My research focuses on AI for Science in marine and atmospheric (MetOcean) applications, including marine remote sensing, meteorological forecasting and underwater robotics. I aim to use AI methods to address real-world problems and operational needs in these domains, rather than just improving benchmarks. Beyond MetOcean, I am also interested in applying AI to other domain-specific problems, such as materials modeling and EDA.
On the technical side, I focus on transfer learning and other data-efficient deep learning techniques, as MetOcean data are often scarce, imbalanced or noisy. I also work on AI agents and spatiotemporal forecasting models for weather and maritime service applications.
Before my postgraduate studies, I worked on AI for coding, exploring cross-lingual and cross-task transfer learning to improve model generalization with limited labeled data. I also won the First Prize in the National Undergraduate Electronic Design Contest (TI Cup), which is highly prestigious and widely recognized in China.
If you are interested in my work or potential collaboration, please feel free to get in touch.