Staff

(Forecasting, Reinforcement Learning, Explainable AI, Net-Zero Energy)

A) AI-driven forecasting and control for energy systems
My research focuses on developing data-driven and physics-informed AI models for multi-horizon forecasting and control in renewable and building energy systems. I work on deep learning and reinforcement learning frameworks to improve prediction accuracy, robustness, and decision-making performance. I also emphasize interpretability (e.g., post-hoc explanations) to enhance transparency and practical deployment. These methods are validated using real-world energy datasets and operational systems.

B) Sustainable AI and data-center energy/water/carbon analytics
I also study the environmental footprint of AI and data centers by quantifying electricity use, water consumption, and carbon emissions under different technology and efficiency scenarios. By combining global datasets with scenario modeling, my goal is to identify high-impact pathways for reducing emissions and improving resource efficiency. This work aims to support evidence-based policy and technology strategies toward net-zero targets.