A fundamental challenge in materials chemistry is to uncover target compounds with optimal properties. This inverse design question underlies almost all of chemistry and materials science -- how to find materials design for energy conversion and storage, such as photovoltaics, piezoelectrics, spintronics, and many others. Computational discovery, particularly the use of quantum chemical methods and density functional approximations have expanded the accuracy of property predictions, but require significant time for accurate predictions. We have used genetic algorithm methods to find optimal polymers for photovoltaics and other applications. In this presentation, we will discuss the use of various machine learning methods, combined with genetic algorithm optimization to perform on-the-fly training of the ML methods while accelerating the GA method. Particular applications will include capacitve and photovoltaic materials, including polarizabilities, optical excitation energies (band gaps) and singlet-triplet gaps.

Combined evolutionary optimization and machine learning for efficient discovery of polymer materials

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.