Project Description
Machine-learning (ML)-based materials informatics approaches (MI) are increasingly used to accelerate design and discovery of new materials with targeted properties, and extend the applicability of first-principles techniques to larger systems. However, in order to empower materials with AI capabilities, it is crucial to develop a predictive framework that can learn and update the relationship between atomistic structure properties and resultant functional properties of the materials. We developed forward and inverse ML models that can predict electronic properties of materials, based on atomic environments and provide important design guide for future materials. In this project, we will continue the development to predict electronic, thermal and other chemical properties of device enabling materials. Once developed, we anticipate that the framework would have broad applicability to diverse materials for a range of technological applications including materials for polycrystalline electronics that is essential to realize transparent electronics on smart phone displays, and electronics on top of metal layers in chips.
CU Aerospace Nanoscale Transport Modelling (CUANTAM) Laboratory
Special Requirement
Student must have experience with MATLAB/Python and/or other programming languages. A strong mathematics background and some basic physics/chemistry knowledge are also desired. The student should have maintained at least a 3.5 GPA. Some fundamental knowledge of materials electronic properties will be helpful but not required.
Contact
- Sanghamitra Neogi (faculty)
- Artem Pimachev (graduate student)