postdoctoral fellow, at Harvard University, United States.
Dr. Han Gao is a dedicated researcher specializing in scientific deep learning, computational mechanics, and generative models for spatiotemporal physics. With a strong background in machine learning-driven physics simulations, he has contributed significantly to advancing numerical modeling and data-driven solutions for complex physical systems. His work bridges the gap between deep learning and traditional computational fluid dynamics, with applications in turbulence modeling, inverse problems, and reduced-order modeling.
Professional Profile
Scopus
Google Scholar
Education 🎓
Dr. Gao earned his Ph.D. in Aerospace and Mechanical Engineering from the University of Notre Dame (2018–2023), where he focused on scientific deep learning for forward and inverse modeling of spatiotemporal physics. He also holds a Master’s degree in Mechanical Engineering & Materials Science from Washington University in St. Louis (2016–2018), with research on numerical simulations of jet impingement and rotor blade effects. His academic journey began with a Bachelor’s degree in Mechanical Engineering from Shanghai University of Electric Power (2012–2016).
Professional Experience 💼
Dr. Gao is currently a Postdoctoral & Teaching Fellow at Harvard University (2023–present), where he continues his research in deep learning-driven physics simulations while mentoring students. Previously, he served as a Research & Teaching Assistant at the University of Notre Dame (2018–2023) and Washington University in St. Louis (2016–2018). Additionally, he gained industry experience as a Research Intern at Google Research (2022), where he worked on advanced AI-driven physics simulations.
Research Interests 🌍
Dr. Gao’s research revolves around the integration of deep learning techniques with physics-based modeling, particularly in solving partial differential equations (PDEs), turbulence modeling, generative models, and reduced-order modeling. He has developed novel physics-informed neural networks (PINNs), Bayesian generative models, and machine-learning frameworks for high-dimensional complex systems. His work is widely applicable in computational fluid dynamics (CFD), climate modeling, aerodynamics, and engineering simulations.
Awards & Honors 🏆
Dr. Gao has been recognized for his outstanding contributions to computational mechanics and machine learning applications in physics. His publications in top-tier journals, including Nature Communications, and prestigious machine learning conferences such as NeurIPS, ICML, and ICLR, reflect his impact in the field. He has also received competitive research opportunities, including a Google Research internship, showcasing his industry relevance.
Top Noted Publications 📚
Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data
L. Sun, H. Gao, S. Pan, J.-X. Wang – 916 citations – Computer Methods in Applied Mechanics and Engineering, 2020
PhyGeoNet: Physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain
H. Gao, L. Sun, J.-X. Wang – 567 citations – Journal of Computational Physics, 2021
Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
H. Gao, M. J. Zahr, J.-X. Wang – 240 citations – Computer Methods in Applied Mechanics and Engineering, 2022
Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
H. Gao, L. Sun, J.-X. Wang – 214 citations – Physics of Fluids, 2021
Predicting physics in mesh-reduced space with temporal attention
X. Han, H. Gao, T. Pfaff, J.-X. Wang, L.-P. Liu – 106 citations – ICLR, 2022
Conclusion
Dr. Han Gao is a highly promising researcher with a strong publication record, interdisciplinary expertise, and experience at prestigious institutions. His contributions to scientific deep learning and computational mechanics make him a strong contender for the Best Researcher Award. To further solidify his case, he could focus on gaining more individual recognitions, expanding his leadership roles, and demonstrating the real-world impact of his research.