Machine Learning for Materials and Microelectronic Device Characterization
Sayeef Salahuddin, Professor
Electrical Engineering and Computer Science
Applications for Fall 2026 are closed for this project.
Modern microelectronic devices operate at length scales where atomic structure, electronic properties, and thermal effects become strongly interconnected. In this project, we will develop machine learning methods to model materials and nanoscale electronic devices. Students will work with atomistic simulations and machine learning models to study nanoscale materials relevant to next-generation semiconductor devices. The broader goal is to use machine learning to better characterize and accelerate the development of next-generation materials and microelectronic devices.
Role: Students will contribute to one or more aspects of the project, such as developing and training machine learning models, analyzing electronic or thermal properties of materials, generating and processing simulation data, and evaluating models for device characterization.
Qualifications: Coursework or experience in at least one of the following is required: machine learning (CS 189/182), solid-state physics (Physics 141a/b), and/or semiconductor devices (EE 130a/230c). Students should be interested in computational research and willing to learn relevant physics and machine learning methods.
Hours: to be negotiated
Engineering, Design & Technologies Mathematical and Physical Sciences