My research focuses on uncovering the underlying mechanisms of hydrological extreme events—including droughts, floods, and compound drought-heatwave events—that are not yet fully understood. I am particularly interested in forecasting and estimating these events using stochastic approaches, physics-informed/pure deep learning techniques, and mechanistic models. By developing state-of-the-art hydrological forecasting models grounded in both physical principles and data-driven methodologies, my work aims to contribute to the establishment of climate-resilient water management measures and infrastructures.

​

My expertise encompasses the following areas, underpinned by strong foundations in physical, mathematical, and statistical principles:

• Analyzing implications of the ocean-atmosphere-land feedback, such as atmospheric internal variability (e.g., Rossby waves, atmospheric blocking), atmospheric rivers, land-atmosphere feedback, on hydrological extreme evens.

• Developing advanced long-term forecasting models using entropy theory, deep learning, and physics-informed deep learning approaches.

• Performing risk analysis to assess and mitigate the impacts of natural hazards comprehensively and proactively.
  ​

As hydrometeorological processes have been increasingly complex, I strive to enhance the robustness, scalability, and utility of my research to address challenges across diverse temporal and spatial scales.