Computer simulations can provide important atomic-scale insights into chemical systems. But the accuracy of simulation predictions relies on how well interatomic interactions are modeled. These interactions generally fall into two classes: strong short-range interactions that lead to interactions like hydrogen bonding, and long-range interactions that often have subtle but important consequences, such as dielectric screening. In this presentation, I will review the importance of long-range interactions in liquids, solids, and their interfaces. After this, I will discuss recent approaches for modeling long-range interactions. I will focus on how a physical understanding of electrostatic interactions in condensed phases can be used to develop machine learning-based models for interatomic interactions that include long-range interactions. I will then demonstrate the accuracy and transferability of this approach, the self-consistent field neural network, before closing with a discussion of future applications and further development.

Machine learning long range interactions in models of liquids and their interfaces

Where thousands of chemistry professionals meet to share ideas and advance scientific and technical knowledge. Spring 2023 abstracts, posters, and presentations will launch at the end of March.

ACS Spring 2023

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