English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

. The computational costs associated with coupled reactive transportsimulations are mostly due to the chemical subsystem: replacing itwith a pre-trained statistical surrogate is a promising strategy toachieve decisive speedups at the price of small accuracy losses andthus to extend the scale of problems which can be handled. Weintroduce a hierarchical coupling scheme in which “full-physics”equation-based geochemical simulations are partially replaced bysurrogates. Errors in mass balance resulting from multivariatesurrogate predictions effectively assess the accuracy ofmultivariate regressions at runtime: inaccurate surrogatepredictions are rejected and the more expensive equation-basedsimulations are run instead. Gradient boosting regressors such asXGBoost, not requiring data standardization and being able to handleTweedie distributions, proved to be a suitable emulator. Finally, wedevise a surrogate approach based on geochemical knowledge, whichovercomes the issue of robustness when encountering previouslyunseen data and which can serve as a basis for further development ofhybrid physics–AI modelling.

DecTree v1.0 – chemistry speedup in reactive transport simulations: purely data-driven and physics-based surrogates