Yuan Qiu

Hi! I am a Ph.D. candidate in Computational Science and Engineering at Georgia Tech, advised by Peng Chen. Before joining Georgia Tech, I received my bachelor’s degree in mathematics from Sun Yat-sen University in 2022.

My research focuses on machine learning for functional data arising primarily from the physical sciences, particularly on developing scalable, reliable, and fast surrogate models by incorporating prior knowledge into the network architecture and training process. Recently, I am exploring broader connections to downstream tasks, including inverse problems, data assimilation, and uncertainty quantification, as well as engineering systems involving AI agents and digital twins.

News

Sep 30, 2026 Our paper on C-STRIDE has been released on arXiv.
Sep 24, 2026 I am presenting a poster on variationally correct operator learning for nonlinear PDEs at the 2026 MFEM Community Workshop.
Sep 17, 2026 Our paper on CLDNet4Flood has been accepted by Journal of Hydrology.
Aug 31, 2026 I am presenting a poster on going beyond small $L^2$ error at the ACM AI Summit 2026.
Jul 06, 2026 Our paper on variationally correct operator learning has been accepted by Computer Methods in Applied Mechanics and Engineering.

Publications & Preprints

  1. C-STRIDE: An Observation-Driven AI Digital Twin for Predicting Basin-Wide Flood Fields from Sparse Stream-Gauge Histories
    Yanjie Tong, Phillip Si, Yuan Qiu, Peng Chen
    arXiv preprint, 2026
  2. Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations
    Phillip Si, Yuan Qiu, Omar Sallam, Jeremy Feinstein, Ziang He, Eugene Yan, Peng Chen
    Journal of Hydrology, 2026
  3. Variationally correct operator learning: Reduced basis neural operator with a posteriori error estimation
    Yuan Qiu, Wolfgang Dahmen, Peng Chen
    Computer Methods in Applied Mechanics and Engineering, 2026
  4. Derivative-enhanced deep operator network
    Yuan Qiu, Nolan Bridges, Peng Chen
    Advances in Neural Information Processing Systems, 2024
  5. Truthful and privacy-preserving generalized linear models
    Yuan Qiu, Jinyan Liu, Di Wang
    Information and Computation, 2024