Research Fellow (Hybrid AI + Physics-Based Urban Modeling)

• Develop and calibrate urban building energy models using physics-based simulation tools
• Integrate AI and machine learning methods (e.g., surrogate modelling, generative design) to enhance simulation efficiency and scalability.

• Estimate both operational and embodied carbon emissions at building and district scales.
• Incorporate various dataset

• Compile, clean, and manage multi-source datasets (geospatial, climate, building archetypes, construction materials, energy use).
• Develop reproducible workflows for integrating physics-based and AI-driven approaches.

• Publish findings in high-impact peer-reviewed journals and present at international conferences.
• Contribute to policy briefs, technical reports, and outreach materials for industry and government stakeholders.

• Coordinate with project partners, government agencies, and industry stakeholders, including organising and participating in meetings, workshops, and knowledge-sharing sessions.

• PhD in Architecture, Building Science, Mechanical Engineering, Environmental, Urban Planning, Data Science, or related fields.

• Some experience in lifecycle analysis or carbon modelling, physics-based building energy modelling and/or urban building energy modelling (UBEM).

• Strong programming skills (e.g., Python) for simulation automation, data analysis, and AI/ML workflows.

• Experience with life-cycle carbon assessment methods and tools.

• Demonstrated track record of research excellence through publications and conference presentations.

• Familiarity with GIS tools and spatial data processing.

• Knowledge of urban sustainability, energy policy, and decarbonisation strategies.

• Ability to work in an interdisciplinary team and engage with external stakeholders.

National University of Singapore