Employing generative adversarial neural networks as surrogate model for reactive transport modeling in the hyporheic zone
Journal of Hydrology(2024)
Abstract
This study explores the application of advanced deep learning techniques, specifically conditional deep convolutional generative adversarial networks (cDC-GANs), to model and predict the complex dynamics of the hyporheic zone (HZ) driven by river stage fluctuations. The HZ is a critical transitional mixing zone between surface water and groundwater, where significant biogeochemical reactions occur. Traditional process-based reactive transport modeling methods are computationally intensive and require fine-scale parameterization. To overcome these challenges, we employ the cDC-GAN as a deep-learning-based surrogate model to predict zones of enhanced biogeochemical activity (i.e., hotspots) and reaction product concentrations in the HZ under varying bimodal sedimentary heterogeneity scenarios. The cDC-GAN model can efficiently capture nonlinear relationships between input data and output parameters without extensive parameterization, making it computationally less demanding. The model’s generative capabilities allow for the creation of new data instances, enabling the exploration of diverse scenarios and interpolation between observed data points. The model uses maps of liquid saturation and solute concentrations at different time steps to generate corresponding maps of reaction rates and reaction product concentrations. Results demonstrate the model’s qualitative and quantitative ability to capture complex relationships without relying on rigid assumptions about linearity or specific probability distribution functions. Notably, even amid variations in aquifer heterogeneity, the model consistently exhibits robust performance, validating its ability to adapt to dynamic geological settings. Our use of a simplified reaction scheme serves as a proof of concept for the cDC-GAN model’s ability to simulate solute transport in the HZ, opening avenues for future applications including more complex reaction networks within HZ system such as nutrient cycling, organic matter degradation, redox reactions, and beyond.
MoreTranslated text
Key words
Generative adversarial networks,Reactive transport modeling,Deep learning,Hyporheic exchange,Heterogeneous aquifer
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined