BaLNet: A probabilistic Bayesian neural network for solar wind speed forecasting | Journal of Space Weather and Space Climate

Open Access

Issue		J. Space Weather Space Clim. Volume 15, 2025


Article Number		34
Number of page(s)		18
DOI		https://doi.org/10.1051/swsc/2025029
Published online		21 August 2025

Abadi, M, Barham P, Chen J, Chen Z, Davis A, et al. 2016. Tensorflow: A system for large-scale machine learning. In: Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16), November 2–4, 2016, Savannah, USA, GA. [Google Scholar]
Arge, CN, Odstrcil D, Pizzo VJ, Mayer LR. 2003. Improved method for specifying solar wind speed near the sun. AIP Conf Proc 679 (1): 190–193. https://doi.org/10.1063/1.1618574. [Google Scholar]
Berndt, DJ, Clifford J. 1994. Using dynamic time warping to find patterns in time series. In: Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining, AAAIWS’94. AAAI Press, pp. 359–370. https://doi.org/10.5555/3000850.3000887. [Google Scholar]
Blei, DM, Kucukelbir A, McAuliffe JD. 2017. Variational inference: A review for statisticians. J Am Stat Assoc 112 (518): 859–877. https://doi.org/10.1080/01621459.2017.1285773. [Google Scholar]
Boucheron, LE, Valluri M, McAteer RTJ. 2016. Segmentation of coronal holes using active contours without edges. Sol Phys 291 (8): 2353–2372. https://doi.org/10.1007/s11207-016-0985-z. [Google Scholar]
Brown, EJE, Svoboda F, Meredith NP, Lane N, Horne RB. 2022. Attention-based machine vision models and techniques for solar wind speed forecasting using solar EUV images. Space Weather 20 (3): e2021SW002976. https://doi.org/10.1029/2021SW002976. [Google Scholar]
Caceres, J, Gonzalez D, Zhou T, Droguett EL. 2021. A probabilistic Bayesian recurrent neural network for remaining useful life prognostics considering epistemic and aleatory uncertainties. Struct Control Health Monit 28 (10): e2811. https://doi.org/10.1002/stc.2811. [Google Scholar]
Camporeale, E. 2019. The challenge of machine learning in space weather: nowcasting and forecasting. Space Weather 17 (8): 1166–1207. https://doi.org/10.1029/2018SW002061. [CrossRef] [Google Scholar]
Camporeale, E, Chu X, Agapitov OV, Bortnik J. 2019. On the generation of probabilistic forecasts from deterministic models. Space Weather 17 (3): 455–475. https://doi.org/10.1029/2018SW002026. [CrossRef] [Google Scholar]
Charnock, T, Perreault-Levasseur L, Lanusse F. 2022. Bayesian neural networks. In: Artificial Intelligence for High Energy Physics, World Scientific, pp. 663–713. https://doi.org/10.1142/9789811234033_0018. [Google Scholar]
Clark, S, Hyndman RJ, Pagendam D, Ryan LM. 2020. Modern strategies for time series regression. Int Stat Rev 88 (S1): S179–S204. https://doi.org/10.1111/insr.12432. [Google Scholar]
Cobos Maestre, M. 2020. Coronal hole tracking using Big Data and Computer Vision, Master’s Thesis, Universidad de Alcalá, Alcalá de Henares, Madrid, Spain. [Google Scholar]
Cobos-Maestre, M, Flores-Soriano M, Barrero DF. 2024. SWAN: A multihead autoregressive attention model for solar wind speed forecasting. Expert Syst With Appl 252: 124128. https://doi.org/10.1016/j.eswa.2024.124128. [Google Scholar]
Collado-Villaverde A, Muñoz P, Cid C. 2024. Operational SYM-H forecasting with confidence intervals using deep neural networks. Space Weather 22 (10): 1–2. [Google Scholar]
Cranmer, SR. 2009. Coronal holes. Liv Rev Sol Phys 6 (1): 3. https://doi.org/10.12942/lrsp-2009-3. [Google Scholar]
Dillon, JV, Langmore I, Tran D, Brevdo E, Vasudevan S, Moore D, Patton B, Alemi A, Hoffman M, SaurousRA. 2017. Tensorflow distributions. arXiv preprint https://doi.org/10.48550/arXiv.1711.10604. [Google Scholar]
Duan, H, Yang L, Fang J, Li H. 2017. Fast inverse-free sparse Bayesian learning via relaxed evidence lower bound maximization. IEEE Signal Process Lett 24 (6): 774–778. https://doi.org/10.1109/LSP.2017.2692217. [Google Scholar]
Dudley, RM. 1978. Central limit theorems for empirical measures. Ann Probability 6 (6): 899–929. http://www.jstor.org/stable/2243028. [Google Scholar]
Le Folgoc, L, Baltatzis V, Desai S, Devaraj A, Ellis S, Martinez Manzanera OE, Nair A, Qiu H, Schnabel J, Glocker B. 2021. Is MC dropout Bayesian? arXiv preprint arXiv:2110.04286. https://doi.org/10.48550/arXiv.2110.04286. [Google Scholar]
Fortuin, V. 2022. Priors in Bayesian deep learning: A review. Int Stat Rev 90 (3): 563–591. https://doi.org/10.1111/insr.12502. [Google Scholar]
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, MF, Balcan, Weinberger KQ (Eds.), vol. 48 of Proceedings of Machine Learning Research. PMLR, New York, NY, USA, pp. 1050–1059. https://proceedings.mlr.press/v48/gal16.html. [Google Scholar]
Ghojogh, B, Crowley M. 2019. The theory behind overfitting, cross validation, regularization, bagging, and boosting: tutorial. https://doi.org/10.48550/arXiv.1905.12787. [Google Scholar]
Guzmán-Martínez, R, Alaiz-Rodríguez R. 2011. Feature selection stability assessment based on the Jensen-Shannon Divergence. In : Machine Learning and Knowledge Discovery in Databases, D, Gunopulos, Hofmann T, Malerba D, Vazirgiannis M, (Eds.) Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 597–612. ISBN 978-3-642-23780-5. [Google Scholar]
Harris, CR, Millman KJ, van der Walt SJ, Gommers R, Virtanen P, et al. 2020. Array programming with NumPy. Nature 585 (7825): 357–362. https://doi.org/10.1038/s41586-020-2649-2. [NASA ADS] [CrossRef] [Google Scholar]
Hochreiter, S, Schmidhuber J. 1997. Long short-term memory. Neural Comput 9 (8): 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735.. [CrossRef] [PubMed] [Google Scholar]
Hofmeister, SJ, Asvestari E, Guo J, Heidrich-Meisner V, Heinemann SG, et al. 2022. How the area of solar coronal holes affects the properties of high-speed solar wind streams near Earth: An analytical model. A&A, 659: A190. https://doi.org/10.1051/0004-6361/202141919. [NASA ADS] [CrossRef] [EDP Sciences] [Google Scholar]
Huang, Z, Lam H, Zhang H. 2023. Conditional coverage estimation for high-quality prediction intervals. J Syst Sci Syst Eng 32 (3): 289–319. https://doi.org/10.1007/s11518-023-5560-1. [Google Scholar]
Jankowiak, M, Obermeyer F. 2018. Pathwise Derivatives Beyond the Reparameterization Trick. In: Proceedings of the 35th International Conference on Machine Learning, vol. 80 of Proceedings of Machine Learning Research, J, Dy, Krause A (Eds.), PMLR. https://proceedings.mlr.press/v80/jankowiak18a.html. [Google Scholar]
Krista, LD, Gallagher PT. 2009. Automated coronal hole detection using local intensity thresholding techniques. Sol Phys 256 (1): 87–100. https://doi.org/10.1007/s11207-009-9357-2. [Google Scholar]
Kullback, S, Leibler RA. 1951. On information and sufficiency. Ann Math Stat 22 (1): 79–86. [CrossRef] [Google Scholar]
Kuznetsov, V, Mohri M. Learning theory and algorithms for forecasting non-stationary time series. In: C, Cortes, Lawrence N, Lee D, Sugiyama M, Garnett R. 2015. Advances in neural information processing systems, vol. 28. Curran Associates Inc. https://proceedings.neurips.cc/paper_files/paper/2015/file/41f1f19176d383480afa65d325c06ed0-Paper.pdf. [Google Scholar]
Kvålseth, TO. 1985. Cautionary note about R². Am Stat. 39 (4): 279–285. [Google Scholar]
Larrodera, C, Cid C. 2020. Bimodal distribution of the solar wind at 1 AU. A&A, 635, A44. https://doi.org/10.1051/0004-6361/201937307. [NASA ADS] [CrossRef] [EDP Sciences] [Google Scholar]
Lemen, JR, Title AM, Akin DJ, Boerner PF, Chou C, et al. 2012. The Atmospheric Imaging Assembly (AIA) on the Solar Dynamics Observatory (SDO). Springer US, New York, NY, pp. 17–40. ISBN 978-1-4614-3673-7. https://doi.org/10.1007/978-1-4614-3673-7_3. [Google Scholar]
MacKay, DJ. 1995. Probable networks and plausible predictions-a review of practical Bayesian methods for supervised neural networks. Network Comput Neural Syst 6 (3): 469. https://doi.org/10.1088/0954-898X/6/3/011. [Google Scholar]
Magris, M, Iosifidis A. 2023. Bayesian learning for neural networks: an algorithmic survey. Artif Intell Rev 56 (10): 11773–11823. https://doi.org/10.1007/s10462-023-10443-1. [Google Scholar]
Massey, F, Jr. 1951. The Kolmogorov-Smirnov Test for Goodness of Fit. J Am Stat Assoc 46 (253): 68–78. https://doi.org/10.1080/01621459.1951.10500769. [Google Scholar]
Mathews, G, Towheed SS. 1995. NSSDC OMNIWeb: The first space physics WWW-based data browsing and retrieval system. Comput Netw ISDN Syst 27 (6): 801–808. Proceedings of the Third International World-Wide Web Conference. https://doi.org/10.1016/0169-7552(95)00033-4. [Google Scholar]
McComas, D, Bame S, Barker P, Feldman W, Phillips J, Riley P, Griffee J. 1998. Solar wind electron proton alpha monitor (SWEPAM) for the Advanced Composition Explorer. Space Sci Rev 86: 563–612. https://doi.org/10.1023/A:1005040232597. [CrossRef] [Google Scholar]
McKinney, W. 2010. Data Structures for Statistical Computing in Python. In: Proceedings of the 9th Python in Science Conference, S, van der Walt, Millman J (Eds.), pp. 56–61. https://doi.org/10.25080/Majora-92bf1922-00a. [Google Scholar]
Moreno-Torres, JG, Saez JA, Herrera F. 2012. Study on the impact of partition-induced dataset shift on k-fold cross-validation. IEEE Trans Neural Netw Learn Syst 23 (8): 1304–1312. https://doi.org/10.1109/TNNLS.2012.2199516. [Google Scholar]
Nwankwo, VUJ. 2018. Space weather: response of the atmosphere to solar activity and its implications for LEO satellites aerodynamic drag. In: Exploring the universe: from near space to extra-galactic, B, Mukhopadhyay, Sasmal S (Eds.), Springer International Publishing, Cham, pp. 637–644. ISBN 978-3-319-94607-8. https://doi.org/10.1007/978-3-319-94607-8_49. [Google Scholar]
Obi, JC, Jecinta IC. 2023. A review of techniques for regularization. Int J Res Eng Sci 11 (1): 360–367. [Google Scholar]
Oleksiienko, I, Tran DT, Iosifidis A. 2023. Variational neural networks Proc Comput Sci 222: 104–113. https://doi.org/1016/j.procs.2023.08.148. [Google Scholar]
Pesnell, WD, Thompson BJ, Chamberlin PC. 2012. The Solar Dynamics Observatory (SDO). Springer US, New York, NY, pp. 3–15. ISBN 978-1-4614-3673-7. https://doi.org/10.1007/978-1-4614-3673-7_2. [Google Scholar]
Petrini, L, Cagnetta F, Vanden-Eijnden E, Wyart M. 2022. Learning sparse features can lead to overfitting in neural networks. In: Advances in Neural Information Processing Systems, vol. 35, S, Koyejo, Mohamed S, Agarwal A, Belgrave D, Cho K, Oh ACurran Associates, Inc., 9403–9416. https://doi.org/10.1088/1742-5468/ad01b9. [Google Scholar]
Pomoell, J, Poedts S. 2018. EUHFORIA: European heliospheric forecasting information asset. J Space Weather Space Clim 8: A35. https://doi.org/10.1051/swsc/2018020. [CrossRef] [EDP Sciences] [Google Scholar]
Price-Whelan, AM, Sipőcz B, Günther H, Lim P, Crawford S, et al. 2018. The astropy project: Building an open-science project and status of the v2. 0 core package. Astron J 156 (3): 123. https://doi.org/10.3847/1538-3881/aabc4f. [CrossRef] [Google Scholar]
Rahaman, R, Thiery A. 2021. Uncertainty quantification and deep ensembles. In: Advances in Neural Information Processing Systems, vol. 34, M, Ranzato, Beygelzimer A, Dauphin Y, Liang P, Vaughan JW, Curran Associates, Inc., pp. 20063–20075. https://proceedings.neurips.cc/paper_files/paper/2021/file/a70dc40477bc2adceef4d2c90f47eb82-Paper.pdf. [Google Scholar]
Raju, H, Das S. 2021. CNN-based Deep Learning Model for Solar Wind Forecasting. Sol Phys 296 (9): 134. https://doi.org/10.1007/s11207-021-01874-6. [Google Scholar]
Ramaswamy, A. 2023. Gradient clipping in deep learning: a dynamical systems perspective. In: The 12th International Conference on Pattern Recognition Applications and Methods ICPRAM, Lisbon, Portugal, February 22–24, 2023, vol. 1, SciTePress, pp. 107–114. https://doi.org/10.5220/0011678000003411. [Google Scholar]
Reback, J, McKinney W, jbrockmendelden Bossche JV, Augspurger T, et al. 2020. pandas-dev/pandas: Pandas 1.0.0. https://doi.org/10.5281/zenodo.3630805. [Google Scholar]
Reddy, S, Reddy KT, ValliKumari V. 2018. Optimization of deep learning using various optimizers, loss functions and dropout. Int J Recent Technol Eng 7: 448–455. [Google Scholar]
Richardson, I, Cane H. 2010. Near-earth interplanetary coronal mass ejections during solar cycle 23 (1996–2009): catalog and summary of properties. Sol Phys 264 (1): 189–237. https://doi.org/10.1007/s11207-010-9568-6. [CrossRef] [Google Scholar]
Schou, J, Scherrer PH, Bush RI, Wachter R, Couvidat S, et al. 2012. Design and ground calibration of the Helioseismic and Magnetic Imager (HMI) instrument on the Solar Dynamics Observatory (SDO), Sol Phys 275 (1): 229–259. https://doi.org/10.1007/s11207-011-9842-2. [CrossRef] [Google Scholar]
Smith CW, Lheureux J, Ness NF, Acuña MH, Burlaga LF, Scheifele J. 1998. The ACE magnetic fields experiment. Space Sci Rev 86(1): 613–632. [CrossRef] [Google Scholar]
Stone, EC, Frandsen A, Mewaldt R, Christian E, Margolies D, Ormes J, Snow F. 1998. The advanced composition explorer, Space Sci Rev 86 (1): 1–22. https://doi.org/10.1023/A:1005082526237. [CrossRef] [Google Scholar]
The SunPy Community, Barnes WT, Bobra MG, Christe SD, Freij N, et al. 2020. The SunPy Project: Open Source Development and Status of the Version 1.0 Core Package. Astrophys J 890: 68. https://doi.org/10.3847/1538-4357/ab4f7a. [CrossRef] [Google Scholar]
Thompson, WT. 2006. Coordinate systems for solar image data. A&A , 449 (2): 791–803. https://doi.org/10.1051/0004-6361:20054262. [NASA ADS] [CrossRef] [EDP Sciences] [Google Scholar]
Upendran, V, Cheung MCM, Hanasoge S, Krishnamurthi G. 2020. Solar wind prediction using deep learning. Space Weather, 18 (9): e2020SW002,478. https://doi.org/10.1029/2020SW002478. [Google Scholar]
Valdenegro-Toro, M, Mori DS. 2022. A deeper look into aleatoric and epistemic uncertainty disentanglement. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1508–1516. [Google Scholar]
Verbanac, G, Vršnak B, Veronig A, Temmer M. 2011. Equatorial coronal holes, solar wind high-speed streams, and their geoeffectiveness. A&A, 526: A20. https://doi.org/10.1051/0004-6361/201014617. [NASA ADS] [CrossRef] [EDP Sciences] [Google Scholar]
Virtanen, P, Gommers R, Oliphant TE, Haberland M, Reddy T, et al. 2020. SciPy 1.0: Fundamental algorithms for scientific computing in Python. Nature Methods 17: 261–272. https://doi.org/10.1038/s41592-019-0686-2. [CrossRef] [PubMed] [Google Scholar]
Vybornov, FI, Sheiner OA. 2021. Coronal mass ejections and high-speed solar wind streams effect on HF ionospheric communication channel. J Phys Conf Ser 2131 (5): 052096. https://doi.org/10.1088/1742-6596/2131/5/052096. [Google Scholar]
Wilson, AG, Izmailov P. 2020. Bayesian deep learning and a probabilistic perspective of generalization. Adv Neural Inform Process Syst 33: 4697–4708. [Google Scholar]
Zaknich, A. 1998. Introduction to the modified probabilistic neural network for general signal processing applications. IEEE Trans Signal Process 46 (7): 1980–1990. https://doi.org/10.1109/78.700969. [Google Scholar]
Zhou, P, Shen L, Han Y, Mi L, Xu G. 2024. A short-term wind speed prediction method utilizing rolling decomposition and time-series extension to avoid information leakage. Energy Sources A Recovery Util Environ Eff 46 (1): 3338–3362. https://doi.org/10.1080/15567036.2024.2318485. [Google Scholar]
Zou, H, Hastie T. 2005. Regularization and variable selection via the elastic net. J R Stat Soc Series B Stat Methodol 67 (2): 301–320. https://doi.org/10.1111/j.1467-9868.2005.00503.x. [Google Scholar]

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.