Xinlun Cheng is a postdoctoral research associate in the School of Data Science. He is currently working in professor Stephen Baek’s Visual Intelligence Lab on developing new algorithm and training strategies in physics-informed machine learning (PIML) and AI4Science, especially for turbulent flow, reactive flow and other complex flow problems. Apart from deep learning, he also has experience in using computational fluid dynamics solvers, such as OpenFOAM, and has generated multi-phase flow simulation data as dataset for PIML model development.
Prior to becoming a postdoc in 2024, Cheng had been involved in research in Baek’s lab for two years and worked on development of PARCv2, application of PARCv2 on various computational fluid dynamics problems, and comparison with other PIML models. He was also involved in data mining large sky survey databases with the UVA Department of Astronomy.
Cheng holds a Ph.D. in astronomy from the University of Virginia. He also holds a B.S. in physics from Tsinghua University and a M.S. in data science from UVA.
PhD in Astronomy, 2024
University of Virginia
MSc in Data Science, 2022
University of Virginia
BSc in Physics, 2018
Tsinghua University
PyTorch, Sklearn, TensorFlow, Numpy, Scipy, Astropy
Deep Learning, Physics-Informed Machine Learning, Physics-Informed Neural Network (PINN), Neural Operators, Data-driven Modeling, AI4Science, Computer Vision, Artificial Intelligence
OpenFOAM