# Emulators and surrogate models via ML

Shortcuts in scientific simulation using ML

August 12, 2020 — August 26, 2020

Emulation, a.k.a. surrogate modelling. In this context, it means reducing complicated physics-driven simulations to simpler/or faster ones using ML techniques. Especially popular in the ML for physics pipeline. I have mostly done this in the context of surrogate optimisation for experiments. See Neil Lawrence on Emulation for a modern overview.

A recent, hyped paper that exemplifies this approach is Kasim et al. (2020), which (somewhat implicitly) uses arguments from Dropout ensembling to produce quasi-Bayesian emulations of notoriously slow simulations. Does it actually work? And if it *does* well quantify posterior predictive uncertainty, can it estimate other posterior uncertainties?

Emukit (Paleyes et al. 2019) is a toolkit which generically wraps ML models for emulation purposes.

ML PDEs might be a particularly useful domain.

## 1 Model order reduction

The traditional, and still useful, approach is reduced order modelling, which has many related tricks.

## 2 References

*Acta Numerica*.

*Water Resources Research*.

*Journal of Hydrology*.

*Progress in Aerospace Sciences*.

*Acta Numerica*.

*Journal of Agricultural, Biological and Environmental Statistics*.

*Frontiers in Environmental Science*.

*Journal of the American Statistical Association*.

*Frontiers in Applied Mathematics and Statistics*.

*Journal of Agricultural, Biological, and Environmental Statistics*.

*Conference on Uncertainty in Artificial Intelligence*.

*arXiv:2001.08055 [Physics, Stat]*.

*arXiv:1801.07337 [Physics]*.

*Computational Geosciences*.

*Science*.

*Geoscientific Model Development*.

*Water Resources Research*.

*Journal of the Royal Statistical Society: Series B (Methodological)*.

*Reliability Engineering & System Safety*, The Fourth International Conference on Sensitivity Analysis of Model Output (SAMO 2004),.

*Technometrics*.

*Advances In Neural Information Processing Systems*.

*Journal of the American Statistical Association*.

*Progress in Aerospace Sciences*.

*Water Resources Research*.

*Technometrics*.

*Statistical Science*.

*Third Workshop on Machine Learning and the Physical Sciences (NeurIPS 2020)*.

*Water Resources Research*.

*arXiv:2006.15641 [Cs, Stat]*.

*Hydrology and Earth System Sciences*.

*Nature Communications*.

*Proceedings of the 34th International Conference on Machine Learning - Volume 70*. ICML’17.

*Neural Networks*, Computational Intelligence in Earth and Environmental Sciences,.

*Statistical Science*.

*Advances in Intelligent Data Analysis XVIII*.

*Statistical Science*.

*Environmental Modelling & Software*.

*Journal of Hydrology*.

*Journal of Computational Physics*.