Deep learning foundation models are revolutionizing many facets of science by leveraging vast amounts of data to learn general-purpose representations that can be adapted to tackle diverse downstream tasks. Foundation models hold the promise to also transform our ability to model our planet and its subsystems by exploiting the vast expanse of Earth system data. Here we introduce Aurora, a large-scale foundation model of the atmosphere trained on over a million hours of diverse weather and climate data. Aurora leverages the strengths of the foundation modelling approach to produce operational forecasts for a wide variety of atmospheric prediction problems, including those with limited training data, heterogeneous variables, and extreme events. In under a minute, Aurora produces 5-day global air pollution predictions and 10-day high-resolution weather forecasts that outperform state-of-the-art classical simulation tools and the best specialized deep learning models. Taken together, these results indicate that foundation models can transform environmental forecasting.<\/p>\n","protected":false},"excerpt":{"rendered":"
Deep learning foundation models are revolutionizing many facets of science by leveraging vast amounts of data to learn general-purpose representations that can be adapted to tackle diverse downstream tasks. Foundation models hold the promise to also transform our ability to model our planet and its subsystems by exploiting the vast expanse of Earth system data. […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[193718],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[268251,246685],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[264846],"msr-pillar":[],"class_list":["post-1039116","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-field-of-study-atmospheric-and-oceanic-physics","msr-field-of-study-machine-learning"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2024-5-20","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"MSR-TR-2024-16","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"Microsoft Research AI for Science","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/2405.13063","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":1039119,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2024\/05\/Aurora__A_Foundation_Model_of_the_Atmosphere.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Cristian Bodnar","user_id":42696,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Cristian Bodnar"},{"type":"user_nicename","value":"Wessel Bruinsma","user_id":42339,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Wessel Bruinsma"},{"type":"user_nicename","value":"Ana Lucic","user_id":42480,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ana Lucic"},{"type":"user_nicename","value":"Megan Stanley","user_id":41482,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Megan Stanley"},{"type":"user_nicename","value":"Johannes Brandstetter","user_id":41874,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Johannes Brandstetter"},{"type":"guest","value":"patrick-garvan","user_id":686985,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=patrick-garvan"},{"type":"text","value":"Maik Riechert","user_id":0,"rest_url":false},{"type":"text","value":"Jonathan Weyn","user_id":0,"rest_url":false},{"type":"text","value":"Haiyu Dong","user_id":0,"rest_url":false},{"type":"text","value":"Anna Vaughan","user_id":0,"rest_url":false},{"type":"text","value":"Jayesh Gupta","user_id":0,"rest_url":false},{"type":"text","value":"Kit Thambiratnam","user_id":0,"rest_url":false},{"type":"text","value":"Alex Archibald","user_id":0,"rest_url":false},{"type":"text","value":"Elizabeth Heider","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Max Welling","user_id":41155,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Max Welling"},{"type":"user_nicename","value":"Richard Turner","user_id":42687,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Richard Turner"},{"type":"user_nicename","value":"Paris Perdikaris","user_id":43110,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Paris Perdikaris"}],"msr_impact_theme":["Computing foundations"],"msr_research_lab":[851467],"msr_event":[],"msr_group":[],"msr_project":[1045410],"publication":[],"video":[],"download":[],"msr_publication_type":"techreport","related_content":{"projects":[{"ID":1045410,"post_title":"Aurora Forecasting","post_name":"aurora-forecasting","post_type":"msr-project","post_date":"2024-08-15 01:11:31","post_modified":"2024-09-26 07:38:16","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/aurora-forecasting\/","post_excerpt":"A flexible 3D foundation model of the atmosphere. Aurora, developed by a team of Microsoft researchers, is a cutting-edge AI foundation model that can extract valuable insights from vast amounts of atmospheric data. This 1.3 billion parameter model excels at a wide range of prediction tasks, even in data-sparse regions or extreme weather scenarios. Aurora is a large-scale deep learning model that can predict global weather patterns and atmospheric processes like air pollution. It is…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1045410"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1039116"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":5,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1039116\/revisions"}],"predecessor-version":[{"id":1042149,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1039116\/revisions\/1042149"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1039116"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=1039116"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1039116"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1039116"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1039116"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=1039116"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1039116"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=1039116"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=1039116"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1039116"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1039116"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1039116"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1039116"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1039116"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1039116"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1039116"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}