{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/weatherbench-2-a-benchmark-for-the-next","title":"WeatherBench 2: A benchmark for the next generation of data-driven global weather models","arxiv_id":"2308.15560","date":"2023-08-29","proceeding":null,"authors":["Stephan Rasp","Stephan Hoyer","Alexander Merose","Ian Langmore","Peter Battaglia","Tyler Russel","Alvaro Sanchez-Gonzalez","Vivian Yang","Rob Carver","Shreya Agrawal","Matthew Chantry","Zied Ben Bouallegue","Peter Dueben","Carla Bromberg","Jared Sisk","Luke Barrington","Aaron Bell","Fei Sha"],"abstract":"WeatherBench 2 is an update to the global, medium-range (1-14 day) weather forecasting benchmark proposed by Rasp et al. (2020), designed with the aim to accelerate progress in data-driven weather modeling. WeatherBench 2 consists of an open-source evaluation framework, publicly available training, ground truth and baseline data as well as a continuously updated website with the latest metrics and state-of-the-art models: https://sites.research.google/weatherbench. This paper describes the design principles of the evaluation framework and presents results for current state-of-the-art physical and data-driven weather models. The metrics are based on established practices for evaluating weather forecasts at leading operational weather centers. We define a set of headline scores to provide an overview of model performance. In addition, we also discuss caveats in the current evaluation setup and challenges for the future of data-driven weather forecasting.","url_abs":"https://arxiv.org/abs/2308.15560v2","url_pdf":"https://arxiv.org/pdf/2308.15560v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"weatherbench-2-a-benchmark-for-the-next","repo_url":"https://github.com/google-research/weatherbench2","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"weather-forecasting","task_name":"Weather Forecasting"}],"methods":[],"datasets_introduced":[{"slug":"weatherbench-2","name":"WeatherBench 2","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2308.15560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.15560"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/weatherbench2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7a1ca4763589d70b","entry":"DEFINE_chunks","repo":"google-research/weatherbench2","repo_kind":"official","path":"weatherbench2/flag_utils.py","file_url":"https://github.com/google-research/weatherbench2/blob/HEAD/weatherbench2/flag_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a1ca4763589d70b"}},{"code_sha256_prefix":"1a236503ef0c4869","entry":"DEFINE_dim_value_pairs","repo":"google-research/weatherbench2","repo_kind":"official","path":"weatherbench2/flag_utils.py","file_url":"https://github.com/google-research/weatherbench2/blob/HEAD/weatherbench2/flag_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1a236503ef0c4869"}},{"code_sha256_prefix":"a259e9a2b43c1f76","entry":"get_dim_value","repo":"google-research/weatherbench2","repo_kind":"official","path":"weatherbench2/flag_utils.py","file_url":"https://github.com/google-research/weatherbench2/blob/HEAD/weatherbench2/flag_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a259e9a2b43c1f76"}},{"code_sha256_prefix":"38a27a508df079aa","entry":"latitude_values","repo":"google-research/weatherbench2","repo_kind":"official","path":"weatherbench2/regridding.py","file_url":"https://github.com/google-research/weatherbench2/blob/HEAD/weatherbench2/regridding.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"38a27a508df079aa"}},{"code_sha256_prefix":"96f0a349a094f84e","entry":"longitude_values","repo":"google-research/weatherbench2","repo_kind":"official","path":"weatherbench2/regridding.py","file_url":"https://github.com/google-research/weatherbench2/blob/HEAD/weatherbench2/regridding.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"96f0a349a094f84e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}