Project Description

Piezotronic materials, as an emerging choice for semiconductors, offer environmentally friendly, low-energy, and high-sensitivity advantages, making them promising candidates for next-generation transistors. However, the research on piezotronic materials is currently limited to a few materials, primarily ZnO and GaN. Despite their proven benefits over traditional semiconductors, the higher costs associated with piezotronic materials have hindered their widespread application. The vast chemical and structural combinations present many potential crystal structures that could serve as alternatives, but these have not been discovered due to computational limitations and experimental effort constraints.

To address these challenges, we propose leveraging AI to accelerate the discovery of future piezotronic materials. Presently, there are no effective AI models capable of quickly understanding and analyzing piezoelectric properties due to the small database size. We propose to use existing AI models and known databases to train models that can rapidly identify potential piezoelectric materials. This will be combined with high-throughput calculations to expand the database.
Furthermore, we aim to integrate cutting-edge AI techniques such as graph neural networks (GNNs), position encoders, and physically informed neural networks (PINNs) to design models specifically for predicting piezoelectric properties and crystal structures of piezotronic materials. By doing so, we will train AI to understand the deeper physical knowledge of materials, digitalize piezoelectric materials, expand the database, and enhance the development of next-generation piezoelectric materials. This approach will enable us to explore the vast chemical and molecular space more efficiently, leading to the rapid identification and design of new, cost-effective piezotronic materials for semiconductor applications. 

Start Date

07/01/2025

Postdoc Qualifications

The candidate should have a PhD in civil engineering, material sciences, applied math, computer science, industrial engineering, chemical engineering, electrical engineering, mechanical engineering, or related fields.
Fluent programming in one of the following programming languages: Python/Julia. Familar with PyTorch or TensorFlow. Have experience in artificial intelligence research.

Co-advisors

Name: Luna Lu
email: luna@purdue.edu
Affiliation: Lyles School of Civil Engineering
website: https://engineering.purdue.edu/CCE/People/ptProfile?resource_id=128278

Name: Guang Lin
email:guanglin@purdue.edu
Affiliation: Departments of Mathematics, Statistics & School of Mechanical Engineering
Website: https://www.math.purdue.edu/~lin491/

Bibliography

Na Lu, Guangshuai Han, Yixuan Sun, Yining Feng, Guang Lin, Artificial intelligence guided thermoelectric materials design and discovery, Advanced Electronic Materials, 9(8): 2300042, 2023.

Guangshuai Han, Yixuan Sun, Guang Lin, Na Lu, Machine learning regression guided thermoelectric materials discovery – A review, ES Materials & Manufacturing, 14, 20-35, 2021.

Guangshuai Han, Yen-Fang Su, Siwei Ma, Tommy Nantung, Na Lu, In Situ Rheological Properties Monitoring of Cementitious Materials through the Piezoelectric-based Electromechanical Impedance (EMI) Approach, Engineered Science, 2021, 16, 259-268.

Ziqi Guo, Roy Chowdhury Prabudhya1, Zherui Han, Yixuan Sun, Dudong Feng, Guang Lin*, and Xiulin Ruan, Fast and Accurate Machine Learning of Phonon Scattering Rates and Lattice Thermal Conductivity, Nature npj Computational Material 9, 95, 2023.

Ziqi Guo, Zherui Han, Dudong Feng, Guang Lin, Xiulin Ruan, Sampling-accelerated prediction of phonon scattering rates for converged thermal conductivity and radiative properties, Npj Computational Materials, 10, 31, 2024.