I am a dedicated atmospheric researcher focused on the application of deep learning in the domain of Meteorology. My expertise lies in employing techniques such as deep learning, nonlinear time series analysis, and graph networks to address the complex nature of the atmosphere. My work encompasses an extensive array of data sources, ranging from re-analysis and satellite radars to meteorological and sensor station networks. Each data set presents its own unique intricacies and challenges. I am adept at adapting and extending the existing state-of-the-art methodologies to derive reliable and insightful results. My research interests are focused on key areas: • Utilizing graph neural networks to precisely quantify the transportation patterns of pollutants. • Investigating the intricate interactions between clouds and aerosols. In my pursuit of scientific excellence, I have undertaken specific projects, including: • Applying deep learning methods to rectify biases in climate data, ensuring accuracy and precision. • Understanding the nature of the tropical cyclones, focus on the translation speed. Through my research, I am committed to developing innovative methods and tools that empower us to predict and comprehend the atmosphere, thereby fostering a deeper understanding of its implications for our world.