Physics-guided recurrent graph model for predicting flow and temperature in river networks
August 23, 2021
This paper proposes a physics-guided machine learning approach that combines machine learning models and physics-based models to improve the prediction of water flow and temperature in river networks. We first build a recurrent graph network model to capture the interactions among multiple segments in the river network. Then we transfer knowledge from physics-based models to guide the learning of the machine learning model. We also propose a new loss function that balances the performance over different river segments. We demonstrate the effectiveness of the proposed method in predicting temperature and streamflow in a subset of the Delaware River Basin. In particular, the proposed method has brought a 33%/14% accuracy improvement over the state-of-the-art physics-based model and 24%/14% over traditional machine learning models (e.g., LSTM) in temperature/streamflow prediction using very sparse (0.1%) training data. The proposed method has also been shown to produce better performance when generalized to different seasons or river segments with different streamflow ranges.
Citation Information
Publication Year | 2021 |
---|---|
Title | Physics-guided recurrent graph model for predicting flow and temperature in river networks |
DOI | 10.1137/1.9781611976700.69 |
Authors | Xiaowei Jia, Jacob Aaron Zwart, Jeffrey Michael Sadler, Alison P. Appling, Samantha K. Oliver, Steven L. Markstrom, Jared Willard, Shaoming Xu, Michael Steinbach, Jordan Read, Vipin Kumar |
Publication Type | Conference Paper |
Publication Subtype | Conference Paper |
Index ID | 70247905 |
Record Source | USGS Publications Warehouse |
USGS Organization | WMA - Integrated Information Dissemination Division |
Related
Jacob Zwart, PhD
Senior Data Scientist
Senior Data Scientist
Email
Jordan S Read, PhD (Former Employee)
Chief, Data Science Branch
Chief, Data Science Branch
Related
Jacob Zwart, PhD
Senior Data Scientist
Senior Data Scientist
Email
Jordan S Read, PhD (Former Employee)
Chief, Data Science Branch
Chief, Data Science Branch