Stream Temperature Prediction in a Shifting Environment: Explaining the Influence of Deep Learning Architecture

Simon N. Topp, Janet Barclay, Jeremy Diaz, Alexander Y. Sun, Xiaowei Jia, Dan Lu, Jeffrey M. Sadler, Alison P. Appling

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

Stream temperature is a fundamental control on ecosystem health. Recent efforts incorporating process guidance into deep learning models for predicting stream temperature have been shown to outperform existing statistical and physical models. This performance is in part because deep learning architectures can actively learn spatiotemporal relationships that govern how water and energy propagate through a river network. However, exploration of how spatiotemporal awareness and process guidance influence a model's generalizability under shifting environmental conditions such as climate change is limited. Here, we use Explainable Artificial Intelligence (XAI) to interrogate how differing deep learning architectures affect a model's learned spatial and temporal dependencies, and how those learned dependencies affect a model's ability to maintain high accuracy when applied to unseen environmental conditions. Using the Delaware River Basin in the northeastern United States as a test case, we compare two spatiotemporally aware process-guided deep learning models for predicting stream temperature (a recurrent graph convolution network—RGCN, and a temporal convolution graph model—Graph WaveNet). Both models achieve equally high predictive performance when testing data are well represented in the training data (test root mean squared errors of 1.64°C and 1.65°C); however, Graph WaveNet significantly outperforms RGCN in 4 out of 5 experiments where test partitions represent different types of unseen environmental conditions. XAI results show that the architecture of Graph WaveNet leads to learned spatial relationships with greater fidelity to physical processes, and that this fidelity improves the generalizability of the model when applied to shifting and/or unseen environmental conditions.

Original languageEnglish
Article numbere2022WR033880
JournalWater Resources Research
Volume59
Issue number4
DOIs
StatePublished - Apr 2023

Funding

Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government. Funding for this project was provided in part by the Department of Energy ExaSheds Project interagency agreement number 89243021SSC000068. We would like to thank Althea Archer and Cee Nell for their help designing Figure 1. Thanks also to the anonymous reviewers who provided constructive feedback to the manuscript. Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government. Funding for this project was provided in part by the Department of Energy ExaSheds Project interagency agreement number 89243021SSC000068. We would like to thank Althea Archer and Cee Nell for their help designing Figure 1 . Thanks also to the anonymous reviewers who provided constructive feedback to the manuscript.

Keywords

  • domain shift
  • explainable AI (XAI)
  • generalization
  • process guided deep learning
  • stream temperature

Fingerprint

Dive into the research topics of 'Stream Temperature Prediction in a Shifting Environment: Explaining the Influence of Deep Learning Architecture'. Together they form a unique fingerprint.

Cite this