Heterogeneous stream-reservoir graph networks with data assimilation
January 5, 2021
Accurate prediction of water temperature in streams is critical for monitoring and understanding biogeochemical and ecological processes in streams. Stream temperature is affected by weather patterns (such as solar radiation) and water flowing through the stream network. Additionally, stream temperature can be substantially affected by water releases from man-made reservoirs to downstream segments. In this paper, we propose a heterogeneous recurrent graph model to represent these interacting processes that underlie stream-reservoir networks and improve the prediction of water temperature in all river segments within a network. Because reservoir release data may be unavailable for certain reservoirs, we further develop a data assimilation mechanism to adjust the deep learning model states to correct for the prediction bias caused by reservoir releases. Our evaluation for the Delaware River Basin has demonstrated the superiority of our proposed method over multiple existing methods. We have extensively studied the effect of the data assimilation mechanism under different scenarios.
Citation Information
Publication Year | 2021 |
---|---|
Title | Heterogeneous stream-reservoir graph networks with data assimilation |
DOI | 10.1109/ICDM51629.2021.00117 |
Authors | Shengyu Chen, Alison P. Appling, Samantha K. Oliver, Hayley Corson-Dosch, Jordan Read, Jeffrey Michael Sadler, Jacob Aaron Zwart, Xiaowei Jia |
Publication Type | Article |
Publication Subtype | Journal Article |
Series Title | IEEE International Conference on Data Mining (ICDM) |
Index ID | 70239241 |
Record Source | USGS Publications Warehouse |
USGS Organization | Wisconsin Water Science Center; WMA - Integrated Information Dissemination Division |
Related Content
Model predictions for heterogeneous stream-reservoir graph networks with data assimilation
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, a
Alison Appling, PhD
Data Scientist
Data Scientist
Email
Hayley Corson-Dosch
Hydrologist
Hydrologist
Email
Jordan S Read, PhD (Former Employee)
Chief, Data Science Branch
Chief, Data Science Branch
Jacob Zwart
Data Scientist
Data Scientist
Email
Related Content
Model predictions for heterogeneous stream-reservoir graph networks with data assimilation
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, a
Alison Appling, PhD
Data Scientist
Data Scientist
Email
Hayley Corson-Dosch
Hydrologist
Hydrologist
Email
Jordan S Read, PhD (Former Employee)
Chief, Data Science Branch
Chief, Data Science Branch
Jacob Zwart
Data Scientist
Data Scientist
Email