Collaborative Research: Elements: Empowering Semiconductor Device Research and Education through Integrated Machine Learning Models and Database

With the efforts to re-shore semiconductor manufacturing and strengthen the U.S. semiconductor ecosystem, semiconductor data and models are playing an increasingly important role in semiconductor design, research, and education. In the materials research and education community, materials databases and machine learning models have been developed and deployed. These efforts have greatly facilitated materials research and education. In contrast, in semiconductor device technologies, such capabilities are important but significantly lag behind. Semiconductor device models, which are fundamental to circuit and system research, require significant domain knowledge of device physics to develop from scratch or to extract a large number of model parameters, which limits their accessibility. This project will develop and deploy a foundational semiconductor research and education cyberinfrastructure (CI) to address these gaps. The CI will be deployed in the form of an integrated device database and ML models. Establishing a conveniently accessible cyberinfrastructure on shared semiconductor device data and ML models will provide semiconductor researchers with a powerful tool, lower the entry barrier, and facilitate broad participation in research and education in the area of semiconductor devices and design. The objectives of this program are to develop and deploy a broadly accessible CI of integrated machine-learning device models and device data for empowering semiconductor device research and education, to understand and explore how to use advanced TCAD simulations to efficiently obtain accurate device data for database deployment, to interface the device data with machine learning methods for producing accurate and reusable ML semiconductor device models, and to self-sustain the semiconductor device CI through developing accompanying learning modules and enabling user participation. The semiconductor devices included in the CI are important to future computing, memory, power electronics, and quantum computing interface technologies. The project will develop a foundational semiconductor research and education CI tool in the form of a device database and ML models, and contribute to strengthening the semiconductor ecosystem by making semiconductor device data and ML models readily accessible. This project is jointly funded by the OAC Cyberinfrastructure for Sustained Scientific Innovation (CSSI) program and the EDU Core Research (ECR) program. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.