 2010 May to 2020 December. We divide them into a training set (January–August), validation set (September), and test set (October–December), to consider the solar cycle effect. The deep-learning model consists of two networks: a convolutional layer–based network for images and a dense layer–based network for solar wind speeds. Our main results are as follows. First, our model successfully predicts the solar wind speed for the next 3 days. The rms error (RMSE) of our model is from 37.4 km s ^−1 (for the 6 hr prediction) to 68.2 km s ^−1 (for the 72 hr prediction), and the correlation coefficient is from 0.92 to 0.67. These results are much better than those of previous studies. Second, the model can predict sudden increase of solar wind speeds caused by large equatorial coronal holes. Third, solar wind speeds predicted by our model are more consistent with observations than those by the Wang–Sheely–Arge–ENLIL model, especially in high-speed-stream regions. It is also noted that our model cannot predict solar wind speed enhancement by coronal mass ejections. Our study demonstrates the effectiveness of deep learning for solar wind speed prediction, with potential applications in space weather forecasting. |
| first_indexed | 2024-03-12T03:47:05Z |
| format | Article |
| id | doaj.art-f78e9d5d79fc48c080d2cba86f664243 |
| institution | Directory Open Access Journal |
| issn | 0067-0049 |
| language | English |
| last_indexed | 2024-03-12T03:47:05Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | The Astrophysical Journal Supplement Series |
| spelling | doaj.art-f78e9d5d79fc48c080d2cba86f6642432023-09-03T12:44:52ZengIOP PublishingThe Astrophysical Journal Supplement Series0067-00492023-01-0126724510.3847/1538-4365/ace59aThree-day Forecasting of Solar Wind Speed Using SDO/AIA Extreme-ultraviolet Images by a Deep-learning ModelJihyeon Son0https://orcid.org/0000-0003-2678-5718Suk-Kyung Sung1Yong-Jae Moon2https://orcid.org/0000-0001-6216-6944Harim Lee3https://orcid.org/0000-0002-9300-8073Hyun-Jin Jeong4https://orcid.org/0000-0003-4616-947XSchool of Space Research, Kyung Hee University , Yongin, 17104, Republic of Korea ; moonyj@khu.ac.krDepartment of Astronomy and Space Science, Kyung Hee University , Yongin, 17104, Republic of KoreaSchool of Space Research, Kyung Hee University , Yongin, 17104, Republic of Korea ; moonyj@khu.ac.kr; Department of Astronomy and Space Science, Kyung Hee University , Yongin, 17104, Republic of KoreaDepartment of Astronomy and Space Science, Kyung Hee University , Yongin, 17104, Republic of KoreaDepartment of Astronomy and Space Science, Kyung Hee University , Yongin, 17104, Republic of KoreaIn this study, we forecast solar wind speed for the next 3 days with a 6 hr cadence using a deep-learning model. For this we use Solar Dynamics Observatory/Atmospheric Imaging Assembly 211 and 193 Å images together with solar wind speeds for the last 5 days as input data. The total period of the data is from 2010 May to 2020 December. We divide them into a training set (January–August), validation set (September), and test set (October–December), to consider the solar cycle effect. The deep-learning model consists of two networks: a convolutional layer–based network for images and a dense layer–based network for solar wind speeds. Our main results are as follows. First, our model successfully predicts the solar wind speed for the next 3 days. The rms error (RMSE) of our model is from 37.4 km s ^−1 (for the 6 hr prediction) to 68.2 km s ^−1 (for the 72 hr prediction), and the correlation coefficient is from 0.92 to 0.67. These results are much better than those of previous studies. Second, the model can predict sudden increase of solar wind speeds caused by large equatorial coronal holes. Third, solar wind speeds predicted by our model are more consistent with observations than those by the Wang–Sheely–Arge–ENLIL model, especially in high-speed-stream regions. It is also noted that our model cannot predict solar wind speed enhancement by coronal mass ejections. Our study demonstrates the effectiveness of deep learning for solar wind speed prediction, with potential applications in space weather forecasting.https://doi.org/10.3847/1538-4365/ace59aThe SunConvolutional neural networksSolar wind |
| spellingShingle | Jihyeon Son Suk-Kyung Sung Yong-Jae Moon Harim Lee Hyun-Jin Jeong Three-day Forecasting of Solar Wind Speed Using SDO/AIA Extreme-ultraviolet Images by a Deep-learning Model The Astrophysical Journal Supplement Series The Sun Convolutional neural networks Solar wind |
| title | Three-day Forecasting of Solar Wind Speed Using SDO/AIA Extreme-ultraviolet Images by a Deep-learning Model |
| title_full | Three-day Forecasting of Solar Wind Speed Using SDO/AIA Extreme-ultraviolet Images by a Deep-learning Model |
| title_fullStr | Three-day Forecasting of Solar Wind Speed Using SDO/AIA Extreme-ultraviolet Images by a Deep-learning Model |
| title_full_unstemmed | Three-day Forecasting of Solar Wind Speed Using SDO/AIA Extreme-ultraviolet Images by a Deep-learning Model |
| title_short | Three-day Forecasting of Solar Wind Speed Using SDO/AIA Extreme-ultraviolet Images by a Deep-learning Model |
| title_sort | three day forecasting of solar wind speed using sdo aia extreme ultraviolet images by a deep learning model |
| topic | The Sun Convolutional neural networks Solar wind |
| url | https://doi.org/10.3847/1538-4365/ace59a |
| work_keys_str_mv | AT jihyeonson threedayforecastingofsolarwindspeedusingsdoaiaextremeultravioletimagesbyadeeplearningmodel AT sukkyungsung threedayforecastingofsolarwindspeedusingsdoaiaextremeultravioletimagesbyadeeplearningmodel AT yongjaemoon threedayforecastingofsolarwindspeedusingsdoaiaextremeultravioletimagesbyadeeplearningmodel AT harimlee threedayforecastingofsolarwindspeedusingsdoaiaextremeultravioletimagesbyadeeplearningmodel AT hyunjinjeong threedayforecastingofsolarwindspeedusingsdoaiaextremeultravioletimagesbyadeeplearningmodel |