Yifan Qu

Yifan Qu

she/her

Hiii! I am passionate about computational mathematics, mathematical modeling, and deep neural networks, with a keen interest in applications in scientific computing and mathematical software development. Outside of research, I enjoy photography, piano, ballet, and figure skating, and I am always eager to explore interdisciplinary collaborations.

Yifan Qu’s Personal Website

I am Yifan Qu, a researcher in graph neural networks, numerical methods, and scientific computing. My work focuses on developing efficient computational methods for PDE-based models, high-performance numerical algorithms, and image processing.

🔬 Research Interests

  • Graph Neural Networks (GNNs): PDE-inspired architectures and applications in geospatial data.
  • Numerical Methods for Differential Equations: Finite element methods (FEM), finite difference methods (FDM), and high-order schemes.
  • Scientific Computing & HPC: Interval numerical methods, mixed-precision computing, and mathematical software development.
  • Computational Imaging: Underwater image processing and enhancement.

📌 Recent Projects

  • River Ice Classification with GNNs: Developed a learnable edge-weight GNN for SAR image classification, achieving a 10% accuracy improvement over CNNs.
  • PDE-Based GNNs: Designed deep GNN architectures using first-order PDEs to mitigate over-smoothing and enhance learning in deep networks.
  • Underwater Image Dehazing: Improved the Dark Channel Prior (DCP) method, reducing mean squared error by 10%.

📄 Publications & Talks

  • Presented at Geoinformatics 2024 on graph-based SAR image classification.
  • Published research on PDE-based deep learning models for graph-structured data.

📫 Get in Touch

📍 GitHub | Google Scholar | Email

Thanks for visiting! 🚀