{
  "created": "2022-04-28T22:18:24.544383+00:00", 
  "files": [
    {
      "bucket": "9a8986c3-8c6d-4e33-9ccc-43dff8a7bddf", 
      "checksum": "md5:f6e0abc3a3d8b141ebbdd4d7aa66569a", 
      "ePIC_PID": "http://hdl.handle.net/21.11125/6a3ff1a8-db40-4849-86ea-6cc71a044f4a", 
      "key": "coords.nc", 
      "size": 1261777, 
      "version_id": "62f04038-feb8-4d37-9654-21f19cc51d0e"
    }, 
    {
      "bucket": "9a8986c3-8c6d-4e33-9ccc-43dff8a7bddf", 
      "checksum": "md5:88293b0fbdfd3a3ffa88f396f4ef097b", 
      "ePIC_PID": "http://hdl.handle.net/21.11125/fa03790c-8018-4236-bfa4-0e2d0492e487", 
      "key": "kleinert_etal_2022_competitor_experiment_dirs.tar.gz", 
      "size": 809995968, 
      "version_id": "b3362511-6bd4-43bd-bb96-7b3dcf6fe993"
    }, 
    {
      "bucket": "9a8986c3-8c6d-4e33-9ccc-43dff8a7bddf", 
      "checksum": "md5:00fb86695fd0529819d82751bfe5cecf", 
      "ePIC_PID": "http://hdl.handle.net/21.11125/6d379394-8a0d-423a-8a0a-b434c9d5fca8", 
      "key": "kleinert_etal_2022_competitor_forecasts.tar.gz", 
      "size": 12219576, 
      "version_id": "81840fbc-fe15-4e09-9b9b-a1718e8b60cf"
    }, 
    {
      "bucket": "9a8986c3-8c6d-4e33-9ccc-43dff8a7bddf", 
      "checksum": "md5:f818a4d7e2a8d3edae3f875555dec3ea", 
      "ePIC_PID": "http://hdl.handle.net/21.11125/784f2e8e-2ef2-49a0-a806-872b69e6c967", 
      "key": "mlair-Kleinert_etal_2022_initial_submission.tar.gz", 
      "size": 5426164, 
      "version_id": "de667b3a-15a5-4ed3-aa22-7d6b38137f26"
    }
  ], 
  "id": "19c94b0b77374395b11cb54991cc497d", 
  "links": {
    "files": "https://b2share.fz-juelich.de/api/files/9a8986c3-8c6d-4e33-9ccc-43dff8a7bddf", 
    "self": "https://b2share.fz-juelich.de/api/records/19c94b0b77374395b11cb54991cc497d", 
    "versions": "https://b2share.fz-juelich.de/api/records/6b13b6a890f245c291feea982d11e6de/versions"
  }, 
  "metadata": {
    "$schema": "https://b2share.fz-juelich.de/api/communities/e9b9792e-79fb-4b07-b6b4-b9c2bd06d095/schemas/0#/json_schema", 
    "DOI": "https://doi.org/10.34730/19c94b0b77374395b11cb54991cc497d", 
    "community": "e9b9792e-79fb-4b07-b6b4-b9c2bd06d095", 
    "community_specific": {}, 
    "creators": [
      {
        "creator_name": "Kleinert, Felix"
      }, 
      {
        "creator_name": "Leufen, Lukas Hubert"
      }, 
      {
        "creator_name": "Lupascu, Aurelia"
      }, 
      {
        "creator_name": "Butler, Tim"
      }, 
      {
        "creator_name": "Schultz, Martin G."
      }
    ], 
    "descriptions": [
      {
        "description": "Here we provide the source code and required data sets to reproduce all results related to \"Representing chemical history in ozone time-series predictions - a model experiment study building on the MLAir (v1.5) deep learning framework\" by F. Kleinert, L. H. Leufen, A. Lupascu, T. Butler and M. G. Schultz, submitted to GMD(D) (gmd-2022-122).\n\nThis record contains the MLAir source code, reference (competitor) experiments and forecasts.\nAs we could not make the full 4D (400x360x35) hourly wrf-chem model fields available for technical reasons, we decided to upload the subdomain of interest only. WRF-Chem model fields (YYYY-MM) are available from:\n2009-01 to 2009-04: https://doi.org/10.34730/c799f04beb644e38a575fa20c2dd8d40\n2009-05 to 2009-08: https://doi.org/10.34730/d5f34ae6a8e34d4c8ac33f75b993e8a9\n2009-09 to 2009-12: https://doi.org/10.34730/a423ec9003194209989726a95a1a490c\n2010-01 to 2010-03: https://doi.org/10.34730/718262bd2c894fd6aadce19a08040f69\n\nThis record contains the MLAir (v1.5) python framework used to conduct the experiments (mlair.tar.gz). The version is also available from the projects gitlab repository (tag Kleinert_etal_2022_initial_submission): https://gitlab.jsc.fz-juelich.de/esde/machine-learning/mlair/-/tree/Kleinert_etal_2022_initial_submission\n\nAdditionally, this record contains the competitor experiment directories (trained neural networks, input & target data, etc.) and our competitor models' forecasts. After extraction, you can use this forecast path as an external parameter in `run_wrf_dh_sector3.py`. Thus, MLAir can use the reference forecasts to calculate skill scores etc. \n\nThe `coords.nc` file contains the time-independent coordinates related to the model fields linked above and can be linked to MLAir by specifying the absolut path within the `run_wrf_dh_sector3.py` runscript (external_coords_file=coords.nc).", 
        "description_type": "TechnicalInfo"
      }
    ], 
    "ePIC_PID": "http://hdl.handle.net/21.11125/4eeea6e7-4ca9-48d5-94fa-2eff38d38fab", 
    "license": {
      "license": "The MIT License (MIT)", 
      "license_uri": "http://opensource.org/licenses/mit-license.php"
    }, 
    "open_access": true, 
    "owners": [
      57
    ], 
    "publication_state": "published", 
    "titles": [
      {
        "title": "Representing chemical history in ozone time-series predictions - a model experiment study building on the MLAir (v1.5) deep learning framework: Experiments and source code"
      }
    ]
  }, 
  "updated": "2022-04-28T22:18:24.544388+00:00"
}