Machine Learning-driven Autonomous Systems for Materials Discovery and Optimization
This project uses machine learning to automate materials discovery and optimization, focusing on integrating physics knowledge and analyzing high-throughput data.
Browse similar grants
This grant is no longer accepting proposals
NRC Research Associateship Programs has archived this opportunity.
Funder: NRC Research Associateship Programs
Due Dates: February 1, 2025 | May 1, 2025 | August 1, 2025 | November 1, 2025
Funding Amounts: Stipend approximately $82,764 per year plus $3,000 travel allowance; typical appointment duration 2 years.
Summary: Supports postdoctoral research using machine learning-driven autonomous systems to accelerate discovery and optimization of advanced materials integrating physics knowledge and high-throughput data analysis.
Key Information: Open to U.S. citizens with a doctoral degree earned within the last 5 years; requires contacting a Research Adviser prior to application; NIST participates in February and August review cycles.
Description
This fellowship opportunity supports research on machine learning-driven autonomous research systems aimed at accelerating the discovery and optimization of advanced materials. The research integrates machine learning with machine-controlled synthesis and characterization tools to enable closed-loop experiment design, execution, and analysis. Key methods include active learning, Bayesian optimization, and the incorporation of prior physics knowledge from theory and materials property databases.
The project focuses on verifying and identifying phase maps for thin films, bulk materials, surface morphologies of solid-state materials, and aqueous electrochemical materials. It also involves offline and real-time analysis of high-throughput combinatorial "library" experiments using hyperspectral methods to analyze X-ray diffraction and Raman spectra, as well as hyperspectral micrographs.
Materials of interest include metallic glasses, photovoltaic, superconductive, multiferroic, thermoelectric, thermochromic, and magnetic materials. This research aligns with the Materials Genome Initiative and emphasizes informatics, data mining, and active learning in functional materials.
The fellowship is hosted at the National Institute of Standards and Technology (NIST) in Gaithersburg, MD, within the Material Measurement Laboratory, Materials Measurement Science Division.
