College of Environmental Science and Engineering, Tongji University, 200092, Shanghai, China; Key Laboratory of Yangtze River Water Environment, Ministry of Education, Tongji University, 200092, Shanghai, China.
School of Energy and Environment, City University of Hong Kong, Hong Kong SAR, China.
Water Res. 2024 Oct 1;263:122142. doi: 10.1016/j.watres.2024.122142. Epub 2024 Jul 25.
Physics-based models are computationally time-consuming and infeasible for real-time scenarios of urban drainage networks, and a surrogate model is needed to accelerate the online predictive modelling. Fully-connected neural networks (NNs) are potential surrogate models, but may suffer from low interpretability and efficiency in fitting complex targets. Owing to the state-of-the-art modelling power of graph neural networks (GNNs) and their match with urban drainage networks in the graph structure, this work proposes a GNN-based surrogate of the flow routing model for the hydraulic prediction problem of drainage networks, which regards recent hydraulic states as initial conditions, and future runoff and control policy as boundary conditions. To incorporate hydraulic constraints and physical relationships into drainage modelling, physics-guided mechanisms are designed on top of the surrogate model to restrict the prediction variables with flow balance and flooding occurrence constraints. According to case results in a stormwater network, the GNN-based model is more cost-effective with better hydraulic prediction accuracy than the NN-based model after equal training epochs, and the designed mechanisms further limit prediction errors with interpretable domain knowledge. As the model structure adheres to the flow routing mechanisms and hydraulic constraints in urban drainage networks, it provides an interpretable and effective solution for data-driven surrogate modelling. Simultaneously, the surrogate model accelerates the predictive modelling of urban drainage networks for real-time use compared with the physics-based model.
基于物理的模型在计算上耗时且不适用于城市排水管网的实时场景，因此需要代理模型来加速在线预测建模。全连接神经网络 (NN) 是潜在的代理模型，但在拟合复杂目标时可能存在低可解释性和效率问题。由于图神经网络 (GNN) 的最新建模能力及其与城市排水管网在图结构上的匹配，这项工作提出了一种基于 GNN 的流量路由模型代理，用于解决排水管网的水力预测问题，该代理将最近的水力状态作为初始条件，将未来的径流和控制策略作为边界条件。为了将水力约束和物理关系纳入排水建模中，在代理模型之上设计了物理引导机制，利用流量平衡和洪水发生约束来限制预测变量。根据雨水管网的案例结果，在相同的训练周期后，基于 GNN 的模型比基于 NN 的模型具有更高的成本效益和更好的水力预测精度，并且所设计的机制利用可解释的领域知识进一步限制了预测误差。由于模型结构遵循城市排水管网中的流量路由机制和水力约束，因此为数据驱动的代理建模提供了一种可解释且有效的解决方案。同时，与基于物理的模型相比，代理模型加速了城市排水管网的预测建模，以实现实时使用。
