no code implementations • 10 Dec 2023 • Naghmeh Shafiee Roudbari, Charalambos Poullis, Zachary Patterson, Ursula Eicker
Since water systems are interconnected and the connectivity information between the stations is implicit, the proposed model leverages a graph learning module to extract a sparse graph adjacency matrix adaptively based on the data.
1 code implementation • 8 Sep 2022 • Naghmeh Shafiee Roudbari, Zachary Patterson, Ursula Eicker, Charalambos Poullis
In recent years, graph neural networks (GNNs) combined with variants of recurrent neural networks (RNNs) have reached state-of-the-art performance in spatiotemporal forecasting tasks.