Abstract:
Machine learning is a useful tool in the context of materials science, but there are many challenges on the way to realizing the dream of accelerating the scientific process. Here, I present some ways forward that the Energy & Materials team at Toyota Research Institute have used to accelerate the design and discovery of new functional materials, with an emphasis on materials representation. Case studies will draw from (among other things) representations of molecular dynamics trajectories, how targeted design of machine learning protocols can let us discover new spectrum-property trends in the context of X-ray absorption spectroscopy (XAS), and how we can strategically use multiple levels of fidelity in the machine learning context to accelerate discovery campaigns.
Bio:
Steven Torrisi is a research scientist at the Toyota Research Institute (TRI). He works on a variety of first-principles simulations, materials informatics, and machine learning projects, including the development of new material representations, computational-experimental workflows, and the study of energy-related materials. Prior to coming to TRI, Steven obtained his Ph.D. in Physics at Harvard University working in the group of Prof. Boris Kozinsky on the application of machine learning to accelerating molecular dynamics simulations. Previously, he has done research in a variety of physical science fields ranging from plasma physics, AMO physics, two-dimensional materials, biophysics, and photocatalysis. Steven also holds a B.S. in Physics and a B.A. in Mathematics from the University of Rochester. At Harvard, he was supported by a Pierce Fellowship, a Wallace-Noyes fellowship, and a Department of Energy Computational Science Graduate Fellowship.
Hosts:
AI/ML @ SUFs Working Group
The Applied AI/ML Seminar Series is presented with the goal of increasing communication and collaboration between scientists at the three facilities: [Advanced Photon Source (APS), Argonne Tandem Linac Accelerator System (ATLAS) and the Center for Nanoscale Materials (CNM)] and providing a resource for both new and experienced AI/ML practitioners at Argonne National Lab. We plan to host a monthly seminar and tutorial series. Please join the Slack workspace or see the group website for scheduling/resources.
Location:
Microsoft Teams meeting
Join on your computer, mobile app or room device
Click here to join the meeting
Meeting ID: 267 408 499 014
Passcode: 98Z3Cz
Download Teams | Join on the web
Or call in (audio only)
+1 630-556-7958,,478435753# United States, Big Rock
Phone Conference ID: 478 435 753#