Hydrodynamic flood models improve the hydrologic and hydraulic prediction of storm events. However, the computationally intensive numerical solutions required for 2D hydrodynamics have historically prevented their implementation in rapid modeling (such as flood forecasting or probabilistic modeling). This study examines whether several Deep Neural Network (DNN) architectures are suitable for optimizing flood models by solving the spatial discretizations of hydrodynamic models. Pluvial flooding events were simulated in a low-relief, high-resolution urban environment using HEC-RAS 2D. These simulations were assembled into a training set for four different DNN architectures (Feedforward DNN, Bayesian DNN, Physics-informed DNN, and LSTM). The architectures were then used to model the spatially-discretized hydrodynamics of two study areas. The DNNs were compared to the hydrodynamic flood models, and showed good capacity to simulate hydrodynamics, with a median RMSE of up to 2 mm for cell flooding depths after fine tuning. The DNNs also improved computation time significantly, being between 15.9 and 52.2 times faster than conventional hydrodynamic models. Notably, the DNNs were also up to an order of magnitude faster than a comparable GPU-optimized hydrodynamic model. Negligible differences in fitting capabilities were observed between HEC-RAS’ Full Momentum Equations and Diffusion Wave Equations once the networks were fine-tuned. Important numerical stability considerations were discovered that impact the selection of hydrodynamic formulation, DNN architecture, and forecast target. Overall, the results from this study show that DNNs can greatly optimize flood modeling, and enable rapid hydrodynamics.

中文翻译：

---

使用深度学习代理项进行快速 2D 水动力洪水建模


水动力洪水模型改进了风暴事件的水文和水力预测。然而，二维流体动力学所需的计算密集型数值解历来阻碍了它们在快速建模（例如洪水预报或概率建模）中的实现。本研究通过求解水动力模型的空间离散化，检查了几种深度神经网络 （DNN） 架构是否适合优化洪水模型。使用 HEC-RAS 2D 在低地势、高分辨率城市环境中模拟雨流洪水事件。这些模拟被组装成四种不同 DNN 架构（前馈 DNN、贝叶斯 DNN、物理信息 DNN 和 LSTM）的训练集。然后，这些架构用于模拟两个研究区域的空间离散流体动力学。将 DNN 与水动力洪水模型进行了比较，并显示出良好的模拟水动力的能力，微调后单元洪水深度的中位 RMSE 高达 2 mm。DNN 还显著缩短了计算时间，比传统流体动力学模型快 15.9 到 52.2 倍。值得注意的是，DNN 也比同类 GPU 优化的流体动力学模型快一个数量级。一旦对网络进行微调，在 HEC-RAS 的全动量方程和扩散波动方程之间观察到拟合能力的差异可以忽略不计。发现了影响流体动力学公式、DNN 结构和预测目标选择的重要数值稳定性考虑因素。总体而言，这项研究的结果表明，DNN 可以极大地优化洪水建模，并实现快速流体动力学。