PNNL

Abstract

Rivers and river habitats around the world are under sustained pressure from anthropogenic activities and the changing global environment. Our ability to quantify and manage the river states in a timely manner is critical for protecting the public safety and natural resources. Vector-based river network models have enabled modeling of large river basins at increasingly fine resolutions, but are computationally demanding. This work presents a novel physics-guided, graph neural network (GNNs) approach for basin-scale river network learning and stream forecasting. GNN models are pretrained using a high-resolution vector-based river network model, and then finetuned with in situ streamflow observations, after which a post-processing data fusion step is proposed to propagate residuals over the entire network to correct predictions. The GNN-based framework is demonstrated over a snowdominated watershed in the western U.S. consisting of 552 reaches. A series of experiments are performed to test training and imputation strategies. Results show the trained GNN model can effectively serve as a surrogate model of the process-based model with high accuracies (median Kling–Gupta efficiency>0.97). Application of the graphbased data fusion further reduces mismatch between the GNN model and observations, with as much as 50 percent KGE improvement over some cross-validation gages. Additionally we exploit and demonstrate a graph coarsening procedure that achieves comparable predicting skills at only a fraction of training cost, thus providing important insights for developing large-scale GNN-based river network models.