My work focuses on developing methodologies that integrate deep neural networks with probabilistic approaches for modeling and prediction in complex dynamical physical systems. A central theme of my research is uncertainty quantification, with the aim of improving the reliability, interpretability, and robustness of predictive models under uncertainty. My research interests include generative modeling, sequential inference methods, and probabilistic machine learning, particularly for scientific applications. By combining data-driven learning with physical modeling and probabilistic reasoning, my work seeks to advance probabilistic approaches for forecasting and state estimation in complex spatio-temporal systems.
