Abstract
Geomagnetic activities have a crucial impact on Earth, which can affect spacecraft and electrical power grids. Geospace scientists use a geomagnetic index, called the Kp index, to describe the overall level of geomagnetic activity. This index is an important indicator of disturbances in the Earth’s magnetic field and is used by the U.S. Space Weather Prediction Center as an alert and warning service for users who may be affected by the disturbances. Another commonly used index, called the ap index, is converted from the Kp index. Early and accurate prediction of the Kp and ap indices is essential for preparedness and disaster risk management. In this paper, we present a deep learning framework, named GNet, to perform short-term forecasting of the Kp and ap indices. Specifically, GNet takes as input time series of solar wind parameters’ values, provided by NASA’s Space Science Data Coordinated Archive, and predicts as output the Kp and ap indices respectively at time point \(\varvec{t + w}\) hours for a given time point \(\varvec{t}\) where \(\varvec{w}\) ranges from 1 to 9. GNet combines transformer encoder blocks with Bayesian inference, which is capable of quantifying both aleatoric uncertainty (data uncertainty) and epistemic uncertainty (model uncertainty) in making predictions. Experimental results show that GNet outperforms closely related machine learning methods in terms of the root mean square error and R-squared score. Furthermore, GNet can provide both data and model uncertainty quantification results, which the existing methods cannot offer. To our knowledge, this is the first time that Bayesian transformers have been used for geomagnetic activity prediction.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Availability of supporting data
The datasets used in this study are available from the corresponding author on request.
References
Krauss, S., Temmer, M., Veronig, A., Baur, O., & Lammer, H. (2015). Thermospheric and geomagnetic responses to interplanetary coronal mass ejections observed by ACE and GRACE: Statistical results. Journal of Geophysical Research (Space Physics), 120(10), 8848–8860. https://doi.org/10.1002/2015JA021702
Poudel, P., Simkhada, S., Adhikari, B., Sharma, D., & Nakarmi, J. J. (2019). Variation of solar wind parameters along with the understanding of energy dynamics within the magnetospheric system during geomagnetic disturbances. Earth and Space Science, 6(2), 276–293. https://doi.org/10.1029/2018EA000495
Collado-Villaverde, A., Muñoz, P., & Cid, C. (2021). Deep neural networks with convolutional and LSTM layers for SYM-H and ASY-H forecasting. Space Weather, 19(6), 02748. https://doi.org/10.1029/2021SW002748
Boberg, F., Wintoft, P., & Lundstedt, H. (2000). Real time Kp predictions from solar wind data using neural networks. Physics and Chemistry of the Earth, Part C: Solar, Terrestrial and Planetary Science, 25(4), 275–280. https://doi.org/10.1016/S1464-1917(00)00016-7
Ji, E.-Y., Moon, Y.-J., Park, J., Lee, J.-Y., & Lee, D.-H. (2013). Comparison of neural network and support vector machine methods for Kp forecasting. Journal of Geophysical Research: Space Physics, 118(8), 5109–5117. https://doi.org/10.1002/jgra.50500
Chakraborty, S., & Morley, S. K. (2020). Probabilistic prediction of geomagnetic storms and the Kp index. Journal of Space Weather and Space Climate, 10, 36. https://doi.org/10.1051/swsc/2020037
Abduallah, Y., Wang, J.T.L., Xu, C., Wang, H. (2022). A transformer-based framework for geomagnetic activity prediction. In: M. Ceci, S. Flesca, E. Masciari, G. Manco, & Z.W. Ras (Eds.), Foundations of Intelligent Systems - 26th International Symposium, ISMIS 2022, Proceedings. Lecture Notes in Computer Science (vol. 13515, pp. 325-335). Springer, Switzerland. https://doi.org/10.1007/978-3-031-16564-1_31
Zhelavskaya, I. S., Vasile, R., Shprits, Y. Y., Stolle, C., & Matzka, J. (2019). Systematic analysis of machine learning and feature selection techniques for prediction of the Kp index. Space Weather, 17(10), 1461–1486. https://doi.org/10.1029/2019SW002271
Tan, Y., Hu, Q., Wang, Z., & Zhong, Q. (2018). Geomagnetic index Kp forecasting with LSTM. Space Weather, 16(4), 406–416. https://doi.org/10.1002/2017SW001764
King, J. H., & Papitashvili, N. E. (2005). Solar wind spatial scales in and comparisons of hourly Wind and ACE plasma and magnetic field data. Journal of Geophysical Research (Space Physics), 110(A2), 02104. https://doi.org/10.1029/2004JA010649
Lethy, A., El-Eraki, M. A., Samy, A., & Deebes, H. A. (2018). Prediction of the Dst index and analysis of its dependence on solar wind parameters using neural network. Space Weather, 16(9), 1277–1290. https://doi.org/10.1029/2018SW001863
Siciliano, F., Consolini, G., Tozzi, R., Gentili, M., Giannattasio, F., & De Michelis, P. (2021). Forecasting SYM-H index: A comparison between long short-term memory and convolutional neural networks. Space Weather, 19(2), 2020–002589. https://doi.org/10.1029/2020SW002589
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., & Kaiser, L.u., & Polosukhin, I. (2017). Attention is all you need. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in Neural Information Processing Systems. (Vol. 30). Red Hook, NY, USA: Curran Associates Inc.
Zerveas, G., Jayaraman, S., Patel, D., Bhamidipaty, A., & Eickhoff, C. (2021). A transformer-based framework for multivariate time series representation learning. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 2114-2124. Association for Computing Machinery, New York, NY, USA https://doi.org/10.1145/3447548.3467401
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(56), 1929–1958.
Lim, H.-I. (2021). A study on dropout techniques to reduce overfitting in deep neural networks. In J. J. Park, V. Loia, Y. Pan, & Y. Sung (Eds.), Advanced Multimedia and Ubiquitous Engineering (pp. 133–139). Singapore: Springer.
Tran, D., Dusenberry, M.W., Wilk, M., & Hafner, D. (2019). Bayesian layers: A module for neural network uncertainty. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems, pp. 14660-14672. Curran Associates Inc., Red Hook, NY, USA
Blei, D. M., Kucukelbir, A., & McAuliffe, J. D. (2016). Variational inference: A review for statisticians. Journal of the American Statistical Association, 112, 859–877. https://doi.org/10.1080/01621459.2017.1285773
Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In: Proceedings of the 33rd International Conference on Machine Learning, pp. 1050-1059 https://doi.org/10.5555/3045390.3045502
Jiang, H., Jing, J., Wang, J., Liu, C., Li, Q., Xu, Y., Wang, J. T. L., & Wang, H. (2021). Tracing H\(\alpha \) fibrils through Bayesian deep learning. The Astrophysical Journal Supplement Series, 256(1), 20. https://doi.org/10.3847/1538-4365/ac14b7
Graves, A. (2011). Practical variational inference for neural networks. In J. Shawe-Taylor, R. Zemel, P. Bartlett, F. Pereira, & K. Q. Weinberger (Eds.), Advances in Neural Information Processing Systems. (Vol. 24). Red Hook, NY, USA: Curran Associates Inc.
Ling, Z.-H., & Dai, L.-R. (2012). Minimum KullbackLeibler divergence parameter generation for HMM-based speech synthesis. IEEE Transactions on Audio, Speech, and Language Processing, 20(5), 1492–1502. https://doi.org/10.1109/TASL.2011.2182511
Goodfellow, I. J., Bengio, Y., & Courville, A. C. (2016). Deep Learning. Cambridge, MA, USA: MIT Press.
Kwon, Y., Won, J.-H., Kim, B. J., & Paik, M. C. (2020). Uncertainty quantification using Bayesian neural networks in classification: Application to biomedical image segmentation. Computational Statistics & Data Analysis, 142, 106816. https://doi.org/10.1016/j.csda.2019.106816
Liu, H., Xu, Y., Wang, J., Jing, J., Liu, C., Wang, J. T. L., & Wang, H. (2020). Inferring vector magnetic fields from stokes profiles of GST/NIRIS using a convolutional neural network. The Astrophysical Journal, 894(1), 70. https://doi.org/10.3847/1538-4357/ab8818
Abduallah, Y., Wang, J.T.L., Shen, Y., Alobaid, K.A., Criscuoli, S., Wang, H. (2021). Reconstruction of total solar irradiance by deep learning. In: E. Bell, & F. Keshtkar (Eds.), Proceedings of the Thirty-Fourth International Florida Artificial Intelligence Research Society Conference. https://doi.org/10.32473/flairs.v34i1.128356
Alobaid, K. A., Abduallah, Y., Wang, J. T. L., Wang, H., Jiang, H., Xu, Y., Yurchyshyn, V., Zhang, H., Cavus, H., & Jing, J. (2022). Predicting CME arrival time through data integration and ensemble learning. Frontiers in Astronomy and Space Sciences, 9, 1013345. https://doi.org/10.3389/fspas.2022.1013345
Abduallah, Y., Wang, J.T.L., Bose, P., Zhang, G., Gerges, F., Wang, H. (2022). Forecasting the disturbance storm time index with Bayesian deep learning. In: R. Barták, F. Keshtkar, & M. Franklin (Eds.), Proceedings of the Thirty-Fifth International Florida Artificial Intelligence Research Society Conference. https://doi.org/10.32473/flairs.v35i.130564
Abduallah, Y., Wang, J. T. L., Nie, Y., Liu, C., & Wang, H. (2021). DeepSun: Machine-learning-as-a-service for solar flare prediction. Research in Astronomy and Astrophysics, 21(7), 160. https://doi.org/10.1088/1674-4527/21/7/160
Acknowledgements
The authors acknowledge the use of NASA/GSFC’s OMNIWeb and OMNI data.
Funding
This work was supported in part by the U.S. National Science Foundation under Grant Nos. AGS-1927578 and AGS-2149748.
Author information
Authors and Affiliations
Contributions
J.W. and H.W. conceived the study. Y.A. and J.J. collected the data. J.W. and Y.A. designed and conducted the experiments. All authors co-wrote and reviewed the manuscript.
Corresponding author
Ethics declarations
Ethical approval
Not applicable.
Conflict of interests
The authors declare that they have no conflict of interest.
Competing interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Abduallah, Y., Wang, J.T.L., Wang, H. et al. A transformer-based framework for predicting geomagnetic indices with uncertainty quantification. J Intell Inf Syst (2023). https://doi.org/10.1007/s10844-023-00828-7
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10844-023-00828-7