{"success":true,"data":{"author":"Aman Gupta et al., NASA-IBM Prithvi WxC team","bucketAccessType":"public","bucketName":"ibm-nasa-geospatial/gravity-wave-parameterization","bucketPrefix":"","category":"Climate & Weather","cloudProvider":"huggingface","createdAt":"2026-11-14T01:01:18.772Z","description":"Input and output training pairs for learning a nonlocal parameterization of atmospheric gravity waves, computed from ECMWF ERA5 reanalysis and used to fine-tune the Prithvi WxC weather and climate foundation model. The publishers computed the pairs for 2010, 2012, 2014 and 2015; this repository provides one month from the validation set for testing. Data are on a 64 latitude by 128 longitude grid at hourly steps. The input has 491 channels: latitude, longitude, surface elevation, and zonal wind u, meridional wind v, temperature T and pressure P on 122 vertical levels each. The output has 366 channels: potential temperature theta and the zonal and meridional fluxes of vertical momentum (u'omega' and v'omega') on 122 levels. Listing the repository (measured 2026-11-13) shows a single 20.9 GB netCDF file (wxc_input_u_v_t_p_output_theta_uw_vw_era5_training_data_hourly_2015_constant_mu_sigma_scaling05.nc) whose attributes record the scaling recipe per variable. Open it with xarray or netCDF4 (ncdump -h shows the attributes). ERA5 is CC-BY-4.0 and that licence governs this derived data; credit the Copernicus Climate Change Service (C3S) and ECMWF.","displayTitle":"Nonlocal Gravity Wave Parameterization Training Data from ERA5","id":"08dfbd11-e192-5562-aa9d-84229964dde7","license":"CC-BY-4.0","licenseEvidenceUrl":"https://forum.ecmwf.int/t/cc-by-licence-to-replace-licence-to-use-copernicus-products-on-02-july-2025/13464","objectCountEstimate":4,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2409.13598","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"ibm-nasa-geospatial/gravity-wave-parameterization\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"ibm-nasa-geospatial/gravity-wave-parameterization\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=ibm-nasa-geospatial, license:apache-2.0, downloads=149"],"format":"mixed","generatedAt":"2026-11-14T01:01:24.686Z","layout":{"example":"prithvi_schematic.png","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"prithvi_schematic.png","truncatedAt":512}],"sampleObjects":["prithvi_schematic.png","wxc_input_u_v_t_p_output_theta_uw_vw_era5_training_data_hourly_2015_constant_mu_sigma_scaling05.nc"],"sidecars":[{"bytes":"---\nlicense: apache-2.0\n---\n\n<h1>Data format description for the nonlocal gravity wave parameterization dataset</h1>\n\n<h1>Data Source</h1>\n\nThe dataset contains input and output training pairs computed using ECMWF's ERA5. The dataset was computed for the years 2010, 2012, 2014, and 2015. One month (from the validation set) is provided here for testing. \n\n<h1>Variables Description</h1>\n\n1. Dimensional variables: 64 latitudes (LAT) and 128 longitudes (LON)\n2. features: background atmospheric state, fixed surface variables lat, lon, surface elevation and \\\\(u, v, T, P\\\\), concatenated along the vertical dimension. \n3. output: potential temperature \\\\(\\theta \\\\) and momentum fluxes, \\\\(u'\\omega',v'\\omega'\\\\), concatenated along the vertical dimension.\n\n<h1>Variables Shape</h1>\n1. Input shape: TIME x IDIM x LAT x LON<br />\n2. Output shape: TIME x ODIM x LAT x LON<br />\n\nHere, IDIM = 491, ODIM = 366, LAT=64, LON=128, TIME index ranges from 0 to 24*31 for months wth 31 days\n\n<center>\n<img src=\"https://huggingface.co/datasets/Prithvi-WxC/Gravity_wave_Parameterization/resolve/main/prithvi_schematic.png\" alt=\"Gravity Wave\" width=\"60%\"/>\n</center>\n\n<h1>Variables Indices</h1>\n\n<b>Input:</b> has IDIM=491 (3 + 4x122) channels. It is created by concatenating the latitude (1), longitude (1), surface elevation (1), zonal winds \\\\(u\\\\) (122), meridional winds \\\\(v\\\\) (122), temperature \\\\(T\\\\) (122), and pressure \\\\(P\\\\) (122), along the vertical dimension. IDIM index 0 corresponds to latitude, 1 corresponds to longitude, 2 corresponds to surface elevation for the given latitude and longitude, 3 to 124 correspond to zonal wind, and so on.\n\n<b>Output:</b> has ODIM=366 (3x122) channels. It is created by concatenating the potential temperature \\\\(\\theta\\\\) (122), zonal flux of vertical momentum \\\\(u'\\omega'\\\\) (122) and the meridional flux of vertical momentum \\\\(v'\\omega'\\\\) (122) along the vertical dimension. ODIM 0 to 121 correspond to the potential temperature, and so on. \n\n<h1>File Attributes</h1>\nThe netCDF attributes describe the scaling recipe for each variable. To view, execute: ncdump -h (filename)\n<br /><br />\n<h1>Contact</h1>\n<a href=\"https://github.com/amangupta2\" target=\"_blank\">https://github.com/amangupta2</a> or <a href=\"\"mailto:webmaster@example.com\">amangupta2@gmail.com</a>","encoding":"utf8","key":"README.md","name":"README.md","size":2312,"truncated":false}],"sourceObjectKey":"prithvi_schematic.png","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"ibm-nasa-geospatial/gravity-wave-parameterization\", filename=\"prithvi_schematic.png\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"prithvi_schematic.png","totalObjects":4},"summary":"Input and output training pairs for learning a nonlocal parameterization of atmospheric gravity waves, computed from ECMWF ERA5 reanalysis and used to fine-tune the Prithvi WxC…","title":"Nonlocal Gravity Wave Parameterization Training Data from ERA5","updatedAt":"2026-11-14T02:53:18.779Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/ibm-nasa-geospatial/gravity-wave-parameterization"}}