Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification
Abstract We propose a novel deep learning framework, named SYMHnet, which employs a graph neural network and a bidirectional long short‐term memory network to cooperatively learn patterns from solar wind and interplanetary magnetic field parameters for short‐term forecasts of the SYM‐H index based o...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-02-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2023SW003824 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536425274638336 |
|---|---|
| author | Yasser Abduallah Khalid A. Alobaid Jason T. L. Wang Haimin Wang Vania K. Jordanova Vasyl Yurchyshyn Huseyin Cavus Ju Jing |
| author_facet | Yasser Abduallah Khalid A. Alobaid Jason T. L. Wang Haimin Wang Vania K. Jordanova Vasyl Yurchyshyn Huseyin Cavus Ju Jing |
| author_sort | Yasser Abduallah |
| collection | DOAJ |
| description | Abstract We propose a novel deep learning framework, named SYMHnet, which employs a graph neural network and a bidirectional long short‐term memory network to cooperatively learn patterns from solar wind and interplanetary magnetic field parameters for short‐term forecasts of the SYM‐H index based on 1‐ and 5‐min resolution data. SYMHnet takes, as input, the time series of the parameters' values provided by NASA's Space Science Data Coordinated Archive and predicts, as output, the SYM‐H index value at time point t + w hours for a given time point t where w is 1 or 2. By incorporating Bayesian inference into the learning framework, SYMHnet can quantify both aleatoric (data) uncertainty and epistemic (model) uncertainty when predicting future SYM‐H indices. Experimental results show that SYMHnet works well at quiet time and storm time, for both 1‐ and 5‐min resolution data. The results also show that SYMHnet generally performs better than related machine learning methods. For example, SYMHnet achieves a forecast skill score (FSS) of 0.343 compared to the FSS of 0.074 of a recent gradient boosting machine (GBM) method when predicting SYM‐H indices (1 hr in advance) in a large storm (SYM‐H = −393 nT) using 5‐min resolution data. When predicting the SYM‐H indices (2 hr in advance) in the large storm, SYMHnet achieves an FSS of 0.553 compared to the FSS of 0.087 of the GBM method. In addition, SYMHnet can provide results for both data and model uncertainty quantification, whereas the related methods cannot. |
| format | Article |
| id | doaj-art-a3a44d9538a24b15ba752280633f7fd0 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2024-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-a3a44d9538a24b15ba752280633f7fd02025-01-14T16:30:41ZengWileySpace Weather1542-73902024-02-01222n/an/a10.1029/2023SW003824Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty QuantificationYasser Abduallah0Khalid A. Alobaid1Jason T. L. Wang2Haimin Wang3Vania K. Jordanova4Vasyl Yurchyshyn5Huseyin Cavus6Ju Jing7Institute for Space Weather Sciences New Jersey Institute of Technology Newark NJ USAInstitute for Space Weather Sciences New Jersey Institute of Technology Newark NJ USAInstitute for Space Weather Sciences New Jersey Institute of Technology Newark NJ USAInstitute for Space Weather Sciences New Jersey Institute of Technology Newark NJ USALos Alamos National Laboratory Space Science and Applications Los Alamos NM USABig Bear Solar Observatory New Jersey Institute of Technology Big Bear City CA USADepartment of Physics Canakkale Onsekiz Mart University Canakkale TurkeyInstitute for Space Weather Sciences New Jersey Institute of Technology Newark NJ USAAbstract We propose a novel deep learning framework, named SYMHnet, which employs a graph neural network and a bidirectional long short‐term memory network to cooperatively learn patterns from solar wind and interplanetary magnetic field parameters for short‐term forecasts of the SYM‐H index based on 1‐ and 5‐min resolution data. SYMHnet takes, as input, the time series of the parameters' values provided by NASA's Space Science Data Coordinated Archive and predicts, as output, the SYM‐H index value at time point t + w hours for a given time point t where w is 1 or 2. By incorporating Bayesian inference into the learning framework, SYMHnet can quantify both aleatoric (data) uncertainty and epistemic (model) uncertainty when predicting future SYM‐H indices. Experimental results show that SYMHnet works well at quiet time and storm time, for both 1‐ and 5‐min resolution data. The results also show that SYMHnet generally performs better than related machine learning methods. For example, SYMHnet achieves a forecast skill score (FSS) of 0.343 compared to the FSS of 0.074 of a recent gradient boosting machine (GBM) method when predicting SYM‐H indices (1 hr in advance) in a large storm (SYM‐H = −393 nT) using 5‐min resolution data. When predicting the SYM‐H indices (2 hr in advance) in the large storm, SYMHnet achieves an FSS of 0.553 compared to the FSS of 0.087 of the GBM method. In addition, SYMHnet can provide results for both data and model uncertainty quantification, whereas the related methods cannot.https://doi.org/10.1029/2023SW003824 |
| spellingShingle | Yasser Abduallah Khalid A. Alobaid Jason T. L. Wang Haimin Wang Vania K. Jordanova Vasyl Yurchyshyn Huseyin Cavus Ju Jing Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification Space Weather |
| title | Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification |
| title_full | Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification |
| title_fullStr | Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification |
| title_full_unstemmed | Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification |
| title_short | Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification |
| title_sort | prediction of the sym h index using a bayesian deep learning method with uncertainty quantification |
| url | https://doi.org/10.1029/2023SW003824 |
| work_keys_str_mv | AT yasserabduallah predictionofthesymhindexusingabayesiandeeplearningmethodwithuncertaintyquantification AT khalidaalobaid predictionofthesymhindexusingabayesiandeeplearningmethodwithuncertaintyquantification AT jasontlwang predictionofthesymhindexusingabayesiandeeplearningmethodwithuncertaintyquantification AT haiminwang predictionofthesymhindexusingabayesiandeeplearningmethodwithuncertaintyquantification AT vaniakjordanova predictionofthesymhindexusingabayesiandeeplearningmethodwithuncertaintyquantification AT vasylyurchyshyn predictionofthesymhindexusingabayesiandeeplearningmethodwithuncertaintyquantification AT huseyincavus predictionofthesymhindexusingabayesiandeeplearningmethodwithuncertaintyquantification AT jujing predictionofthesymhindexusingabayesiandeeplearningmethodwithuncertaintyquantification |