Development of a Deep Learning Emulator for a Distributed Groundwater–Surface Water Model: ParFlow-ML

Abstract

Integrated hydrologic models solve coupled mathematical equations that represent natural processes, including groundwater, unsaturated, and overland flow. However, these models are computationally expensive. It has been recently shown that machine leaning (ML) and deep learning (DL) in particular could be used to emulate complex physical processes in the earth system. In this study, we demonstrate how a DL model can emulate transient, three-dimensional integrated hydrologic model simulations at a fraction of the computational expense. This emulator is based on a DL model previously used for modeling video dynamics, PredRNN. The emulator is trained based on physical parameters used in the original model, inputs such as hydraulic conductivity and topography, and produces spatially distributed outputs (e.g., pressure head) from which quantities such as streamflow and water table depth can be calculated. Simulation results from the emulator and ParFlow agree well with average relative biases of 0.070, 0.092, and 0.032 for streamflow, water table depth, and total water storage, respectively. Moreover, the emulator is up to 42 times faster than ParFlow. Given this promising proof of concept, our results open the door to future applications of full hydrologic model emulation, particularly at larger scales.

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

“…In general, we see a good match between the hydrographs produced by the ML models and those produced by ParFlow. This finding is similar to results of another emulator study [22]. Visually, the CNN3D model has the best match to the simulated hydrographs, with the CNN2D_A1 and CNN2D models also exhibiting a good fit.…”

“…In Figure 2, we see that all models represent the basic spatial and temporal patterns simulated by ParFlow, with high pressures occurring along the central channel of the domain where water accumulates and flows to the exit. This behavior is similar in general to the results of prior flood mapping studies [21] and other emulator studies [22]. Visually, the CNN3D and CNN2D cases appear to have the closest average behavior to that simulated by ParFlow.…”

“…Still, studies that develop ML-emulator models are rare in hydrology and hydrogeology. Recent examples include use of models to augment time observational datasets for streamflow prediction [18], learning subsurface constitutive relationships in variably-saturated systems [19,20], flood forecasting [21], and recent emulators of 3D hydrologic models [22].…”

Recent advances and opportunities in data assimilation for physics-based hydrological modeling

“…These challenges suggest the need to develop new modeling approaches at continental and global scales that can properly simulate hydrological processes (especially lateral subsurface flows) at resolutions compatible with remote sensing data (i.e., resolutions used in the LSM/GHM community). To this end, machine learning and deep learning techniques are recently being explored to emulate complex subsurface physical processes (Radmanesh et al, 2020;Tran et al, 2021) and also to link modeled estimates with indirect measurements of the state variables (e.g., to link moisture states to radiances observations, Section Earth observations).…”

Geospatial Artificial Intelligence (GeoAI) in the Integrated Hydrological and Fluvial Systems Modeling: Review of Current Applications and Trends

“…ML application in hydrological predictions dates to the 1990s [16], but the development of the new GeoAI and ML algorithms, particularly the deep learning techniques, alongside new data collection technologies, has substantially increased in recent years [17,18]. Moreover, there are new studies on developing hybrid models (ML and physical-based models) [14,19,20] and physical process-guided ML methods [21][22][23][24]. Therefore, a review of the potential of the new GeoAI and ML methods for integrated hydrological and fluvial systems modeling is needed to guide scientists and practitioners to select the proper tools and to be aware of current and potential future methodologies.…”