Show simple item record

dc.contributor.authorChakraborty, Shibajien
dc.contributor.authorMorley, Steven Karlen
dc.date.accessioned2020-11-04T16:21:36Zen
dc.date.available2020-11-04T16:21:36Zen
dc.date.issued2020-07-30en
dc.identifier.issn2115-7251en
dc.identifier.other36en
dc.identifier.urihttp://hdl.handle.net/10919/100786en
dc.description.abstractGeomagnetic activity is often described using summary indices to summarize the likelihood of space weather impacts, as well as when parameterizing space weather models. The geomagnetic indexK(p)in particular, is widely used for these purposes. Current state-of-the-art forecast models provide deterministicK(p)predictions using a variety of methods - including empirically-derived functions, physics-based models, and neural networks - but do not provide uncertainty estimates associated with the forecast. This paper provides a sample methodology to generate a 3-hour-aheadK(p)prediction with uncertainty bounds and from this provide a probabilistic geomagnetic storm forecast. Specifically, we have used a two-layered architecture to separately predict storm (K-p >= 5(-)) and non-storm cases. As solar wind-driven models are limited in their ability to predict the onset of transient-driven activity we also introduce a model variant using solar X-ray flux to assess whether simple models including proxies for solar activity can improve the predictions of geomagnetic storm activity with lead times longer than the L1-to-Earth propagation time. By comparing the performance of these models we show that including operationally-available information about solar irradiance enhances the ability of predictive models to capture the onset of geomagnetic storms and that this can be achieved while also enabling probabilistic forecasts.en
dc.description.sponsorshipSpace Science and Applications group; Center for Space and Earth Science (CSES) at Los Alamos National Laboratory; US Department of EnergyUnited States Department of Energy (DOE); Laboratory Directed Research and Development (LDRD) program [20190262ER]en
dc.format.mimetypeapplication/pdfen
dc.language.isoenen
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectgeomagnetic stormsen
dc.subjectK(p)forecastingen
dc.subjectdeep learningen
dc.subjectLSTMen
dc.subjectGaussian processen
dc.titleProbabilistic prediction of geomagnetic storms and the Kp indexen
dc.typeArticle - Refereeden
dc.contributor.departmentElectrical and Computer Engineeringen
dc.description.notesSC thanks to the Space Science and Applications group and the Center for Space and Earth Science (CSES) at Los Alamos National Laboratory for organizing and supporting the Los Alamos Space Weather Summer School. Portions of this work by SKM were performed under the auspices of the US Department of Energy and were partially supported by the Laboratory Directed Research and Development (LDRD) program, award number 20190262ER. The authors wish to acknowledge the use of the OMNI solar wind data, available at https://omniweb.gsfc.nasa.gov/ow.html. The Kp index and GOES X-ray datasets were accessed through the GFZ-Potsdam website https://www.gfz-potsdam.de/en/kpindex/ and NOAA FTP server https://satdat.ngdc.noaa.gov/sem/goes/data/, respectively. The majority of analysis and visualization was completed with the help of free, open-source software tools, notably: Keras (Chollet, 2015); matplotlib (Hunter, 2007); IPython (Perez & Granger, 2007); pandas (McKinney, 2010); Spacepy (Morley et al., 2011); PyForecast-Tools (Morley, 2018); and others (see, e.g., Millman & Aivazis, 2011). The code developed during this work is available at https://github.com/shibaji7/Codebase_Kp_Prediction. The editor thanks two anonymous reviewers for their assistance in evaluating this paper.en
dc.title.serialJournal of Space Weather and Space Climateen
dc.identifier.doihttps://doi.org/10.1051/swsc/2020037en
dc.identifier.volume10en
dc.type.dcmitypeTexten


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Creative Commons Attribution 4.0 International
License: Creative Commons Attribution 4.0 International