Kopera awarded research fellowship for machine learning research

Machine Learning


Michal Kopera, associate professor of mathematics and director of the Numerical Modeling Laboratory (NUMO Institute), has been awarded a prestigious National Science Foundation EPSCoR Research Fellowship to support new research initiatives at the intersection of scientific computing and machine learning.

As part of this award, Kopela will spend a significant portion of his next sabbatical, starting in the summer of 2026, in the Massachusetts Institute of Technology’s Multiscale Estimation and Assimilation Laboratory. There he will collaborate with Professor Pierre L’Hermjoux, a leading expert on ocean modeling and data-driven forecasting.

This project focuses on developing adaptive mesh refinement techniques using machine learning, an advanced computational method to dynamically adjust the resolution of numerical simulations. By integrating data-driven decision-making into these techniques, this research aims to improve the efficiency and accuracy of simulations used in complex systems such as ocean circulation and environmental forecasting.

The research will involve members of the Boise State NUMO Lab, including graduate students Antone Chacartegui (PhD in Computing) and Hailey Stubbers (Master’s in Mathematics). Chacartegui will join Kopera at MIT for part of the visit and will directly contribute to the collaboration.

In addition to advancing fundamental research in computational mathematics, this fellowship will establish new collaborations between Boise State University and MIT, strengthen the relationship between the NUMO lab and the MIT group, and create new opportunities for students to participate in cutting-edge research.



Source link