This data release provides the predictions from stream temperature models described in Chen et al. 2021. Briefly, various deep learning and process-guided deep learning models were built to test improved performance of stream temperature predictions below reservoirs in the Delaware River Basin. The spatial extent of predictions was restricted to streams above the Delaware River at Lordville, NY, and includes the West Branch of the Delaware River below Cannonsville Reservoir and the East Branch of the Delaware River below Pepacton Reservoir. Various model architectures, training schemes, and data assimilation methods were used to generate the table and figures in Chen et a.l (2021) and predictions of each model are captured in this release. For each model, there are test period predictions for 56 river reaches from 2006-10-01 through 2020-09-30. Model input and validation data can be found in Oliver et al. (2021). The publication associated with this data release is Chen, S., Appling, A.P., Oliver, S.K., Corson-Dosch, H.R., Read, J.S., Sadler, J.M., Zwart, J.A., Jia, X, 2021, Heterogeneous stream-reservoir graph networks with data assimilation. International Conference on Data Mining (ICDM). DOI: XX.
|Title||Model predictions for heterogeneous stream-reservoir graph networks with data assimilation|
|Authors||Shengyu Chen, Alison P Appling, Samantha K Oliver, Hayley R Corson-Dosch, Jordan S Read, Jeffrey M Sadler, Jacob A Zwart, Xiaowei Jia|
|Product Type||Data Release|
|Record Source||USGS Digital Object Identifier Catalog|
|USGS Organization||Integrated Information Dissemination Division|