Train, Inform, Borrow, or Combine? Approaches to Process‐Guided Deep Learning for Groundwater‐Influenced Stream Temperature Prediction
Abstract Although groundwater discharge is a critical stream temperature control process, it is not explicitly represented in many stream temperature models, an omission that may reduce predictive accuracy, hinder management of aquatic habitat, and decrease user confidence. We assessed the performan...
Saved in:
| Published in: | Water resources research Vol. 59; no. 12 |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Washington
John Wiley & Sons, Inc
01-12-2023
|
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract
Although groundwater discharge is a critical stream temperature control process, it is not explicitly represented in many stream temperature models, an omission that may reduce predictive accuracy, hinder management of aquatic habitat, and decrease user confidence. We assessed the performance of a previously‐described process‐guided deep learning model of stream temperature in the Delaware River Basin (USA). We found lower accuracy (root mean square error [RMSE] of 1.71 versus 1.35°C) and stronger seasonal bias (absolute mean monthly bias of 1.06 vs. 0.68°C) for reaches primarily influenced by deep groundwater as compared to atmospheric conditions. We then tested four approaches for improving groundwater process representation: (a) a custom loss function leveraging the unique patterns of air and water temperature coupling characteristic of different temperature drivers, (b) inclusion of additional groundwater‐relevant catchment attributes, (c) incorporation of additional process model outputs, and (d) a composite model. The custom loss function and the additional attributes significantly improved the predictive accuracy in groundwater‐dominated reaches (RMSE of 1.37 and 1.26°C) and reduced the seasonal bias (absolute mean monthly bias of 0.44 and 0.48°C), but neither approach could identify holdout groundwater reaches. Variable importance analysis indicates the custom loss function nudges the model to use the existing inputs more efficiently, whereas with the added features the model relies on a broader suite of inputs. This analysis is a substantial step toward more accurately representing groundwater discharge processes in stream temperature models and will improve predictive accuracy and inform habitat management.
Plain Language Summary
Groundwater flowing into streams and rivers can cool the water during the summer and warm it during the winter. This creates important habitat for animals like trout and dwarf wedgemussels. Resource managers use computer models of stream temperature, but most models do not simulate groundwater flows with much detail. Insufficient accounting for groundwater could lead to predicted temperatures that are less accurate or less trusted. We tested four ways of including groundwater in a stream temperature model. The particular model we used is a type of machine learning model termed “process‐guided deep learning” because it takes advantage of both the computational advances in machine learning and our collective understanding of the science of stream temperature. We found that two approaches, one that focused on patterns between the air temperature and water temperature and one that incorporated additional descriptions of each stream reach, significantly improved the temperature predictions. Our findings have important implications for stream temperature predictions, habitat management, and methods for incorporating scientific expertise into machine learning models.
Key Points
Existing process‐guided deep learning stream temperature models perform poorly in reaches with groundwater‐controlled temperatures
A custom loss function or enhanced input data improved predictive performance in monitored but not hold‐out groundwater reaches
The loss function used existing input data more efficiently; the enhanced inputs model spread its reliance to a wider range of inputs |
|---|---|
| ISSN: | 0043-1397 1944-7973 |
| DOI: | 10.1029/2023WR035327 |