The Michigan Institute for Computational Discovery and Engineering has awarded four outstanding junior faculty at the University of Michigan with its 2022 Catalyst Grants.
“This year’s MICDE Catalyst Grants bolster junior faculty innovations in computational science,” said MICDE Director Krishna Garikipati, professor of mechanical engineering in the College of Engineering, and professor of mathematics in LSA.
Grant recipients will share a $200,000 award that allows for the exploration of these high-impact projects with novel advancements in computational science across a breadth of research areas.
“Ranging from computer vision-enabled insights into animal behavior, through fundamental mathematical frameworks to advance quantum physics and materials discovery, to probability-based computational modeling of material behavior, the 2022–23 cohort of Catalyst Grant awardees will continue MICDE’s tradition of uncovering new frontiers of computational science,” Garikipati said.
MICDE, a unit within the Office of the Vice President for Research, launched the program in 2017. It has funded a wide spectrum of cutting-edge research that combines science, engineering, mathematics and computer science.
MICDE awarded grants for the following projects:
Evidential Crystal-graph Convolutional Neural Networks for Efficient Global Optimization of Electrocatalysts
Bryan Goldsmith, the Dow Corning Assistant Professor of Chemical Engineering and assistant professor of chemical engineering in the College of Engineering, and Suljo Linic, the Martin Lewis Perl Collegiate Professor of Chemical Engineering, associate chair in the Department of Chemical Engineering, academic program director for energy systems engineering in the Department of Integrative Systems and Design, and professor of chemical engineering and integrative systems and design in CoE, will implement evidential regression with crystal-graph convolutional neural networks to enable accurate prediction of model uncertainty and accelerate electrocatalyst optimization for energy applications.
The team will use evidential regression CGCNN within an optimization framework to discover electrocatalysts for sustainable fuel generation, which is critical to combating climate change.
Multi-Scale Continuous Tensor Networks for Quantum Simulations
Alex Gorodetsky, assistant professor of aerospace engineering in CoE, seeks to develop faster, scalable computational tools to solve higher-dimensional quantum many-body problems. The novelty of these tools lies in their ability to simultaneously exploit low-rank and locally multi-scale structures via continuous tensor networks.
These methods will enable more efficient computation, bringing solutions to several important problems in materials physics within reach.
Computer Vision Tools for Automatic Animal Behavior Classification in Complex Environments
Ada Eban-Rothschild, assistant professor of psychology in LSA, and Justin Johnson, assistant professor of electrical engineering and computer science in CoE, will work to develop an accessible computer vision toolbox to automatically track multiple animals and classify their behaviors in complex social environments.
The researchers will harness state-of-the-art developments in machine learning and computer vision as well as a rich dataset of manually annotated video recordings.
Probability Mechanisms Map of Dislocation-Obstacle Interactions as an Enabler of Physics-Based Multiscale Modeling on Precipitation Hardening
Yue Fan, assistant professor of mechanical engineering in CoE, and Xun Huan, assistant professor of mechanical engineering in CoE, seek to develop a novel modeling framework to probe the accessible transition pathways and uncover the competing atomistic interaction mechanisms for any given dislocation-obstacle pair.
The project will establish a capability of quantifying the occurrence probability of each mechanism and its embedded uncertainty over broad thermo-mechanical parameter space covering realistic timescales. This effort will make possible research of a wide range of temperature and deformation states with relevance to material behavior for energy, aerospace and other applications.