Research Highlights

The solution manifold for different parameters is explored and compressed in the offline learning stage. The constructed reduced model faithfully reproduces the solution manifold with only 10 basis functions. Computer Science and Mathematics Division CSMD ORNL

A Model Order Reduction Method for Non-classical Models of Diffusion

April 15, 2020

A learning-based approximation strategy has been developed to accelerate parameter studies for non-classical models of diffusion.