@article{9db18b7451564097a4459b613cbe7848,
title = "Probabilistic Forecasts of Storm Sudden Commencements From Interplanetary Shocks Using Machine Learning",
abstract = "In this study we investigate the ability of several different machine learning models to provide probabilistic predictions as to whether interplanetary shocks observed upstream of the Earth at L1 will lead to immediate (Sudden Commencements, SCs) or longer lasting magnetospheric activity (Storm Sudden Commencements, SSCs). Four models are tested including linear (Logistic Regression), nonlinear (Naive Bayes and Gaussian Process), and ensemble (Random Forest) models and are shown to provide skillful and reliable forecasts of SCs with Brier Skill Scores (BSSs) of ∼0.3 and ROC scores >0.8. The most powerful predictive parameter is found to be the range in the interplanetary magnetic field. The models also produce skillful forecasts of SSCs, though with less reliability than was found for SCs. The BSSs and ROC scores returned are ∼0.21 and 0.82, respectively. The most important parameter for these predictions was found to be the minimum observed BZ. The simple parameterization of the shock was tested by including additional features related to magnetospheric indices and their changes during shock impact, resulting in moderate increases in reliability. Several parameters, such as velocity and density, may be able to be more accurately predicted at a longer lead time, for example, from heliospheric imagery. When the input was limited to the velocity and density the models were found to perform well at forecasting SSCs, though with lower reliability than previously (BSSs ∼ 0.16, ROC Scores ∼ 0.8), Finally, the models were tested with hypothetical extreme data beyond current observations, showing dramatically different extrapolations.",
keywords = "Sudden Commencement, forecast, interplanetary shock, machine leaning, space weather",
author = "Smith, {A. W.} and Rae, {I. J.} and C. Forsyth and Oliveira, {D. M.} and Freeman, {M. P.} and Jackson, {D. R.}",
note = "Funding Information: We acknowledge and thank the Wind and ACE teams for the solar wind data and NASA GSFC's Space Physics Data Facility's CDAWeb service for data availability ( https://cdaweb.gsfc.nasa.gov/index.html/ ). The results presented in the paper also rely on the SC list made available by the International Service on Rapid Magnetic Variations ( https://www.obsebre.es/en/rapid ) and published by the Observatorio de l'Ebre in association with the International Association of Geomagnetism and Aeronomy (IAGA) and the International Service of Geomagnetic Indices (ISGI). We thank the involved national institutes, the INTERMAGNET network and the ISGI. The authors would like to thank A. A. Samsonov for helpful discussions. This work has also used the interplanetary shock catalog compiled by Oliveira, Arel, et al. ( 2018 ), including those intervals identified Wang et al. ( 2010 ), and Dr. J. C. Kasper for the Wind ( https://www.cfa.harvard.edu/shocks/wi_data/ ) and ACE data ( https://www.cfa.harvard.edu/shocks/ac_master_data/ ), and also by the ACE team ( https://www‐ssg.sr.unh.edu/mag/ace/ACElists/obs_list.html#shocks ). It may be found in the supporting information of Oliveira, Arel, et al. ( 2018 ). A. W. S. and I. J. R. were supported by STFC Consolidated Grant ST/S000240/1 and NERC grants NE/P017150/1 and NE/V002724/1. C. F. was supported by the NERC Independent Research Fellowship NE/N014480/1 and STFC Consolidated Grant ST/S000240/1. D. M. O. was supported by NASA through grant HISFM18‐HIF (Heliophysics Innovation Fund). The analysis in this paper was performed using python, including the pandas (McKinney, 2010 ), numpy (van der Walt et al., 2011 ), scikit‐learn (Pedregosa et al., 2011 ), scipy (Virtanen et al., 2020 ) and matplotlib (Hunter, 2007 ) libraries. Detailed documentation for the models can be found at https://scikit‐learn.org/ , while the specific implementations of the models used in this work are: sklearn.linear_model.LogisticRegression, sklearn.naive_bayes.GaussianNB, sklearn.gaussian_process.GaussianProcessClassifier, sklearn.ensemble.RandomForestClassifier.",
year = "2020",
month = nov,
day = "1",
doi = "10.1029/2020SW002603",
language = "English",
volume = "18",
journal = "Space Weather",
issn = "1542-7390",
publisher = "American Geophysical Union",
number = "11",
}