{"accessLevel": "public", "bureauCode": ["020:00"], "contactPoint": {"fn": "Jay Christensen", "hasEmail": "mailto:christensen.jay@epa.gov"}, "description": "Linked remote sensing and Long Short-Term Memory (LSTM) models reveal how surface water storage dynamics influence river discharge. This dataset is not publicly accessible because: It belongs to external collaborators. It can be accessed through the following means: The DOI for the final data release will be: (https://doi.org/10.5066/P14WYWSY). Format: The data will be housed at USGS's sciencebase.gov with an FGDC metadata .xml file as well as a csv file have been included along with model results for both remote sensing at the SWAT model subbasins. A link should be included on ScienceHub that will direct users to USGS's sciencebase. The DOI for the final data release will be: (https://doi.org/10.5066/P14WYWSY) ", "distribution": [], "identifier": "https://doi.org/10.23719/1532080", "keyword": ["LSTM machine learning", "remote sensing", "sentinel time-series", "surface water storage"], "license": "https://pasteur.epa.gov/license/sciencehub-license-non-epa-generated.html", "modified": "2025-03-11", "programCode": ["020:000"], "publisher": {"name": "U.S. EPA Office of Research and Development (ORD)", "subOrganizationOf": {"name": "U.S. Environmental Protection Agency", "subOrganizationOf": {"name": "U.S. Government"}}}, "references": null, "rights": null, "title": "Linked remote sensing and Long Short-Term Memory (LSTM) models reveal how surface water storage dynamics influence river discharge"}