{"success":true,"data":{"author":"LEAP NSF Science and Technology Center, Columbia University, and ClimSim consortium","bucketAccessType":"public","bucketName":"LEAP/ClimSim_low-res","bucketPrefix":"","category":"Climate & Weather","cloudProvider":"huggingface","createdAt":"2026-11-14T14:15:16.072Z","description":"ClimSim, from the LEAP NSF Science and Technology Center and partners, is the largest dataset built for hybrid ML-physics climate emulation: input and output vectors from the multi-scale climate model E3SM-MMF that isolate how embedded high-resolution cloud-resolving physics changes the host model's macro-scale state, so neural networks can learn to replace the expensive subgrid physics. Data were saved every 20 minutes for 10 simulated years as paired netCDF files, E3SM-MMF.mli.* (inputs) and E3SM-MMF.mlo.* (targets), with scalar and vertically resolved variables on ncol and lev. This is the low-resolution real-geography configuration: 11.5 x 11.5 degree grid (384 grid columns), which the documentation counts as 100 million samples and 744 GB (about 1.9 MB per input and 1.1 MB per output file), the usual starting point for ClimSim baselines. The listing (measured 2026-11-14) shows train/ with 96 monthly subfolders (0001-02 onward) and ClimSim_low-res_grid-info.nc; the repository uses about 796 GB. Open with xarray or netCDF4, or use the climsim_utils preprocessing to build subsampled NumPy training sets. Data are released under CC-BY-4.0 (code Apache-2.0); cite arXiv:2306.08754.","displayTitle":"ClimSim Low-Resolution Real Geography (E3SM-MMF, 11.5 degree)","id":"c71825cf-9750-5012-88c5-dd9fef8c244d","license":"CC-BY-4.0","licenseEvidenceUrl":"https://github.com/leap-stc/ClimSim","objectCountEstimate":100000,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2306.08754","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"LEAP/ClimSim_low-res\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"LEAP/ClimSim_low-res\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=LEAP, license:cc-by-4.0, downloads=7453"],"format":"mixed","generatedAt":"2026-11-14T14:15:21.889Z","layout":{"example":"ClimSim_low-res_grid-info.nc","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"ClimSim_low-res_grid-info.nc","truncatedAt":512}],"sampleObjects":["ClimSim_low-res_grid-info.nc","train/0001-02/E3SM-MMF.mli.0001-02-01-00000.nc","train/0001-02/E3SM-MMF.mli.0001-02-01-01200.nc","train/0001-02/E3SM-MMF.mli.0001-02-01-02400.nc","train/0001-02/E3SM-MMF.mli.0001-02-01-03600.nc"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\n---\n\nCorresponding GitHub repo can be found here:\n\nhttps://github.com/leap-stc/ClimSim\n\nRead more: https://arxiv.org/abs/2306.08754.","encoding":"utf8","key":"README.md","name":"README.md","size":155,"truncated":false}],"sourceObjectKey":"ClimSim_low-res_grid-info.nc","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"LEAP/ClimSim_low-res\", filename=\"ClimSim_low-res_grid-info.nc\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"ClimSim_low-res_grid-info.nc","totalObjects":100000},"summary":"ClimSim, from the LEAP NSF Science and Technology Center and partners, is the largest dataset built for hybrid ML-physics climate emulation: input and output vectors from the…","title":"ClimSim Low-Resolution Real Geography (E3SM-MMF, 11.5 degree)","updatedAt":"2026-11-14T17:29:17.969Z","visibility":"public","websiteUrl":"https://leap-stc.github.io/ClimSim/"}}