A chemist’s view on R&D digitalization

Dr. Laura Scarbath-Evers, Senior Scientist

How the integration of machine learning with physics based modelling and enterprise informatics transforms materials discovery.

Global challenges, like a clean energy future or circular economy, have increased the demand for new materials. Typically, the performance of materials depends on a multitude of parameters which makes traditional research approaches, relying on experiments solely, slow, inefficient, and prohibitively expensive. Data driven approaches can significantly speed up the discovery process and shorten the time from idea to market.

In this presentation, we will illustrate how the integration of Schrödinger’s machine learning technologies with physics based modelling can be utilized to predict properties of new materials. Use cases from important materials science areas, like polymers and opto-electronic materials, will illustrate how data generated from experiment as well as physics-based modelling can be used to build machine learning models to predict physical properties and even suggest new compounds. Finally, we demonstrate how the integration of machine learning approaches into collaborative design schemes can maximize their usability and accessibility to non-expert users.