The majority of research literature on chemical separations focuses on a relatively small collection of chemicals. We will discuss steps towards methods that may eventually allow rapid development of adsorption-based separations for a diverse range of molecules drawn from a broad chemical space. By applying machine learning approaches to a rich set of molecular simulation data, a closed form model that accurately predicts adsorption isotherms for tens of thousands of molecules in thousands of metal-organic frameworks has been developed. Prospects for using this information to describe complex mixture adsorption and also efforts to broaden the scope of systems for which accurate predictions can be made will be discussed.<br/>

Making accurate predictions of millions of adsorption isotherms to enable chemical separations of complex mixtures

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.