My research lies at the intersection of artificial intelligence, spatiotemporal data mining, and sustainability science. I focus on developing scalable, interpretable, and sample-efficient AI methods to tackle real-world challenges in energy, infrastructure, mobility, and environmental systems.

Key areas of interest include:
• Graph-based and geometric deep learning for modeling complex networks in transport and energy systems
• Uncertainty-aware and data-centric machine learning for geo-risk assessment and decision support
• Spatiotemporal analytics across urban traffic safety, maritime logistics, and environmental monitoring
• AI for climate infrastructure, with a current focus on global scaling of carbon capture and storage (CCS/CCUS)
• Cross-domain transferability of AI methods from urban to subsurface systems, enabling robust, multi-sector sustainability solutions

My work is grounded in real-world deployment and interdisciplinary collaboration, bridging data science with geospatial, engineering, and policy domains.