{"accessLevel": "public", "bureauCode": ["010:12"], "contactPoint": {"@type": "vcard:Contact", "fn": "Farshid Rahmani", "hasEmail": "mailto:fzr5082@psu.edu"}, "description": "&lt;p&gt;This data release component contains water temperature predictions in 118 river catchments across the U.S. Predictions are from the four models described by Rahmani et al. (2020): locally-fitted linear regression, LSTM-noQ, LSTM-obsQ, and LSTM-simQ.&lt;/p&gt;", "distribution": [{"@type": "dcat:Distribution", "description": "The metadata original format", "downloadURL": "https://data.usgs.gov/datacatalog/metadata/USGS.5f9865e5d34e198cb77ff08a.xml", "format": "XML", "mediaType": "text/xml", "title": "Original Metadata"}, {"@type": "dcat:Distribution", "accessURL": "https://doi.org/10.5066/P97CGHZH", "description": "Landing page for access to the data", "format": "XML", "mediaType": "application/http", "title": "Digital Data"}], "identifier": "http://datainventory.doi.gov/id/dataset/USGS_5f9865e5d34e198cb77ff08a", "keyword": ["inlandWaters", "Michigan", "United States", "NJ", "NM", "Utah", "Texas", "NV", "VA", "AL", "Delaware", "Iowa", "North Carolina", "Nevada", "NC", "USGS:5f9865e5d34e198cb77ff08a", "RI", "Rhode Island", "New Mexico", "GA", "OK", "environment", "WV", "Washington", "OR", "WY", "Oregon", "Maryland", "Virginia", "KS", "NY", "Kansas", "WA", "Wyoming", "New York", "SC", "modeling", "New Jersey", "WI", "OH", "TN", "South Carolina", "DE", "Mississippi", "Idaho", "Pennsylvania", "West Virginia", "TX", "deep learning", "Ohio", "Tennessee", "water temperature", "PA", "Wisconsin", "Massachusetts", "ID", "Maine", "MI", "UT", "US", "Oklahoma", "water resources", "MS", "machine learning", "streams", "Alabama", "MA", "MD", "Georgia", "IA", "ME"], "modified": "2020-12-09T00:00:00Z", "publisher": {"@type": "org:Organization", "name": "U.S. Geological Survey"}, "spatial": "-123.32988684, 30.1454932, -70.97964444, 48.90595739", "theme": ["geospatial"], "title": "Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data: 5 Model predictions"}