Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data: 5 Model predictions

<p>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.</p>

Data and Resources

Field Value
accessLevel public
bureauCode {010:12}
catalog_@context https://project-open-data.cio.gov/v1.1/schema/catalog.jsonld
catalog_conformsTo https://project-open-data.cio.gov/v1.1/schema
catalog_describedBy https://project-open-data.cio.gov/v1.1/schema/catalog.json
datagov_dedupe_retained 20220722134805
identifier USGS:5f9865e5d34e198cb77ff08a
metadata_type geospatial
modified 20201209
old-spatial {"type": "Polygon", "coordinates": [[[-123.32988684, 30.1454932], [-123.32988684, 48.90595739], [ -70.97964444, 48.90595739], [ -70.97964444, 30.1454932], [-123.32988684, 30.1454932]]]}
publisher U.S. Geological Survey
publisher_hierarchy Department of the Interior > U.S. Geological Survey
resource-type Dataset
source_datajson_identifier true
source_hash be39032037d90c7c9be321f4225c2a771e92e5d7
source_schema_version 1.1
spatial {"type": "Polygon", "coordinates": [[[-123.32988684, 30.1454932], [-123.32988684, 48.90595739], [ -70.97964444, 48.90595739], [ -70.97964444, 30.1454932], [-123.32988684, 30.1454932]]]}
theme {geospatial}
Groups
  • AmeriGEOSS
  • National Provider
  • North America
Tags
  • al
  • alabama
  • amerigeo
  • amerigeoss
  • ckan
  • de
  • deep-learning
  • delaware
  • environment
  • ga
  • geo
  • georgia
  • geoss
  • ia
  • id
  • idaho
  • inlandwaters
  • iowa
  • kansas
  • ks
  • ma
  • machine-learning
  • maine
  • maryland
  • massachusetts
  • md
  • me
  • mi
  • michigan
  • mississippi
  • modeling
  • ms
  • national
  • nc
  • nevada
  • new-jersey
  • new-mexico
  • new-york
  • nj
  • nm
  • north-america
  • north-carolina
  • nv
  • ny
  • oh
  • ohio
  • ok
  • oklahoma
  • or
  • oregon
  • pa
  • pennsylvania
  • rhode-island
  • ri
  • sc
  • south-carolina
  • streams
  • tennessee
  • texas
  • tn
  • tx
  • united-states
  • us
  • usgs-5f9865e5d34e198cb77ff08a
  • ut
  • utah
  • va
  • virginia
  • wa
  • washington
  • water-resources
  • water-temperature
  • west-virginia
  • wi
  • wisconsin
  • wv
  • wy
  • wyoming
isopen False
license_id notspecified
license_title License not specified
maintainer Farshid Rahmani
maintainer_email fzr5082@psu.edu
metadata_created 2025-11-21T01:28:10.621137
metadata_modified 2025-11-21T01:28:10.621141
notes &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;
num_resources 2
num_tags 78
title Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data: 5 Model predictions