Deep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins
January 4, 2023
This data release provides all data and code used in Rahmani et al. (2021b) to model stream temperature and assess results. Briefly, we modeled stream temperature at sites across the continental United States using deep learning methods. The associated manuscript explores the prediction challenges posed by reservoirs, the value of additional training sites when predicting in gaged vs ungaged sites, and the value of an ensemble of attribute subsets in improving prediction accuracy. The data are organized into these child items: Site Information - Attributes and spatial information about the monitoring sites and basins in this study Observations - Water temperature observations for the sites used in this study Model Inputs - Model input, including meteorological drivers and discharge Model Code - Model code, instructions, and configurations for running the stream temperature models Model Predictions - Predictions of stream water temperature This research was funded by the Integrated Water Prediction Program at the US Geological Survey. The publication associated with this data release is Rahmani, F., Shen, C., Oliver, S.K., Lawson, K., and Appling, A.P., 2021, Deep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins. Hydrologic Processes. DOI: XX.
Citation Information
Publication Year | 2023 |
---|---|
Title | Deep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins |
DOI | 10.5066/P9VHMO56 |
Authors | Farshid Rahmani, Chaopeng Shen, Samantha K Oliver, Kathryn Lawson, Alison P Appling |
Product Type | Data Release |
Record Source | USGS Asset Identifier Service (AIS) |
USGS Organization | Water Resources Mission Area - Headquarters |
Rights | This work is marked with CC0 1.0 Universal |
Related
Deep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins
Basin-centric long short-term memory (LSTM) network models have recently been shown to be an exceptionally powerful tool for stream temperature (Ts) temporal prediction (training in one period and predicting in another period at the same sites). However, spatial extrapolation is a well-known challenge to modelling Ts and it is uncertain how an LSTM-based daily Ts model will perform in...
Authors
Farshid Rahmani, Chaopeng Shen, Samantha K. Oliver, Kathryn Lawson, Alison P. Appling
Related
Deep learning approaches for improving prediction of daily stream temperature in data-scarce, unmonitored, and dammed basins
Basin-centric long short-term memory (LSTM) network models have recently been shown to be an exceptionally powerful tool for stream temperature (Ts) temporal prediction (training in one period and predicting in another period at the same sites). However, spatial extrapolation is a well-known challenge to modelling Ts and it is uncertain how an LSTM-based daily Ts model will perform in...
Authors
Farshid Rahmani, Chaopeng Shen, Samantha K. Oliver, Kathryn Lawson, Alison P. Appling