{"success":true,"data":{"author":"Google DeepMind / Google Research (WeatherBench 2)","bucketAccessType":"public","bucketListable":true,"bucketName":"weatherbench2","bucketPrefix":"datasets/graphcast","category":"Climate & Weather","cloudProvider":"gcp","createdAt":"2026-11-14T14:15:25.567Z","description":"Deterministic medium-range global weather forecasts from GraphCast, the graph neural network weather model of Lam et al. (Science, 2023), as published in the WeatherBench 2 benchmark. Forecasts are initialised from ERA5 every 12 hours and run out to 10 days in 6-hour steps (40 lead times, 6 h to 240 h). The 2018 forecasts come from a model trained on data up to 2017 and the 2020 forecasts from a model trained up to 2019, so each year is an out-of-sample test. Measured 2026-11-14: the 2020 store spans initialisation times 2019-11-16 to 2021-01-31 (886 times) and the 2018 store 2017-11-16 to 2019-01-31 (884 times), on the native 0.25 degree 1440x721 grid with 37 pressure levels from 1 to 1000 hPa. Variables include geopotential, temperature, specific humidity, u and v wind, vertical velocity, 2 m temperature, 10 m wind, mean sea level pressure and 6-hour total precipitation. Each year also has regridded 240x121 and 64x32 conservative versions and a _derived store; the full-resolution 2020 store is roughly 33 TB uncompressed. Files are consolidated Zarr; open with xarray.open_zarr and score against ERA5 with the weatherbench2 package. Licensed CC BY 4.0 by Google LLC; cite Lam et al. 2023 and Rasp et al. 2024 (WeatherBench 2).","displayTitle":"WeatherBench 2 GraphCast Forecasts (ERA5-initialised, 2018 and 2020)","doi":"10.1126/science.adi2336","fuseMountBrowsable":true,"id":"3e1c3c0e-3831-5939-9429-0df6183327e5","license":"CC-BY-4.0","licenseEvidenceUrl":"https://storage.googleapis.com/weatherbench2/datasets/graphcast/LICENSE","objectCountEstimate":2,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1126/science.adi2336","region":"us","schemaCard":{"accessHints":[{"language":"python-gcsfs","snippet":"import gcsfs\nfs = gcsfs.GCSFileSystem(token='anon')\nfs.ls('weatherbench2/datasets/graphcast/', detail=False)[:10]"},{"language":"python-storage","snippet":"from google.cloud import storage\nclient = storage.Client.create_anonymous_client()\nlist(client.bucket('weatherbench2').list_blobs(prefix='datasets/graphcast/', max_results=10))"}],"caveats":["Files are binary — use a domain-specific parser rather than text I/O."],"format":"binary","generatedAt":"2026-11-14T14:15:29.679Z","layout":{"example":"datasets/graphcast/2018/date_range_2017-11-16_2019-02-01_12_hours-240x121_equiangular_with_poles_conservative.zarr/.zgroup","pattern":"{prefix}/{seg1}/{YYYY}/{seg3}/{filename}"},"mountPath":"/mnt/gcs-archive/data","sampleHeaders":[{"bytes":"{\n    \"zarr_format\": 2\n}","encoding":"utf8","key":"datasets/graphcast/2018/date_range_2017-11-16_2019-02-01_12_hours-240x121_equiangular_with_poles_conservative.zarr/.zgroup","truncatedAt":512},{"bytes":"{\n    \"metadata\": {\n        \".zgroup\": {\n            \"zarr_format\": 2\n        },\n        \"10m_u_component_of_wind/.zarray\": {\n            \"chunks\": [\n                1,\n                8,\n                240,\n                121\n            ],\n            \"compressor\": {\n                \"blocksize\": 0,\n                \"clevel\": 5,\n                \"cname\": \"lz4\",\n                \"id\": \"blosc\",\n                \"shuffle\": 1\n            },\n            \"dtype\": \"<f4\",\n            \"fill_value\": \"NaN\",\n           ","encoding":"utf8","key":"datasets/graphcast/2018/date_range_2017-11-16_2019-02-01_12_hours-240x121_equiangular_with_poles_conservative.zarr/.zmetadata","truncatedAt":512}],"sampleObjects":["datasets/graphcast/2018/date_range_2017-11-16_2019-02-01_12_hours-240x121_equiangular_with_poles_conservative.zarr/.zgroup","datasets/graphcast/2018/date_range_2017-11-16_2019-02-01_12_hours-240x121_equiangular_with_poles_conservative.zarr/.zmetadata","datasets/graphcast/2018/date_range_2017-11-16_2019-02-01_12_hours-240x121_equiangular_with_poles_conservative.zarr/10m_u_component_of_wind/.zarray","datasets/graphcast/2018/date_range_2017-11-16_2019-02-01_12_hours-240x121_equiangular_with_poles_conservative.zarr/10m_u_component_of_wind/.zattrs","datasets/graphcast/2018/date_range_2017-11-16_2019-02-01_12_hours-240x121_equiangular_with_poles_conservative.zarr/10m_u_component_of_wind/0.0.0.0"],"sidecars":[{"bytes":"Copyright 2024-2026 Google LLC.\n\nThese GraphCast forecast datasets are licensed under the Creative Commons\nAttribution 4.0 International (CC BY 4.0) license. You may obtain a copy of the\nLicense at: https://creativecommons.org/licenses/by/4.0/ (and included in full\nbelow).\n\nDisclaimers\n-----------\n\nThis is not an officially supported Google product.\n\nUnless required by applicable law or agreed to in writing, all materials\ndistributed here under the CC BY 4.0 license are distributed on an \"AS IS\"\nBASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\nSee the license for the specific language governing permissions and limitations\nunder the license.\n\nGraphCast is part of an experimental research project. You are solely\nresponsible for determining the appropriateness of using or distributing\nGraphCast or any outputs generated and assume all risks associated with your use\nor distribution of GraphCast and outputs and your exercise of rights and\npermissions granted by Google to you under the relevant License. Use discretion\nbefore relying on, publishing, downloading or otherwise using GraphCast or any\noutputs generated. GraphCast outputs have not been produced in collaboration\nwith nor endorsed by any government meteorological agency or department, and in\nno way replace official alerts, warnings or notices published by such agencies.\n\nCitations\n---------\n\nIf you use this work, consider citing our paper\n(https://www.science.org/doi/10.1126/science.adi2336):\n\n@article{lam2023learning,\n  title={Learning skillful medium-range global weather forecasting},\n  author={Lam, Remi and Sanchez-Gonzalez, Alvaro and Willson, Matthew and Wirnsberger, Peter and Fortunato, Meire and Alet, Ferran and Ravuri, Suman and Ewalds, Timo and Eaton-Rosen, Zach and Hu, Weihua and others},\n  journal={Science},\n  volume={382},\n  number={6677},\n  pages={1416--1421},\n  year={2023},\n  publisher={American Association for the Advancement of Science}\n}\n\nAcknowledgements\n----------------\n\nThese forecasts were generated using data and products of the European Centre\nfor Medium-Range Weather Forecasts (ECMWF), as modified by Google:\n\n* Modified Copernicus Climate Change Service information 2023. Neither the\n  European Commission nor ECMWF is responsible for any use that may be made of\n  the Copernicus information or data it contains.\n* ECMWF HRES datasets (where initialized from operational HRES data):\n  Copyright statement: Copyright \"© 2023 European Centre for Medium-Range\n  Weather Forecasts (ECMWF)\".\n  Source: www.ecmwf.int\n  License Statement: ECMWF open data is published under a Creative Commons\n  Attribution 4.0 International (CC BY 4.0).\n  https://creativecommons.org/licenses/by/4.0/\n  Disclaimer: ECMWF does not accept any liability whatsoever for any error or\n  omission in the data, their availability, or for any loss or damage arising\n  from their use.\n\nUse of the third-party materials referred to above may be governed by separate\nterms and conditions or license provisions. Your use of the third-party\nmaterials is subject to any such terms and you should check that you can comply\nwith any applicable restrictions or terms and conditions before use.\n\n=======================================================================\n\nAttribution 4.0 International\n\n=======================================================================\n\nCreative Commons Corporation (\"Creative Commons\") is not a law firm and\ndoes not provide legal services or legal advice. Distribution of\nCreative Commons public licenses does not create a lawyer-client or\nother relationship. Creative Commons makes its licenses and related\ninformation available on an \"as-is\" basis. Creative Commons gives no\nwarranties regarding its licenses, any material licensed under their\nterms and conditions, or any related information. Creative Commons\ndisclaims all liability for damages resulting from their use to the\nfullest extent possible.\n\nUsing Creative Commons Public Licenses\n\nCreative Commons public licenses provide a standard set of terms and\nconditions that creators and other right","encoding":"utf8","key":"datasets/graphcast/LICENSE","name":"LICENSE","size":21920,"truncated":true},{"bytes":"Copyright 2024-2026 Google LLC.\n\nThese GraphCast forecast datasets are licensed under the Creative Commons\nAttribution 4.0 International (CC BY 4.0) license. You may obtain a copy of the\nLicense at: https://creativecommons.org/licenses/by/4.0/ (and included in full\nbelow).\n\nDisclaimers\n-----------\n\nThis is not an officially supported Google product.\n\nUnless required by applicable law or agreed to in writing, all materials\ndistributed here under the CC BY 4.0 license are distributed on an \"AS IS\"\nBASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\nSee the license for the specific language governing permissions and limitations\nunder the license.\n\nGraphCast is part of an experimental research project. You are solely\nresponsible for determining the appropriateness of using or distributing\nGraphCast or any outputs generated and assume all risks associated with your use\nor distribution of GraphCast and outputs and your exercise of rights and\npermissions granted by Google to you under the relevant License. Use discretion\nbefore relying on, publishing, downloading or otherwise using GraphCast or any\noutputs generated. GraphCast outputs have not been produced in collaboration\nwith nor endorsed by any government meteorological agency or department, and in\nno way replace official alerts, warnings or notices published by such agencies.\n\nCitations\n---------\n\nIf you use this work, consider citing our paper\n(https://www.science.org/doi/10.1126/science.adi2336):\n\n@article{lam2023learning,\n  title={Learning skillful medium-range global weather forecasting},\n  author={Lam, Remi and Sanchez-Gonzalez, Alvaro and Willson, Matthew and Wirnsberger, Peter and Fortunato, Meire and Alet, Ferran and Ravuri, Suman and Ewalds, Timo and Eaton-Rosen, Zach and Hu, Weihua and others},\n  journal={Science},\n  volume={382},\n  number={6677},\n  pages={1416--1421},\n  year={2023},\n  publisher={American Association for the Advancement of Science}\n}\n\nAcknowledgements\n----------------\n\nThese forecasts were generated using data and products of the European Centre\nfor Medium-Range Weather Forecasts (ECMWF), as modified by Google:\n\n* Modified Copernicus Climate Change Service information 2023. Neither the\n  European Commission nor ECMWF is responsible for any use that may be made of\n  the Copernicus information or data it contains.\n* ECMWF HRES datasets (where initialized from operational HRES data):\n  Copyright statement: Copyright \"© 2023 European Centre for Medium-Range\n  Weather Forecasts (ECMWF)\".\n  Source: www.ecmwf.int\n  License Statement: ECMWF open data is published under a Creative Commons\n  Attribution 4.0 International (CC BY 4.0).\n  https://creativecommons.org/licenses/by/4.0/\n  Disclaimer: ECMWF does not accept any liability whatsoever for any error or\n  omission in the data, their availability, or for any loss or damage arising\n  from their use.\n\nUse of the third-party materials referred to above may be governed by separate\nterms and conditions or license provisions. Your use of the third-party\nmaterials is subject to any such terms and you should check that you can comply\nwith any applicable restrictions or terms and conditions before use.\n\n=======================================================================\n\nAttribution 4.0 International\n\n=======================================================================\n\nCreative Commons Corporation (\"Creative Commons\") is not a law firm and\ndoes not provide legal services or legal advice. Distribution of\nCreative Commons public licenses does not create a lawyer-client or\nother relationship. Creative Commons makes its licenses and related\ninformation available on an \"as-is\" basis. Creative Commons gives no\nwarranties regarding its licenses, any material licensed under their\nterms and conditions, or any related information. Creative Commons\ndisclaims all liability for damages resulting from their use to the\nfullest extent possible.\n\nUsing Creative Commons Public Licenses\n\nCreative Commons public licenses provide a standard set of terms and\nconditions that creators and other right","encoding":"utf8","key":"datasets/graphcast/2018/LICENSE","name":"LICENSE","size":21920,"truncated":true}],"sourceObjectKey":"datasets/graphcast/2018/date_range_2017-11-16_2019-02-01_12_hours-240x121_equiangular_with_poles_conservative.zarr/.zgroup","starterCell":"from google.cloud import storage\nclient = storage.Client.create_anonymous_client()\nbucket = client.bucket('weatherbench2')\nblob = bucket.blob('datasets/graphcast/2018/date_range_2017-11-16_2019-02-01_12_hours-240x121_equiangular_with_poles_conservative.zarr/.zgroup')\nwith blob.open(\"rb\") as fh:\n    print(fh.read(64))","starterSamplePath":"2018/date_range_2017-11-16_2019-02-01_12_hours-240x121_equiangular_with_poles_conservative.zarr","totalObjects":"2 top-level prefixes"},"summary":"Deterministic medium-range global weather forecasts from GraphCast, the graph neural network weather model of Lam et al.","title":"WeatherBench 2 GraphCast Forecasts (ERA5-initialised, 2018 and 2020)","updatedAt":"2026-11-14T17:46:51.805Z","visibility":"public","websiteUrl":"https://weatherbench2.readthedocs.io/en/latest/data-guide.html"}}