Biological and Environmental Research - Earth and Environmental System Sciences
Earth and Environmental System Modeling

Revealing Causal Controls of Storage-Streamflow Relationships With a Data-Centric Bayesian Framework Combining Machine Learning and Process-Based Modeling

TitleRevealing Causal Controls of Storage-Streamflow Relationships With a Data-Centric Bayesian Framework Combining Machine Learning and Process-Based Modeling
Publication TypeJournal Article
Year of Publication2020
JournalFrontiers in Water
Volume2
Abstract / Summary

Some machine learning (ML) methods such as classification trees are useful tools to generate hypotheses about how hydrologic systems function. However, data limitations dictate that ML alone often cannot differentiate between causal and associative relationships. For example, previous ML analysis suggested that soil thickness is the key physiographic factor determining the storage-streamflow correlations in the eastern US. This conclusion is not robust, especially if data are perturbed, and there were alternative, competing explanations including soil texture and terrain slope. However, typical causal analysis based on process-based models (PBMs) is inefficient and susceptible to human bias. Here we demonstrate a more efficient and objective analysis procedure where ML is first applied to generate data-consistent hypotheses, and then a PBM is invoked to verify these hypotheses. We employed a surface-subsurface processes model and conducted perturbation experiments to implement these competing hypotheses and assess the impacts of the changes. The experimental results strongly support the soil thickness hypothesis as opposed to the terrain slope and soil texture ones, which are co-varying and coincidental factors. Thicker soil permits larger saturation excess and longer system memory that carries wet season water storage to influence dry season baseflows. We further suggest this analysis could be formulated into a data-centric Bayesian framework. This study demonstrates that PBM present indispensable value for problems that ML cannot solve alone, and is meant to encourage more synergies between ML and PBM in the future.

URLhttp://dx.doi.org/10.3389/frwa.2020.583000
DOI10.3389/frwa.2020.583000
Project: 
Journal: Frontiers in Water
Year of Publication: 2020
Volume: 2
Publication Date: 11/2020

Some machine learning (ML) methods such as classification trees are useful tools to generate hypotheses about how hydrologic systems function. However, data limitations dictate that ML alone often cannot differentiate between causal and associative relationships. For example, previous ML analysis suggested that soil thickness is the key physiographic factor determining the storage-streamflow correlations in the eastern US. This conclusion is not robust, especially if data are perturbed, and there were alternative, competing explanations including soil texture and terrain slope. However, typical causal analysis based on process-based models (PBMs) is inefficient and susceptible to human bias. Here we demonstrate a more efficient and objective analysis procedure where ML is first applied to generate data-consistent hypotheses, and then a PBM is invoked to verify these hypotheses. We employed a surface-subsurface processes model and conducted perturbation experiments to implement these competing hypotheses and assess the impacts of the changes. The experimental results strongly support the soil thickness hypothesis as opposed to the terrain slope and soil texture ones, which are co-varying and coincidental factors. Thicker soil permits larger saturation excess and longer system memory that carries wet season water storage to influence dry season baseflows. We further suggest this analysis could be formulated into a data-centric Bayesian framework. This study demonstrates that PBM present indispensable value for problems that ML cannot solve alone, and is meant to encourage more synergies between ML and PBM in the future.

DOI: 10.3389/frwa.2020.583000
Citation:
Tsai, W, K Fang, X Ji, K Lawson, and C Shen.  2020.  "Revealing Causal Controls of Storage-Streamflow Relationships With a Data-Centric Bayesian Framework Combining Machine Learning and Process-Based Modeling."  Frontiers in Water 2.  https://doi.org/10.3389/frwa.2020.583000.