A physically integrated GNN surrogate for microbially-mediated kinetic reactive transport: PHYGNET
Abstract
Reactive transport modelling (RTM) is essential for subsurface environmental management but is fundamentally constrained by traditional geochemical solvers. These solvers incur prohibitive computational costs and frequently suffer from numerical instabilities such as convergence failures, particularly in microbially-mediated kinetic reaction systems. While machine learning surrogates offer acceleration, they often lack physical consistency when dealing with stiff biogeochemical dynamics. Here we propose PHYGNET (Physically GNN Network), which maps microbial reaction networks into a directed graph by representing species and reactions as nodes and edges. It embeds Monod-type kinetics within a differentiable physics layer that enforces stoichiometric mass conservation and thermodynamic hierarchies, and incorporates a residual corrector that refines the final outputs at the cost of small deviations from exact mass balance. By successfully coupling with COMSOL, PHYGNET demonstrates the capability to execute full reactive transport simulations. Benchmark tests reveal that, in contrast to the severe super-linear time penalties faced by traditional solvers at engineering scales, PHYGNET maintains stable sub-linear scaling via tensor parallelism. At a scale of 10 ⁵ grid nodes, PHYGNET achieved an acceleration (up to 3588-fold) without numerical crashes. Furthermore, its escalating speedup ratio establishes a “small-sample training, ultra-large-scale inference” paradigm that effectively offsets initial data generation costs. Overall, PHYGNET provides an efficient and physically consistent framework for accelerating Monod-type microbial reactive transport simulations, offering a practical pathway for large-scale environmental applications.
Versions
Related
- Microbially mediated interactions between enhanced weathering and carbon inputs shift soil organic carbon dynamics
- West-WRF AI 2-km: High-Resolution Prediction of Integrated Vapor Transport and Precipitation
- Bacterial interfaces and surface chemistry shape hydroxyapatite mineral architecture during microbially induced calcium phosphate precipitation
- Integrated assessment of heavy metal dynamics, ecological risk, and plant-mediated phytostabilization in mining-affected soils
- Physically constrained Mamba forecasting supports multiobjective reservoir water quality decisions
BibTeX
@article{wang2026physically,
title = {{A physically integrated GNN surrogate for microbially-mediated kinetic reactive transport: PHYGNET}},
author = {Jinbo Wang and Kunfeng Zhang and Walter Illman and Shuai Chen and Mingzhu Liu},
journal = {Hydrology and Earth System Sciences},
year = {2026},
month = nov,
doi = {10.5194/hess-30-6843-2026},
url = {https://doi.org/10.5194/hess-30-6843-2026},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A physically integrated GNN surrogate for microbially-mediated kinetic reactive transport: PHYGNET
AU - Jinbo Wang
AU - Kunfeng Zhang
AU - Walter Illman
AU - Shuai Chen
AU - Mingzhu Liu
PY - 2026
DA - 2026/11/09
JO - Hydrology and Earth System Sciences
DO - 10.5194/hess-30-6843-2026
UR - https://doi.org/10.5194/hess-30-6843-2026
AB - Reactive transport modelling (RTM) is essential for subsurface environmental management but is fundamentally constrained by traditional geochemical solvers. These solvers incur prohibitive computational costs and frequently suffer from numerical instabilities such as convergence failures, particularly in microbially-mediated kinetic reaction systems. While machine learning surrogates offer acceleration, they often lack physical consistency when dealing with stiff biogeochemical dynamics. Here we propose PHYGNET (Physically GNN Network), which maps microbial reaction networks into a directed graph by representing species and reactions as nodes and edges. It embeds Monod-type kinetics within a differentiable physics layer that enforces stoichiometric mass conservation and thermodynamic hierarchies, and incorporates a residual corrector that refines the final outputs at the cost of small deviations from exact mass balance. By successfully coupling with COMSOL, PHYGNET demonstrates the capability to execute full reactive transport simulations. Benchmark tests reveal that, in contrast to the severe super-linear time penalties faced by traditional solvers at engineering scales, PHYGNET maintains stable sub-linear scaling via tensor parallelism. At a scale of 10 ⁵ grid nodes, PHYGNET achieved an acceleration (up to 3588-fold) without numerical crashes. Furthermore, its escalating speedup ratio establishes a “small-sample training, ultra-large-scale inference” paradigm that effectively offsets initial data generation costs. Overall, PHYGNET provides an efficient and physically consistent framework for accelerating Monod-type microbial reactive transport simulations, offering a practical pathway for large-scale environmental applications.
SN - 1607-7938
ER -