My research centers on advancing artificial intelligence and machine learning methodologies for climate prediction, air quality forecasting, and environmental decision-making. I have developed interpretable physics-informed neural networks and transformer-based deep learning models to accurately forecast daily temperature, humidity, wind speed, and particulate matter concentrations, with applications tailored to diverse climatic regions. These models incorporate explainable AI to provide transparency in forecasting, facilitating informed and reliable decisions for environmental management.

By integrating country-level embeddings and leveraging data-driven hybrid approaches, my work enhances the scalability and precision of climate and pollution forecasts, supporting actionable insights for sustainable environmental policies. The ultimate goal is to build advanced computational tools that empower stakeholders in resource-constrained environments to mitigate climate-related health risks and improve public well-being through data-driven interventions.

I have also designed and taught courses in mathematical sciences, artificial intelligence and emerging technologies, have contributed to academic journals as an editor, and actively participated in conferences and scholarly events. As a mentor, I have founded and led several student communities, including Google Developer Group (SMIU), Microsoft Learn Student Community (SMIU), Artificial Intelligence Students’ Club (SMIU) and Notion (SMIU) to foster innovation and leadership.