Adjoint-Matching Neural Network Surrogates for Fast 4D-Var Data Assimilation

dc.contributor.authorChennault, Austinen
dc.contributor.authorPopov, Andrey A.en
dc.contributor.authorSubrahmanya, Amit N.en
dc.contributor.authorCooper, Rachelen
dc.contributor.authorKarpatne, Anujen
dc.contributor.authorSandu, Adrianen
dc.date.accessioned2022-02-27T04:03:07Zen
dc.date.available2022-02-27T04:03:07Zen
dc.date.issued2021-11-16en
dc.date.updated2022-02-27T04:03:07Zen
dc.description.abstractThe data assimilation procedures used in many operational numerical weather forecasting systems are based around variants of the 4D-Var algorithm. The cost of solving the 4D-Var problem is dominated by the cost of forward and adjoint evaluations of the physical model. This motivates their substitution by fast, approximate surrogate models. Neural networks offer a promising approach for the data-driven creation of surrogate models. The accuracy of the surrogate 4D-Var problem’s solution has been shown to depend explicitly on accurate modeling of the forward and adjoint for other surrogate modeling approaches and in the general nonlinear setting. We formulate and analyze several approaches to incorporating derivative information into the construction of neural network surrogates. The resulting networks are tested on out of training set data and in a sequential data assimilation setting on the Lorenz-63 system. Two methods demonstrate superior performance when compared with a surrogate network trained without adjoint information, showing the benefit of incorporating adjoint information into the training process.en
dc.format.mimetypeapplication/pdfen
dc.identifier.orcidSandu, Adrian [0000-0002-5380-0103]en
dc.identifier.urihttp://hdl.handle.net/10919/108892en
dc.language.isoenen
dc.relation.urihttp://arxiv.org/abs/2111.08626v1en
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectcs.LGen
dc.subjectcs.CEen
dc.subjectcs.NAen
dc.subjectmath.NAen
dc.subjectmath.OCen
dc.titleAdjoint-Matching Neural Network Surrogates for Fast 4D-Var Data Assimilationen
dc.typeArticleen
dc.type.dcmitypeTexten
pubs.organisational-group/Virginia Techen
pubs.organisational-group/Virginia Tech/Engineeringen
pubs.organisational-group/Virginia Tech/Engineering/Computer Scienceen
pubs.organisational-group/Virginia Tech/All T&R Facultyen
pubs.organisational-group/Virginia Tech/Engineering/COE T&R Facultyen
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
2111.08626v1.pdf
Size:
624.01 KB
Format:
Adobe Portable Document Format