Physics-Guided Recurrent Graph Model for Predicting Flow and Temperature in River Networks

Jia, Xiaowei; Zwart, Jacob A.; Sadler, Jeffrey M.; Appling, Alison P.; Oliver, Samantha; Markstrom, Steven L.; Willard, Jared; Xu, Shaoming; Steinbach, Michael; Read, Jordan S.; Kumar, Vipin

doi:10.1137/1.9781611976700.69

Cited by 58 publications

(62 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, our framework and models were developed for forecasting at the watershed level, and we neglected the geographical distribution of rainfall. Several simulation experiments involving graph neural networks have been conducted (Jia et al, 2021;Xiang et al, 2022), and that could be addressed in future studies. We recommended updating the deep learning model continuously with the most recent data in our framework as a potential improvement step for prediction.…”

Section: Discussionmentioning

confidence: 99%

Real-Time Streamflow Forecasting Framework, Implementation and Post-Analysis Using Deep Learning

Xiang¹,

Demir²

2022

Preprint

View full text Add to dashboard Cite

Rainfall-runoff modeling and streamflow prediction using deep learning algorithms have been studied significantly in the last few years. The majority of these studies focus on the simulation and testing of historical datasets. Deployment and operation of a real-time streamflow forecast model using deep learning will face additional data and computational challenges such as inaccurate rainfall forecast data and real-time data assimilation with limited studies guiding on these difficulties. We proposed a real-time streamflow forecast framework that includes pre-event model training using deep learning, real-time data acquisition, and post-event analysis. We implemented the framework for 124 USGS gauged watersheds across Iowa to forecast 120-hour streamflow rates since April 2021. This is the first time deep learning models have been used to predict streamflow in real-time operational settings at a large scale, and we anticipate seeing more real-time implementations of deep learning models in the future.

show abstract

Section: Discussionmentioning

confidence: 99%

Real-Time Streamflow Forecasting Framework, Implementation and Post-Analysis Using Deep Learning

Xiang¹,

Demir²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…These advances have enhanced the capability to model interacting processes in complex physical systems, which commonly requires substantial efforts in calibration in traditional physics-based modeling approaches. Graph neural networks have also shown potential for the modeling of water temperature and streamflow in river networks [4,3]. Despite the accuracy improvement brought by these methods, they are mostly evaluated in stream regions without reservoirs.…”

Section: Related Workmentioning

confidence: 99%

“…Prior works have shown the potential for combining physical simulations with machine learning models. For example, simulated data can be used to pre-train deep learning models [15,16,17,18] and add supervision to intermediate hidden variables [19,4]. These studies have shown improved model accuracy and generalizability using limited observed samples.…”

Section: Related Workmentioning

confidence: 99%

“…We conduct experiments to answer three questions: Q1: Can the proposed SAG model with the PP approach outperform existing methods when the reservoir release data is not accessible for any reservoirs? We test the performance of the SAG model with the PP embedding approach (SAG-pp) in S 1 , and compare it with multiple baselines, including standard fully connected artificial neural networks (ANN), recurrent neural networks (RNN) with the LSTM cell, and recurrent graph neural networks (RGrN) [4]. All of these baselines do not consider the reservoir release information.…”

Section: Evaluation Detailsmentioning

confidence: 99%

“…Prior work has used global data-driven models [3,4] to simulate water temperature dynamics in the entire stream network given variations in climate drivers (e.g., solar radiation, precipitation, and air temperature), catchment characteristics, and the influence of the stream network topology. However, these approaches are not designed for capturing the impact of reservoirs, which brings stochasticity to the relationship between input climate drivers and observed water temperature, and makes it difficult to capture such relationship.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Modeling Reservoir Release Using Pseudo-Prospective Learning and Physical Simulations to Predict Water Temperature

Jia¹,

Chen²,

Xie³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper proposes a new data-driven method for predicting water temperature in stream networks with reservoirs. The water flows released from reservoirs greatly affect the water temperature of downstream river segments. However, the information of released water flow is often not available for many reservoirs, which makes it difficult for data-driven models to capture the impact to downstream river segments. In this paper, we first build a state-aware graph model to represent the interactions amongst streams and reservoirs, and then propose a parallel learning structure to extract the reservoir release information and use it to improve the prediction. In particular, for reservoirs with no available release information, we mimic the water managers' release decision process through a pseudo-prospective learning method, which infers the release information from anticipated water temperature dynamics. For reservoirs with the release information, we leverage a physics-based model to simulate the water release temperature and transfer such information to guide the learning process for other reservoirs. The evaluation for the Delaware River Basin shows that the proposed method brings over 10% accuracy improvement over existing data-driven models for stream temperature prediction when the release data is not available for any reservoirs. The performance is further improved after we incorporate the release data and physical simulations for a subset of reservoirs.

show abstract

Hybrid Modeling of Evapotranspiration: Inferring Stomatal and Aerodynamic Resistances Using Combined Physics-Based and Machine Learning

ElGhawi

Kraft

Reimers

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Physics-Guided Recurrent Graph Model for Predicting Flow and Temperature in River Networks

Cited by 58 publications

References 20 publications

Real-Time Streamflow Forecasting Framework, Implementation and Post-Analysis Using Deep Learning

Real-Time Streamflow Forecasting Framework, Implementation and Post-Analysis Using Deep Learning

Modeling Reservoir Release Using Pseudo-Prospective Learning and Physical Simulations to Predict Water Temperature

Hybrid Modeling of Evapotranspiration: Inferring Stomatal and Aerodynamic Resistances Using Combined Physics-Based and Machine Learning

Contact Info

Product

Resources

About