Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks
Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-8201-0282
Swedish Meteorological and Hydrological Institute.
University College London.
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0003-3749-5820
2024 (English)In: Advances in Neural Information Processing Systems: 38th Conference on Neural Information Processing Systems (NeurIPS 2024) / [ed] A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang, Neural Information Processing Systems, 2024, Vol. 37, p. 41577-41648Conference paper, Published paper (Refereed)
Abstract [en]

In recent years, machine learning has established itself as a powerful tool forhigh-resolution weather forecasting. While most current machine learning modelsfocus on deterministic forecasts, accurately capturing the uncertainty in thechaotic weather system calls for probabilistic modeling. We propose a probabilisticweather forecasting model called Graph-EFM, combining a flexible latent-variableformulation with the successful graph-based forecasting framework. The use of ahierarchical graph construction allows for efficient sampling of spatially coherentforecasts. Requiring only a single forward pass per time step, Graph-EFM allowsfor fast generation of arbitrarily large ensembles. We experiment with the modelon both global and limited area forecasting. Ensemble forecasts from Graph-EFMachieve equivalent or lower errors than comparable deterministic models, with theadded benefit of accurately capturing forecast uncertainty.

Place, publisher, year, edition, pages
Neural Information Processing Systems, 2024. Vol. 37, p. 41577-41648
Keywords [en]
weather forecasting, graph neural network, probabilistic, ensemble forecasting, latent variable model, earth system modeling
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:liu:diva-212805ISBN: 9798331314385 (electronic)OAI: oai:DiVA.org:liu-212805DiVA, id: diva2:1949847
Conference
38th Conference on Neural Information Processing Systems (NeurIPS 2024), 10-15 December 2024, Vancouver, Canada.
Available from: 2025-04-03 Created: 2025-04-03 Last updated: 2025-04-04Bibliographically approved

Open Access in DiVA

fulltext(39363 kB)87 downloads
File information
File name FULLTEXT01.pdfFile size 39363 kBChecksum SHA-512
8a69379d94a1760606ebeb2be5303bf54468dcda4be0f0135a0aa62f8081055434167694b70d892d349254987295d3c450d822cab081c6d4e4d37b3d99f00456
Type fulltextMimetype application/pdf

Other links

Förlagets fulltext / Publisher's full text

Search in DiVA

By author/editor
Oskarsson, JoelLindsten, Fredrik
By organisation
The Division of Statistics and Machine LearningFaculty of Science & EngineeringAutomatic Control
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 88 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 436 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf