Differentiable, Learnable, Regionalized Process‐Based Models With Multiphysical Outputs can Approach State‐Of‐The‐Art Hydrologic Prediction Accuracy. Issue 10 (20th October 2022)

• Record Type: Journal Article
• Authors: Feng, Dapeng; Liu, Jiangtao; Lawson, Kathryn; Shen, Chaopeng
• Is Part Of: Water resources research. Volume 58:Issue 10(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-10-20
• Subjects: rainfall runoff -- differentiable programming -- machine learning -- physical model -- differentiable hydrology -- LSTM; Hydrology -- Periodicals; 333.91
• DOI: 10.1029/2022WR032404
• Languages: English
• ISSNs: 0043-1397

Abstract

Abstract: Predictions of hydrologic variables across the entire water cycle have significant value for water resources management as well as downstream applications such as ecosystem and water quality modeling. Recently, purely data‐driven deep learning models like long short‐term memory (LSTM) showed seemingly insurmountable performance in modeling rainfall runoff and other geoscientific variables, yet they cannot predict untrained physical variables and remain challenging to interpret. Here, we show that differentiable, learnable, process‐based models (called δ models here) can approach the performance level of LSTM for the intensively observed variable (streamflow) with regionalized parameterization. We use a simple hydrologic model HBV as the backbone and use embedded neural networks, which can only be trained in a differentiable programming framework, to parameterize, enhance, or replace the process‐based model's modules. Without using an ensemble or post‐processor, δ models can obtain a median Nash‐Sutcliffe efficiency of 0.732 for 671 basins across the USA for the Daymet forcing data set, compared to 0.748 from a state‐of‐the‐art LSTM model with the same setup. For another forcing data set, the difference is even smaller: 0.715 versus 0.722. Meanwhile, the resulting learnable process‐based models can output a full set of untrained variables, for example, soil and groundwater storage, snowpack, evapotranspiration, and baseflow, and can later be constrained by their observations. Both simulated evapotranspiration and fraction of discharge from baseflow agreed decently with alternative estimates. The general framework can work with models with various process complexity and opens up the path for learning physics from big data. Plain Language Summary: Recently, deep neural networks like long short‐term memory (LSTM) have received a lot of attention for producing high‐accuracy simulations in hydrology, but they do not respect physical laws and remain difficult to understand. However, what if you can have a model with similar accuracy, but with clarity about physical processes? What if at the same time the model respects physical laws like mass conservation and produces interpretable outputs (like soil moisture, groundwater storage, evapotranspiration and baseflow), with which you can tell a whole story to stakeholders? What if the same framework allows you to ask precise questions about different parts of hydrology and re‐examine your understanding of some parts of the physical system or check if your past equations are correct? This paper delivers a system that achieves these grand goals and opens many avenues for further exploration. Key Points: Differentiable ( δ ) hydrologic models show that process clarity and a performance approaching deep learning (DL) can be both attained Unlike DL, δ models can output untrained physical variables, which agreed well with alternative estimates Dynamic parameterization has a moderate impact but is needed to narrow the gap to DL, suggesting that current model states are inadequate