Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data

<p>This data release provides all data and code used in Rahmani et al. (2020) to model stream temperature and assess results. Briefly, we used a subset of the USGS GAGES-II dataset as a test case for temperature prediction using deep learning methods. The associated manuscript explores the value of including stream discharge as a predictor in the temperature models, including the value of predicted discharge from a separate model when no discharge measurements are available.</p> <p>The data are organized into these items:</p> <ol> <li><a href="https://www.sciencebase.gov/catalog/item/5f908db182ce720ee2d0fef9">Spatial Information</a> - Locations of the 118 monitoring sites used in this study</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f986594d34e198cb77ff084">Observations</a> - Water temperature observations for the 118 sites used in this study</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865abd34e198cb77ff086">Model Inputs</a> - Model inputs, including basin attributes, weather drivers, and discharge</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865cfd34e198cb77ff088">Models</a> - Code and configurations for the stream temperature models</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865e5d34e198cb77ff08a">Model Predictions</a> - Predictions of stream water temperature</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865fbd34e198cb77ff08c">Model Evaluation</a> - Performance metrics for each stream temperature model</li> </ol> <p>This research was funded by the Integrated Water Prediction Program at the US Geological Survey.</p>