Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
AI-Based Computational Metrology
Development of machine learning systems to accelerate and scale up physics-based modeling and simulation — Using AI tools and physics-, chemistry-, and materials science-based knowledge, this project is aimed at developing machine learning (ML) algorithms to enable rapid and accurate selection of optimal system features and performance, as well as material discovery, under a variety of conditions.Currently, our focus is on development of Atomistic Machine Learning for prediction of atomistic properties of materials, AI-based generation and curation of microscopy images and datasets, and Performance Metrics for Direct Air Capture.
Projects
- ML algorithm development and AI Benchmarking — Using AI tools and physics-, chemistry-, and materials science-based knowledge, this project is aimed at developing machine learning (ML) algorithms to enable rapid and accurate selection of optimal system features and performance, as well as material discovery, under a variety of conditions.
- Performance Metrics for Direct Air Capture of Carbon Dioxide — For the Direct Air Capture (DAC) of CO2 from the atmosphere it is important to know how well the materials will perform as sorbents. Current material characterization includes isothermal adsorption measurements, but such information is insufficient to determine the performance. This work aims to define performance metrics based on intrinsic material properties to enable accurate and informative high-throughput screening of materials for use in DAC.