Abstract
The daily 10.7-cm solar radio flux (F10.7) is one of the most important solar activity indices and has been widely applied in various space environment modeling as a crucial parameter. In this study, we adopt a deep-learning Informer model, based on the transformer architecture to predict the medium-term F10.7 index, which uses 48 historical daily F10.7 indices as input to directly forecast the following 1 – 27 days’ F10.7 index. The model is demonstrated to be effective and to have superior performance compared with other widely-used forecasting techniques: two statistical methods provided by British Geological Survey (BGS), Space Weather Prediction Center (SWPC), and a multiflux neural network method provided by Collecte Localisation Satellites (CLS). In comparison, the Informer model significantly improves the forecast accuracy for the prediction horizon larger than 6 days, especially during the solar activity descending phase and at the solar activity minimum. For its effectiveness, accurate prediction capability and the advantage in F10.7 forecasting with longer horizon, the Informer could be potentially used as a candidate model for space weather operational forecasting.
Similar content being viewed by others
Data Availability
The yearly average total sunspot numbers are available at Solar Influences Data Analysis Center (https://www.sidc.be/SILSO/dayssnplot). The observed values of F10.7 are downloaded from OMNIWeb service (https://omniweb.gsfc.nasa.gov/form/dx1.html). The prediction data of BGS and SWPC can be obtained through the European Space Agency (ESA) data platform (https://swe.ssa.esa.int/web/guest/forind-federated). The CLS model’s prediction data can be found at the official website (https://spaceweather.cls.fr/services/radioflux/).
References
Bilitza, D.: 2018, IRI the international standard for the ionosphere. Adv. Radio Sci. 16, 1.
Bowman, B., Tobiska, W.K., Marcos, F., Huang, C., Lin, C., Burke, W.: 2008, A new empirical thermospheric density model JB2008 using new solar and geomagnetic indices. In: AIAA/AAS Astrodynamics Specialist Conf., 6438.
Bruinsma, S., Boniface, C.: 2021, The operational and research DTM-2020 thermosphere models. J. Space Weather Space Clim. 11, 47.
Covington, A.E.: 1969, Solar radio emission at 10.7 cm, 1947-1968. J. Roy. Astron. Soc. Can. 63, 125.
Du, Z.: 2020, Forecasting the daily 10.7 cm solar radio flux using an autoregressive model. Solar Phys. 295, 125.
Elvidge, S., Themens, D.R., Brown, M.K., Donegan-Lawley, E.: 2023, What to do when the F10. 7 goes out? Space Weather 21, e2022SW003392.
Feynman, J., Gabriel, S.: 2000, On space weather consequences and predictions. J. Geophys. Res. 105, 10543.
Gulati, A., Qin, J., Chiu, C.-C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., et al.: 2020. Conformer: convolution-augmented transformer for speech recognition. arXiv.
Kalyan, K.S., Rajasekharan, A., Sangeetha, S.: 2021, Ammus: a survey of transformer-based pretrained models in natural language processing. arXiv.
Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: 2022 Transformers in vision: a survey. ACM Comput. Surv. 54 1.
Lei, L., Zhong, Q., Wang, J., Shi, L., Liu, S., et al.: 2019, The mid-term forecast method of f 10.7 based on extreme ultraviolet images. Adv. Astron. 2019 Article ID 5604092.
Liu, C.-A., Zhao, X.-H., Chen, T., Li, H.-C.: 2018, Predicting short-term F 10.7 with transport models. Astrophys. Space Sci. 363, 266.
Oreshkin, B.N., Carpov, D., Chapados, N., Bengio, Y.: 2019, N-BEATS: neural basis expansion analysis for interpretable time series forecasting. arXiv.
Picone, J., Hedin, A., Drob, D.P., Aikin, A.: 2002, NRLMSISE-00 empirical model of the atmosphere: statistical comparisons and scientific issues. J. Geophys. Res. 107, SIA 15-1.
Riley, P., Baker, D., Liu, Y.D., Verronen, P., Singer, H., Güdel, M.: 2018, Extreme space weather events: from cradle to grave. Space Sci. Rev. 214, 1.
Stevenson, E., Rodriguez-Fernandez, V., Minisci, E., Camacho, D.: 2022, A deep learning approach to solar radio flux forecasting. Acta Astronaut. 193, 595.
Su, Y., Bailey, G., Fukao, S.: 1999, Altitude dependencies in the solar activity variations of the ionospheric electron density. J. Geophys. Res. 104, 14879.
Tapping, K.: 2013, The 10.7 cm solar radio flux (F10. 7). Space Weather 11, 394.
To, A.S., James, A.W., Bastian, T., van Driel-Gesztelyi, L., Long, D.M., Baker, D., Brooks, D.H., Lomuscio, S., Stansby, D., Valori, G.: 2023, Understanding the relationship between solar coronal abundances and F10. 7 cm radio emission. Astrophys. J. 948, 121.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: 2017, Attention is all you need. In: Adv. Neural Inf. Process. Syst. 30.
Wang, H.B., Xiong, J.N., Zhao, C.Y.: 2015, The mid-term forecast method of solar radiation index. Chin. Astron. Astrophys. 39, 198.
Wang, Z., Hu, Q., Zhong, Q., Wang, Y.: 2018, Linear multistep F10. 7 forecasting based on task correlation and heteroscedasticity. Earth Space Sci. 5, 863.
Warren, H.P., Emmert, J.T., Crump, N.A.: 2017, Linear forecasting of the F 10.7 proxy for solar activity. Space Weather 15, 1039.
Worden, J., Harvey, J.: 2000, An evolving synoptic magnetic flux map and implications for the distribution of photospheric magnetic flux. Solar Phys. 195, 247.
Yaya, P., Hecker, L., de Wit, T.D., Le Fèvre, C., Bruinsma, S.: 2017, Solar radio proxies for improved satellite orbit prediction. J. Space Weather Space Clim. 7, A35.
Yeates, A., Mackay, D., van Ballegooijen, A.: 2007, Modelling the global solar corona: filament chirality observations and surface simulations. Solar Phys. 245, 87.
Zhang, W., Zhao, X., Feng, X., Liu, C., Xiang, N., Li, Z., Lu, W.: 2022, Predicting the daily 10.7-cm solar radio flux using the long short-term memory method. Universe 8, 30.
Zhao, J., Han, Y.-B.: 2008, Historical dataset reconstruction and a prediction method of solar 10.7 cm radio flux. Chin. J. Astron. Astrophys. 8, 472.
Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., Zhang, W.: 2021, Informer: beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence 35, 11106.
Acknowledgments
We greatly acknowledge British Geological Survey (BGS), Collecte Localisation Satellites (CLS), and the Space Weather Prediction Center (SWPC), as well as the National Geophysical Data Center (NOAA) for providing the data necessary to carry out this work. We also thank Haoyi Zhou, the creator of the Informer model, for answering questions on the details and providing valuable insights.
Funding
This work is jointly supported by National Key Research and Development Program of China (grant No. 2022YFF0503904), the National Natural Science Foundation of China (grant No. 42074205), Guangdong Basic and Applied Basic Research Foundation (grant No. 2023B1515040021), Hong Kong–Macao Exchange Project of Harbin Institute of Technology, Shenzhen Key Laboratory Launching Project (grant No. ZDSYS20210702140800001), Shenzhen Science and Technology Program (grant No. JCYJ20220818102401003) and the Science and Technology Development Fund of Macao SAR (File No. 0048/2021/A).
Author information
Authors and Affiliations
Contributions
Zhang, Zuo and Zou wrote the main manuscript text and Feng prepared Figures 1-5. Huang and Wang prepared Figures 5-10. Wei and Yang prepared Tables 1-4. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
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
Zhang, K., Zuo, P., Zou, Z. et al. Forecasting Medium-Term F10.7 Using the Deep-Learning Informer Model. Sol Phys 299, 47 (2024). https://doi.org/10.1007/s11207-024-02284-0
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11207-024-02284-0