What the study found
The study found that river stage dynamics, meaning the period and amplitude of water-level fluctuations, are the main drivers of dissolved oxygen supply to riparian aquifers. Other factors, such as hydraulic conductivity, riverine dissolved oxygen concentration, and the maximum dissolved oxygen reaction rate, matter in more limited or localized ways. Several other parameters showed negligible influence.
Why the authors say this matters
The authors say this matters because dissolved oxygen is key to controlling redox conditions, the chemical conditions that affect subsurface processes. They conclude that combining deep learning with global sensitivity analysis can help evaluate complex environmental systems efficiently and can support model simplification and diagnosis.
What the researchers tested
The researchers used a global sensitivity analysis framework to study dissolved oxygen dynamics in riparian aquifers. They combined Bayesian network-based and variance-based sensitivity methods, and built surrogate models with deep learning approaches, specifically multi-layer perceptrons and convolutional neural networks, to reduce the computational cost of analyzing a high-resolution numerical model.
What worked and what didn't
The framework identified river stage dynamics as the dominant control on dissolved oxygen supply. Hydraulic conductivity, riverine dissolved oxygen concentration, and maximum dissolved oxygen reaction rate had important but localized effects, influencing pathways such as river water infiltration, entrapped air dissolution, and diffusion through the unsaturated zone. In contrast, porosity, longitudinal dispersion, and van Genuchten soil parameters had negligible influence.
What to keep in mind
The abstract does not describe detailed study limitations beyond the general challenge of uncertainty and computational expense in complex models. The results are reported for a high-resolution model of riparian dissolved oxygen transport, so the scope described here is specific to that system.
Key points
- River stage dynamics were the primary drivers of dissolved oxygen supply to the aquifer.
- Hydraulic conductivity, riverine dissolved oxygen concentration, and maximum dissolved oxygen reaction rate had localized effects.
- Porosity, longitudinal dispersion, and van Genuchten soil parameters showed negligible influence.
- The study used Bayesian network-based and variance-based global sensitivity analysis methods.
- Deep learning surrogate models were built with multi-layer perceptrons and convolutional neural networks.
Disclosure
- Research title:
- River stage dynamics drive dissolved oxygen supply in riparian aquifers
- Authors:
- Heng Dai, Yijie Yang, Fangqiang Zhang, Alberto Guadagnini, Jing Yang, Xiaochuang Bu, Lunche Wang, Songhu Yuan, Ming Ye
- Institutions:
- Chang'an University, China University of Geosciences, China University of Geosciences, China University of Geosciences, China University of Geosciences, China University of Geosciences, China University of Geosciences, Florida State University, Hubei University, Politecnico di Milano
- Publication date:
- 2026-01-30
- DOI:
- 10.1029/2025wr041884
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with scholarly research without reading academic papers — one filtered digest, every Friday.