About me
My name is Pu Ren. I am a Postdoc Fellow in Machine Learning and Analytics Group at Lawrence Berkeley National Lab, where I am working with Prof. Michael Mahoney. I also work closely with Dr. Dmitriy Morozov and Prof. Ben Erichson. I received my Ph.D. at Northeastern University in July 2022, where I worked with Prof. Hao Sun and Prof. Ryan Wang. I was also fortunate to collaborate with Prof. Jerome F. Hajjar, Prof. Yang Liu, and Prof. Jian-Xun Wang.
I am broadly interested in AI methods for scientific problems. I am working on both the methodology and application sides of scientific machine learning. In specific, I work on soft and hard-constrained machine learning, super-resolution, and generative modeling. I apply these methods to many scientific domains, e.g., fluid dynamics, geophysics, and cosmology. Please see the latest update on my [Google Scholar] page.
If you are interested in my research, feel free to reach out at puren93 AT gmail DOT com.
Selected news
- [08/2023] Our work on physics-informed super-resolution for spatiotemporal data has been published in the Journal of Computational Physics. [Paper]
- [06/2023] Our work on SuperBench is on [arXiv] now. We build a super-resolution benchmark for scientific machine learning!
- [06/2023] Our work on encoding physics to learn reaction-diffusion processes has been accepted by Nature Machine Intelligence. If you are interested in it, please see our [arXiv] version. [Update: This Paper is online now!]
- [04/2023] Our work on seismic inversion using PINNs is on [arXiv].
- [10/2022] Our work on physics-informed deep learning for seismic wave propagation is available on [arXiv].
- [09/2022] I joined the Machine Learning and Analytics Group at Lawrence Berkeley National Lab!
- [07/2022] I successfully defended my PhD dissertation!
- [01/2022] Our paper ‘‘Discovering nonlinear PDEs from scarce data with Physics-encoded learning’’ has been accepted in The Tenth International Conference on Learning Representations (ICLR)! [arXiv]
- [12/2021] Our Paper ‘‘PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs’’ has been published in Computer Methods in Applied Mechanics and Engineering. [Paper], [arXiv]
Selected awards
- [05/2021] Second Place of 2021 EMI Dynamics Committee Student Paper Competition [Link]
- [05/2020] Third Place of 2020 EMI SHM&C Committee Student Paper Competition [Link]
- [09/2019] Vilas Mujumdar Fellowship
- [10/2018] China National Scholarship
- [04/2015] Finalist of Mathematical Contest in Modeling (top 1%)