This research focuses on advancing state-of-the-art aerodynamic design 
methodologies to significantly enhance wind energy harvesting in urban settings. 
The primary objective is to develop a high-fidelity CFD–machine learning (CFD-ML) 
framework capable of efficiently analyzing and optimizing the coupled 
interactions among urban wind dynamics, rooftop flow structures, and vertical-
axis wind turbines. With a focus on building-integrated wind energy systems, this 
project aims to push the boundaries of current technology by identifying optimal 
aerodynamic configurations that maximize wind capture efficiency and mitigate 
turbulence under diverse urban layouts and meteorological conditions. To achieve 
this, the project explores machine learning approaches—including surrogate 
modeling, and reinforcement learning—to accelerate CFD optimization and enable 
adaptive control strategies for complex urban wind environments. The ultimate 
goal is to deliver a scalable, high-performance solution that supports continuous 
and efficient decentralized power generation in densely populated areas.

More information about this position and the application procedure can be found 
here:https://www.linkedin.com/feed/update/urn:li:activity:7325783970170736641/