Addressing materials-by-design
Led by Prasanna Balachandran, the Materials Informatics Group focuses on developing novel informatics approaches to accelerate the search and discovery of new materials. Our capabilities include establishing quantitative structure-property relationships for bulk, thin films, and heterostructures (to name a few) and guiding experiments/computations towards promising regions in the vast design space using density functional theory (DFT), machine learning (with an emphasis on uncertainty quantification), Bayesian learning, and optimal learning methods.
Applying ML to materials design and discovery
Materials Informatics: Data and Knowledge Driven Materials Science
We seek to address the grand challenges of materials-by-design from the viewpoint of learning from data (experimental and/or computational). Further, we also leverage the materials knowledge (whenever possible) and seek to uncover meaningful physical insights from the vast and high-dimensional search space.
Our overarching goal is to build a data- and knowledge-based informatics platform for a wide variety of problems in materials science and engineering.
Research methods:
Density Functional Theory:
Computational methods based on density functional theory (DFT) that calculate the electronic structure of solids have been pivotal to accelerate the search and discovery of new materials.
Machine Learning:
Methods ranging from dimensionality reduction, clustering analysis, classification learning, and regression methods
Optimal Learning:
Advanced evaluation of he tradeoff between “exploration” and “exploitation” in an iterative feedback loop.
