Transferable surrogate models based on inductive biases of graph neural networks for water distribution systems

Water utilities tackle various problems in planning and operating their systems with complex and computationally expensive hydraulic models, i.e., maximizing system resilience, fault isolation, risk assessment, optimal pump scheduling, or water loss reduction via pressure management. To meet limited computational budgets, engineers employ less resource-intensive surrogate models. Current surrogate models based on artificial neural networks deliver similar accuracies as hydraulic models with lower computational costs. However, they require retraining when applied to an unknown water distribution system, which increases their computational load and limits their general applicability. Recent advancements in graph-based machine learning address these limitations. Graph neural networks (GNNs) naturally connect with the network elements (e.g., pipes and valves with edges, junctions, and tanks with vertices)  of water distribution systems, proving themselves to be a promising candidate for surrogate modeling. Once trained on a specific network to be a surrogate model, GNNs possess inductive biases that allow transferability to an unseen topology. In this work, we adopted a demand-driven simulation of a water distribution system in a graph machine learning setting. We built a synthetic dataset of demand-driven simulation with EPANET, founded on the example of real-world water distribution systems, and trained an attention-based GNN to emulate the hydraulic simulator. The accuracy was evaluated inductively on an unseen larger-sized water distribution network. We observed that the model showed promising transferability results to a larger network without the need for additional re-training on the unseen topology.