First-principles and Machine Learning-Guided Search for High Thermal Conductivity Materials
|Interdisciplinary Areas:||Data and Engineering Applications, Micro-, Nano-, and Quantum Engineering, Power, Energy, and the Environment
High thermal conductivity is a key material property desired for semiconductor devices. Meanwhile, devices and heat sinks should have other favorable features such as high interfacial thermal conductance (ITC) and matching coefficient of thermal expansion (CTE). Existing high thermal conductivity materials suffer one or more drawbacks including high cost, poor ITC and high thermal stress. Moreover, discovery of such materials has been based on trial and error process, which is expensive and slow. Accelerated development based on state-of-the-art first principles calculations and machine learning methods are highly desirable. Recently, Ruan has developed the general formulation of four-phonon scattering and predicted a room-temperature thermal conductivity of 1400 W/m-K for boron arsenide (BAs), which was confirmed by experiments later. It has since been accepted by the community that Ruan’s four-phonon scattering theory should be considered when searching for high thermal conductivity dielectric and semiconductor materials. Built upon our previous success, the goal of this project is to enable high throughput search of high thermal conductivity materials with predictive first principles calculations that incorporate 3- and 4-phonon scattering. Further, considering that such predictions are computationally expensive, we will develop novel machine learning approaches such as neural networks and genetic algorithms to significantly accelerate the prediction. We expect to discover new high thermal conductivity materials and gain unique insights. The project is built upon Professors Xiulin Ruan and Guang Lin’s combined expertise on thermal transport predictions, machine learning, and GPU programming.
The candidate is expected to have earned (or will earn in the near future) a PhD degree in Mechanical Engineering, Physics, Materials Science and Engineering, or other related fields. Relevant previous research experience and scientific publications are desired. The candidate should also have excellent writing and speaking skills.
Xiulin Ruan, email@example.com, Professor, School of Mechanical Engineering, https://engineering.purdue.edu/NANOENERGY/
Guang Lin, firstname.lastname@example.org, Professor, Department of Mathematics (primary appointment), Professor, Department of Statistics, Professor, School of Mechanical Engineering, https://www.math.purdue.edu/~lin491/
Ziqi Guo, Prabudhya Roy Chowdhury, Zherui Han, Yixuan Sun, Dudong Feng, Guang Lin, and Xiulin Ruan, "Fast and Accurate Machine Learning Prediction of Phonon Scattering Rates and Lattice Thermal Conductivity," npj Computational Materials 9, 95 (2023).
Prabudhya Roy Chowdhury and Xiulin Ruan, "Unexpected thermal conductivity enhancement in aperiodic superlattices discovered using active machine learning," npj Computational Materials 8, 12 (2022).
Tianli Feng, Lucas Lindsay, and Xiulin Ruan, “Four phonon scattering significantly reduces thermal conductivity in solids,” Phys. Rev. B, 161201(R) (2017).
Guangshuai Han, Yixuan Sun, Yining Feng, Guang Lin, and Na Lu, Artificial intelligence guided thermoelectric materials design and discovery, Advanced Electronic Materials, 2300042 , 2023.
Guangshuai Han, Yixuan Sun, Guang Lin, and Na Lu, Machine learning regression guided thermoelectric materials discovery – A review, ES Materials & Manufacturing, 14, 20-35, 2021.