Physics-Informed Forecasting | Urban Thermal Risk | Edge AI Optimization
Resilient AI for Energy, Climate, and Infrastructure Physics-informed models for sustainable systems — designed to run where they’re needed, even on constrained hardware
I build physics-informed forecasting systems for clean energy, grid reliability, and city-scale thermal-stress early warning. These models operate under edge constraints such as NVIDIA Jetson Nano while still delivering high-fidelity short-horizon forecasts of wind speed, electrical load, and near-surface air temperature under extreme regimes. My peer-reviewed publications include 10+ papers (6 first-author), with state-of-the-art error reductions such as 69.2% lower extreme-condition temperature error in dense urban cores and multi-hour wind predictions that outperform recent deep-learning baselines under strict memory and latency budgets.
Working Toward Global Sustainability Goals
This work supports clean and reliable energy access (SDG 7), sustainable and heat-resilient cities (SDG 11), and climate action and adaptation (SDG 13).
SDG 7 Affordable and Clean Energy
SDG 11 Sustainable Cities and Communities
SDG 13 Climate Action
Current research trends in physics-informed AI for wind forecasting and urban climate resilience · AI / ML for climate change, wind energy, and SDG-aligned collaboration
Publications & Research
Recent work in physics-informed forecasting, urban thermal risk, and embedded deployment.