A Physics-Informed, Machine Learning Emulator of a 2D Surface Water Model: What Temporal Networks and Simulation-Based Inference Can Help Us Learn about Hydrologic Processes

A Physics-Informed, Machine Learning Emulator of a 2D Surface Water Model: What Temporal Networks and Simulation-Based Inference Can Help Us Learn about Hydrologic Processes
复制标题

DOI：
10.3390/w13243633
复制
发表时间：
2021-12
期刊：
Water
影响因子：
3.4
通讯作者：
R. Maxwell;L. Condon;Peter Melchior
R. Maxwell;L. Condon;Peter Melchior
中科院分区：
环境科学与生态学3区
文献类型：
--
作者：
R. Maxwell;L. Condon;Peter Melchior

文献摘要

被引文献

相似文献

虽然机器学习方法正在迅速应用于水文问题，但基于物理的方法仍然相对较少。许多成功的深度学习应用程序都专注于根据一段时间内的流量计观测训练的水流点估计。虽然这些方法在某些应用中显示出前景，但仍需要分布式方法来生成模型状态的准确二维结果，例如积水深度。在这里，我们演示了倾斜 V 流域基准问题的 2D 模拟器，以及集成水文模型 ParFlow 提供的解决方案。该仿真器模型可以使用 2D 卷积神经网络 (CNN)、3D CNN 和 U-Net 机器学习架构，并生成与时间相关的积水深度空间图，从中可以导出水文过程线和其他感兴趣的水文量。对不同深度学习架构和超参数进行了比较，特别关注 3D CNN（具有依赖时间的学习组件）和 2D CNN 和 U-Net 方法（仅使用当前模型状态来及时预测下一个状态）等方法。除了测试模型性能之外，我们还使用基于简化模拟的推理方法来评估将模拟器校准到随机选择的模拟的能力以及 ML 校准输入参数与底层基于物理的模拟之间的匹配。
While machine learning approaches are rapidly being applied to hydrologic problems, physics-informed approaches are still relatively rare. Many successful deep-learning applications have focused on point estimates of streamflow trained on stream gauge observations over time. While these approaches show promise for some applications, there is a need for distributed approaches that can produce accurate two-dimensional results of model states, such as ponded water depth. Here, we demonstrate a 2D emulator of the Tilted V catchment benchmark problem with solutions provided by the integrated hydrology model ParFlow. This emulator model can use 2D Convolution Neural Network (CNN), 3D CNN, and U-Net machine learning architectures and produces time-dependent spatial maps of ponded water depth from which hydrographs and other hydrologic quantities of interest may be derived. A comparison of different deep learning architectures and hyperparameters is presented with particular focus on approaches such as 3D CNN (that have a time-dependent learning component) and 2D CNN and U-Net approaches (that use only the current model state to predict the next state in time). In addition to testing model performance, we also use a simplified simulation based inference approach to evaluate the ability to calibrate the emulator to randomly selected simulations and the match between ML calibrated input parameters and underlying physics-based simulation.