Next Article in Journal
A Lagrangian Backward Air Parcel Trajectories Clustering Framework
Previous Article in Journal
Future Climate Change Impact on the Nyabugogo Catchment Water Balance in Rwanda
Article

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

1
Department of Civil and Environmental Engineering, The High Meadows Environmental Institute and the Integrated GroundWater Modeling Center, Princeton University, Princeton, NJ 08544, USA
2
Department of Hydrology and Atmospheric Sciences, University of Arizona, Tucson, AZ 85721, USA
3
Department of Astrophysical Sciences and the Center for Statistics and Machine Learning, Princeton University, Princeton, NJ 08544, USA
*
Authors to whom correspondence should be addressed.
Academic Editor: Zheng Duan
Water 2021, 13(24), 3633; https://doi.org/10.3390/w13243633
Received: 22 November 2021 / Revised: 12 December 2021 / Accepted: 13 December 2021 / Published: 17 December 2021
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. View Full-Text
Keywords: hydrologic modeling; machine learning; model emulation; hydrologic runoff processes; simulation-based inference hydrologic modeling; machine learning; model emulation; hydrologic runoff processes; simulation-based inference
Show Figures

Figure 1

MDPI and ACS Style

Maxwell, R.M.; Condon, L.E.; Melchior, P. 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. Water 2021, 13, 3633. https://doi.org/10.3390/w13243633

AMA Style

Maxwell RM, Condon LE, Melchior P. 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. Water. 2021; 13(24):3633. https://doi.org/10.3390/w13243633

Chicago/Turabian Style

Maxwell, Reed M., Laura E. Condon, and Peter Melchior. 2021. "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" Water 13, no. 24: 3633. https://doi.org/10.3390/w13243633

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop