Marco De Lucia , Michael Kühn

The computational costs associated with coupled reactive transport
simulations are mostly due to the chemical subsystem: replacing it
with a pre-trained statistical surrogate is a promising strategy to
achieve decisive speedups at price of small accuracy losses and thus
to extend the scale of problems which can be handled. We introduce a
hierarchical coupling scheme in which ``full physics'',
equation-based geochemical simulations are partially replaced by
surrogates. Errors on mass balance resulting from multivariate
surrogate predictions effectively assess the accuracy of
multivariate regressions at runtime: inaccurate surrogate
predictions are rejected and the more expensive equation-based
simulations are run instead. Gradient boosting regressors such as
xgboost, not requiring data standardization and being able to handle
Tweedie distributions, proved a suitable emulator. Finally, we
devise a surrogate approach based on geochemical knowledge which
overcomes the issue of robustness when encountering previously
unseen data, and which can serve as basis for further development of
hybrid physics-AI modelling.