Postdoc on Machine Learning–Enhanced CFD for Wind-Energy Aerodynamic Optimization

Rotterdam School of Management, Erasmus University (RSM); Eindhoven; On-site; EUR 50.000 - 70.000; Full time

Job summary

A leading technical university in the Netherlands is seeking an innovative researcher to develop cutting-edge solutions for aerodynamic design optimization of wind energy systems. The role involves advanced CFD and machine learning methods to enhance urban wind energy harvesting. Ideal candidates should have a strong background in CFD, scientific ML, and wind energy, and are expected to collaborate with industry partners to deliver practical solutions.

Qualifications

• Strong background in CFD, scientific ML, wind energy, and advanced optimization.
• Experience with high-fidelity simulation, surrogate modeling, and reinforcement learning.
• Ability to collaborate with industry partners and academic institutions.

Responsibilities

• Develop a high-fidelity CFD–ML framework for rooftop aerodynamic duct structures.
• Implement surrogate modeling and reinforcement learning for CFD optimization.
• Optimize PowerNEST duct structures for wind capture efficiency.
• Collaborate with industrial partners and contribute to PowerNEST solutions.
• Translate CFD–ML methodologies into practical design strategies.

Skills

CFD

Scientific machine learning

Wind energy

Advanced optimization

Job description

Overview

Are you an innovative researcher with a strong background in CFD, scientific machine learning (ML), wind energy, and advanced optimization? Join our team to develop cutting-edge solutions for aerodynamic design optimization of wind energy systems in complex urban environments.

Information

This research focuses on advancing cutting-edge 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 rooftop aerodynamic duct structures for building-integrated wind energy systems. The aim is 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 advanced machine learning approaches, including surrogate modeling and reinforcement learning, to accelerate CFD optimization and enable adaptive control strategies for complex urban wind conditions. From an industrial standpoint, the objective is to deliver a cost-effective and efficient solution that facilitates continuous decentralized power generation in densely populated urban areas.

The research outcomes are expected to contribute to both fundamental scientific knowledge and practical innovations in renewable energy. In close collaboration with IBIS Power, the project will contribute to the further development of PowerNEST, a modular rooftop system that integrates wind and solar energy. At this stage, the focus is on optimizing the aerodynamic design of the PowerNEST duct structure, which accelerates and guides the airflow toward the integrated turbines. The turbines are represented using simplified actuator models and are not explicitly included in the optimization process. This project will play a key role in translating advanced CFD–ML methodologies into practical design and control strategies, helping unlock the full potential of urban wind energy integration. The selected candidate will be affiliated with Eindhoven University of Technology (TU/e) in the Netherlands, with active engagement in the Eindhoven Institute for Renewable Energy Systems (EIRES) initiatives.

Responsibilities

• Develop a high-fidelity CFD–ML framework to analyze and optimize rooftop aerodynamic duct structures for building-integrated wind energy systems.
• Investigate and implement surrogate modeling and reinforcement learning approaches to accelerate CFD optimization and enable adaptive control strategies for urban wind conditions.
• Optimize the aerodynamic design of PowerNEST duct structures to maximize wind capture efficiency and guide airflow toward integrated turbines.
• Collaborate with industrial partners (e.g., IBIS Power) and contribute to the evolution of PowerNEST towards practical, cost-effective solutions for urban energy systems.
• Translate CFD–ML methodologies into practical design and control strategies for real-world urban wind energy integration.

Qualifications

• Strong background in CFD, scientific ML, wind energy, and advanced optimization.
• Experience with high-fidelity simulation, surrogate modeling, reinforcement learning, and actuator models in wind energy contexts.
• Ability to work collaboratively with industry partners and academic institutions; affiliation with Eindhoven University of Technology (TU/e) and engagement with EIRES is preferred.