Show simple item record

dc.contributor.authorBrown, EJE
dc.contributor.authorSvoboda, F
dc.contributor.authorMeredith, NP
dc.contributor.authorLane, N
dc.contributor.authorHorne, RB
dc.date.accessioned2022-03-17T21:00:09Z
dc.date.available2022-03-17T21:00:09Z
dc.date.issued2022
dc.date.submitted2021-11-01
dc.identifier.issn1542-7390
dc.identifier.otherswe21271
dc.identifier.other2021sw002976
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/335135
dc.description.abstractAbstract: Extreme ultraviolet images taken by the Atmospheric Imaging Assembly on board the Solar Dynamics Observatory make it possible to use deep vision techniques to forecast solar wind speed—a difficult, high‐impact, and unsolved problem. At a 4 day time horizon, this study uses attention‐based models and a set of methodological improvements to deliver an 11.1% lower RMSE and a 17.4% higher prediction correlation compared to the previous work testing on the period from 2010 to 2018. Our analysis shows that attention‐based models combined with our pipeline consistently outperform convolutional alternatives. Our study shows a large performance improvement by using a 30 min as opposed to a daily sampling frequency. Our model has learned relationships between coronal holes' characteristics and the speed of their associated high‐speed streams, agreeing with empirical results. Our study finds a strong dependence of our best model on the phase of the solar cycle, with the best performance occurring in the declining phase.
dc.languageen
dc.publisherAmerican Geophysical Union (AGU)
dc.subjectHeliophysics and Space Weather Studies from the Sun‐Earth Lagrange Points
dc.subjectCOMPUTATIONAL GEOPHYSICS
dc.subjectNeural networks, fuzzy logic, machine learning
dc.subjectINFORMATICS
dc.subjectMachine learning
dc.subjectINTERPLANETARY PHYSICS
dc.subjectSolar wind sources
dc.subjectCoronal mass ejections
dc.subjectMAGNETOSPHERIC PHYSICS
dc.subjectMagnetic storms and substorms
dc.subjectNATURAL HAZARDS
dc.subjectSpace weather
dc.subjectSOLAR PHYSICS, ASTROPHYSICS, AND ASTRONOMY
dc.subjectSPACE WEATHER
dc.subjectModels
dc.subjectSolar effects
dc.subjectMagnetic storms
dc.subjectResearch Article
dc.subjectmachine learning
dc.subjectsolar wind speed
dc.subjectsolar images
dc.subjectcomputer vision
dc.subjectvision transformer
dc.subjectcoronal holes
dc.titleAttention-Based Machine Vision Models and Techniques for Solar Wind Speed Forecasting Using Solar EUV Images
dc.typeArticle
dc.date.updated2022-03-17T21:00:09Z
prism.issueIdentifier3
prism.publicationNameSpace Weather
prism.volume20
dc.identifier.doi10.17863/CAM.82567
dcterms.dateAccepted2022-01-27
rioxxterms.versionofrecord10.1029/2021SW002976
rioxxterms.versionAO
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by/4.0/
dc.contributor.orcidBrown, EJE [0000-0002-4719-9518]
dc.contributor.orcidMeredith, NP [0000-0001-5032-3463]
dc.contributor.orcidHorne, RB [0000-0002-0412-6407]
dc.identifier.eissn1542-7390
pubs.funder-project-idNatural Environment Research Council (NERC) (NE/V00249X/1, NE/R016038/1)
pubs.funder-project-idUKRI | Engineering and Physical Sciences Research Council (EPSRC) (EP/M50659X/1, EP/S001530/1)
cam.issuedOnline2022-03-17


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record