{"url":"/dataset/climateset","name":"ClimateSet","full_name":"ClimateSet - : A Large-Scale Climate Model Dataset for Machine Learning","description_markdown":"Climate models are critical tools for analyzing climate change and projecting its future impact. The machine learning (ML) community has taken an increased interest in supporting climate scientists’ efforts on various tasks such as climate model emulation, downscaling, and prediction tasks. However, traditional datasets based on single climate models are limiting. We thus present ClimateSet — a comprehensive collection of inputs and outputs from 36 climate models sourced from the Input4MIPs and CMIP6 archives, designed for large-scale ML applications.","description_withheld":null,"homepage":"https://climateset.github.io/","introduced_date":"2023-11-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/climateset-a-large-scale-climate-model","title":"ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning","first_author":null,"url":null},"license":{"name":"CC BY 4.0 Deed","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"3D","url":"/datasets/modality/3d"},{"name":"Time series","url":"/datasets/modality/time-series"}],"tasks":[],"languages":[],"variants":["ClimateSet"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}