Main content start
Data-driven approaches in materials research
Data-driven approaches have suggested novel ways in science and engineering research based on accumulated scientific data with advances in data science, machine learning algorithms, and computing power. Machine learning-assisted, data-driven approaches can provide a comprehensive way to investigate feature-property relationships in material systems with unknown governing equations. Our group uses data-driven approaches along with traditional mechanics-driven approaches in our research to answer scientific questions.
Selected Publications
- "Machine Learning Assisted Analysis of Electrochemical H2O2 Production," J. Leem#, L. Vallez#, T. M. Gill, and X. L. Zheng, ACS Appl. Energy Mater. 6, 3953–3959 (2023)
- "Data-Driven Approach to Tailoring Mechanical Properties of a Soft Material," J. Leem, Y. Jiang, A. Robinson, Y. Xia, and X. L. Zheng, Adv. Funct. Mater. 2304451 (2023)
Interested in this research area?
Contact Juyoung Leem (jleem@stanford.edu).