GenCast: Diffusion-based ensemble forecasting for medium-range weather

Weather forecasts are fundamentally uncertain, so predicting the range of probable weather scenarios is crucial for important decisions, from warning the public about hazardous weather, to planning renewable energy use. Here, we introduce GenCast, a probabilistic weather model with greater skill and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Price, Ilan, Sanchez-Gonzalez, Alvaro, Alet, Ferran, Andersson, Tom R, El-Kadi, Andrew, Masters, Dominic, Ewalds, Timo, Stott, Jacklynn, Mohamed, Shakir, Battaglia, Peter, Lam, Remi, Willson, Matthew
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Price, Ilan
Sanchez-Gonzalez, Alvaro
Alet, Ferran
Andersson, Tom R
El-Kadi, Andrew
Masters, Dominic
Ewalds, Timo
Stott, Jacklynn
Mohamed, Shakir
Battaglia, Peter
Lam, Remi
Willson, Matthew
description Weather forecasts are fundamentally uncertain, so predicting the range of probable weather scenarios is crucial for important decisions, from warning the public about hazardous weather, to planning renewable energy use. Here, we introduce GenCast, a probabilistic weather model with greater skill and speed than the top operational medium-range weather forecast in the world, the European Centre for Medium-Range Forecasts (ECMWF)'s ensemble forecast, ENS. Unlike traditional approaches, which are based on numerical weather prediction (NWP), GenCast is a machine learning weather prediction (MLWP) method, trained on decades of reanalysis data. GenCast generates an ensemble of stochastic 15-day global forecasts, at 12-hour steps and 0.25 degree latitude-longitude resolution, for over 80 surface and atmospheric variables, in 8 minutes. It has greater skill than ENS on 97.4% of 1320 targets we evaluated, and better predicts extreme weather, tropical cyclones, and wind power production. This work helps open the next chapter in operational weather forecasting, where critical weather-dependent decisions are made with greater accuracy and efficiency.
doi_str_mv 10.48550/arxiv.2312.15796
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2312_15796</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2312_15796</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-3b076966002ec337f8fb741d04b36bf199a4e3baae84e11758bb7b8d05ecb7163</originalsourceid><addsrcrecordid>eNotz71OwzAUBWAvDKjwAEz4BRzs-DdsKNCCVImle3Rvcl0sNS6yW37eHlqYzhmOjvQxdqNkY4K18g7KV_poWq3aRlnfuUu2XFHuoR7u-WOK8VjTPguEShOnXGnGHfG4LzT-TlLenjqfaUrHWRTIW-KfBIc3KlfsIsKu0vV_Lthm-bTpn8X6dfXSP6wFOO-ERuld55yULY1a-xgieqMmaVA7jKrrwJBGAAqGlPI2IHoMk7Q0oldOL9jt3-0ZMryXNEP5Hk6g4QzSP_xiRho</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>GenCast: Diffusion-based ensemble forecasting for medium-range weather</title><source>arXiv.org</source><creator>Price, Ilan ; Sanchez-Gonzalez, Alvaro ; Alet, Ferran ; Andersson, Tom R ; El-Kadi, Andrew ; Masters, Dominic ; Ewalds, Timo ; Stott, Jacklynn ; Mohamed, Shakir ; Battaglia, Peter ; Lam, Remi ; Willson, Matthew</creator><creatorcontrib>Price, Ilan ; Sanchez-Gonzalez, Alvaro ; Alet, Ferran ; Andersson, Tom R ; El-Kadi, Andrew ; Masters, Dominic ; Ewalds, Timo ; Stott, Jacklynn ; Mohamed, Shakir ; Battaglia, Peter ; Lam, Remi ; Willson, Matthew</creatorcontrib><description>Weather forecasts are fundamentally uncertain, so predicting the range of probable weather scenarios is crucial for important decisions, from warning the public about hazardous weather, to planning renewable energy use. Here, we introduce GenCast, a probabilistic weather model with greater skill and speed than the top operational medium-range weather forecast in the world, the European Centre for Medium-Range Forecasts (ECMWF)'s ensemble forecast, ENS. Unlike traditional approaches, which are based on numerical weather prediction (NWP), GenCast is a machine learning weather prediction (MLWP) method, trained on decades of reanalysis data. GenCast generates an ensemble of stochastic 15-day global forecasts, at 12-hour steps and 0.25 degree latitude-longitude resolution, for over 80 surface and atmospheric variables, in 8 minutes. It has greater skill than ENS on 97.4% of 1320 targets we evaluated, and better predicts extreme weather, tropical cyclones, and wind power production. This work helps open the next chapter in operational weather forecasting, where critical weather-dependent decisions are made with greater accuracy and efficiency.</description><identifier>DOI: 10.48550/arxiv.2312.15796</identifier><language>eng</language><subject>Computer Science - Learning ; Physics - Atmospheric and Oceanic Physics</subject><creationdate>2023-12</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,782,887</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2312.15796$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2312.15796$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Price, Ilan</creatorcontrib><creatorcontrib>Sanchez-Gonzalez, Alvaro</creatorcontrib><creatorcontrib>Alet, Ferran</creatorcontrib><creatorcontrib>Andersson, Tom R</creatorcontrib><creatorcontrib>El-Kadi, Andrew</creatorcontrib><creatorcontrib>Masters, Dominic</creatorcontrib><creatorcontrib>Ewalds, Timo</creatorcontrib><creatorcontrib>Stott, Jacklynn</creatorcontrib><creatorcontrib>Mohamed, Shakir</creatorcontrib><creatorcontrib>Battaglia, Peter</creatorcontrib><creatorcontrib>Lam, Remi</creatorcontrib><creatorcontrib>Willson, Matthew</creatorcontrib><title>GenCast: Diffusion-based ensemble forecasting for medium-range weather</title><description>Weather forecasts are fundamentally uncertain, so predicting the range of probable weather scenarios is crucial for important decisions, from warning the public about hazardous weather, to planning renewable energy use. Here, we introduce GenCast, a probabilistic weather model with greater skill and speed than the top operational medium-range weather forecast in the world, the European Centre for Medium-Range Forecasts (ECMWF)'s ensemble forecast, ENS. Unlike traditional approaches, which are based on numerical weather prediction (NWP), GenCast is a machine learning weather prediction (MLWP) method, trained on decades of reanalysis data. GenCast generates an ensemble of stochastic 15-day global forecasts, at 12-hour steps and 0.25 degree latitude-longitude resolution, for over 80 surface and atmospheric variables, in 8 minutes. It has greater skill than ENS on 97.4% of 1320 targets we evaluated, and better predicts extreme weather, tropical cyclones, and wind power production. This work helps open the next chapter in operational weather forecasting, where critical weather-dependent decisions are made with greater accuracy and efficiency.</description><subject>Computer Science - Learning</subject><subject>Physics - Atmospheric and Oceanic Physics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAUBWAvDKjwAEz4BRzs-DdsKNCCVImle3Rvcl0sNS6yW37eHlqYzhmOjvQxdqNkY4K18g7KV_poWq3aRlnfuUu2XFHuoR7u-WOK8VjTPguEShOnXGnGHfG4LzT-TlLenjqfaUrHWRTIW-KfBIc3KlfsIsKu0vV_Lthm-bTpn8X6dfXSP6wFOO-ERuld55yULY1a-xgieqMmaVA7jKrrwJBGAAqGlPI2IHoMk7Q0oldOL9jt3-0ZMryXNEP5Hk6g4QzSP_xiRho</recordid><startdate>20231225</startdate><enddate>20231225</enddate><creator>Price, Ilan</creator><creator>Sanchez-Gonzalez, Alvaro</creator><creator>Alet, Ferran</creator><creator>Andersson, Tom R</creator><creator>El-Kadi, Andrew</creator><creator>Masters, Dominic</creator><creator>Ewalds, Timo</creator><creator>Stott, Jacklynn</creator><creator>Mohamed, Shakir</creator><creator>Battaglia, Peter</creator><creator>Lam, Remi</creator><creator>Willson, Matthew</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20231225</creationdate><title>GenCast: Diffusion-based ensemble forecasting for medium-range weather</title><author>Price, Ilan ; Sanchez-Gonzalez, Alvaro ; Alet, Ferran ; Andersson, Tom R ; El-Kadi, Andrew ; Masters, Dominic ; Ewalds, Timo ; Stott, Jacklynn ; Mohamed, Shakir ; Battaglia, Peter ; Lam, Remi ; Willson, Matthew</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-3b076966002ec337f8fb741d04b36bf199a4e3baae84e11758bb7b8d05ecb7163</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><topic>Physics - Atmospheric and Oceanic Physics</topic><toplevel>online_resources</toplevel><creatorcontrib>Price, Ilan</creatorcontrib><creatorcontrib>Sanchez-Gonzalez, Alvaro</creatorcontrib><creatorcontrib>Alet, Ferran</creatorcontrib><creatorcontrib>Andersson, Tom R</creatorcontrib><creatorcontrib>El-Kadi, Andrew</creatorcontrib><creatorcontrib>Masters, Dominic</creatorcontrib><creatorcontrib>Ewalds, Timo</creatorcontrib><creatorcontrib>Stott, Jacklynn</creatorcontrib><creatorcontrib>Mohamed, Shakir</creatorcontrib><creatorcontrib>Battaglia, Peter</creatorcontrib><creatorcontrib>Lam, Remi</creatorcontrib><creatorcontrib>Willson, Matthew</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Price, Ilan</au><au>Sanchez-Gonzalez, Alvaro</au><au>Alet, Ferran</au><au>Andersson, Tom R</au><au>El-Kadi, Andrew</au><au>Masters, Dominic</au><au>Ewalds, Timo</au><au>Stott, Jacklynn</au><au>Mohamed, Shakir</au><au>Battaglia, Peter</au><au>Lam, Remi</au><au>Willson, Matthew</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>GenCast: Diffusion-based ensemble forecasting for medium-range weather</atitle><date>2023-12-25</date><risdate>2023</risdate><abstract>Weather forecasts are fundamentally uncertain, so predicting the range of probable weather scenarios is crucial for important decisions, from warning the public about hazardous weather, to planning renewable energy use. Here, we introduce GenCast, a probabilistic weather model with greater skill and speed than the top operational medium-range weather forecast in the world, the European Centre for Medium-Range Forecasts (ECMWF)'s ensemble forecast, ENS. Unlike traditional approaches, which are based on numerical weather prediction (NWP), GenCast is a machine learning weather prediction (MLWP) method, trained on decades of reanalysis data. GenCast generates an ensemble of stochastic 15-day global forecasts, at 12-hour steps and 0.25 degree latitude-longitude resolution, for over 80 surface and atmospheric variables, in 8 minutes. It has greater skill than ENS on 97.4% of 1320 targets we evaluated, and better predicts extreme weather, tropical cyclones, and wind power production. This work helps open the next chapter in operational weather forecasting, where critical weather-dependent decisions are made with greater accuracy and efficiency.</abstract><doi>10.48550/arxiv.2312.15796</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2312.15796
ispartof
issn
language eng
recordid cdi_arxiv_primary_2312_15796
source arXiv.org
subjects Computer Science - Learning
Physics - Atmospheric and Oceanic Physics
title GenCast: Diffusion-based ensemble forecasting for medium-range weather
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-11-29T17%3A28%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=GenCast:%20Diffusion-based%20ensemble%20forecasting%20for%20medium-range%20weather&rft.au=Price,%20Ilan&rft.date=2023-12-25&rft_id=info:doi/10.48550/arxiv.2312.15796&rft_dat=%3Carxiv_GOX%3E2312_15796%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true