Accessible time and size scales severely limit the range of ab initio molecular dynamics simulations. Machine learning techniques are rapidly changing this state of affairs: deep neural networks learn the interatomic potential energy surface from ab-initio data and make possible simulations with quantum mechanical accuracy at the cost of empirical force fields. The scheme leads naturally to models that include partial electronic structure information, allowing us to access properties like the dielectric response functions measured in experiments. Moreover, with incremental learning techniques it becomes feasible to construct reactive potentials that work well over a vast range of thermodynamic conditions, such as the pressure and temperature regimes that characterize molecular and ionic phases of water.

Boosting <i>ab-initio</i> molecular dynamics with machine learning

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.

Boosting ab-initio molecular dynamics with machine learning