PIONEER-TOPIC#2025: PhD in Architecture and City:Hybrid AI–Physics Urban Digital Twins for Fast[...]

Universidad de Huelva; España; Presencial; EUR 50.000 - 70.000; Jornada completa

Descripción de la vacante

A leading university in Spain is seeking a PhD candidate for a project on Urban Digital Twins. The role involves developing a hybrid AI-Physics framework to optimize urban microclimate simulations. Candidates should have a Master's degree in Engineering and a strong background in machine learning and urban modeling. This is a full-time position associated with collaborative research in EU cities, starting in March 2026. The application deadline is on November 21, 2025.

Servicios

Research mobility opportunity

Participation in international projects

Formación

• Master's degree in engineering or a related field is required.
• Strong background in AI and machine learning is essential.
• Experience with urban climate modeling is preferred.

Responsabilidades

• Develop a hybrid urban microclimate simulation framework.
• Generate datasets using physical simulations and measurements.
• Train AI models to approximate microclimatic results.

Conocimientos

Machine learning

Computational Fluid Dynamics (CFD)

Project management

Data analysis

Educación

Master Degree or equivalent

Herramientas

UME-P

ENVI-met

Descripción del empleo

Organisation/Company Universidad de Huelva Department Human Resources Research Field Engineering » Mechanical engineering Researcher Profile First Stage Researcher (R1) Positions PhD Positions Country Spain Application Deadline 21 Nov 2025 - 23:59 (Europe/Madrid) Type of Contract Temporary Job Status Full-time Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

• Introduction andcontext

In recent years, climate change, urban densification, and the population's increasing exposure to extreme phenomena (heat waves, urban heat islands) have placed the need to design healthier, more resilient, and more comfortable outdoor environments at the center of urban research. Thermal comfort in open urban spaces not only affects the health and well-being of citizens, but also conditions the social and economic use of squares, streets, and parks in European Union (UE) cities.

Currently, microclimate simulation tools are based on high-fidelity physical models such as Computational Fluid Dynamics (CFD) or models such as UMEP and ENVI-met, capable of reproducing thermal behavior in complex urban environments. However, these models have high computational costs and long simulation times, which makes them difficult to use in iterative design processes or in real-time decision-making contexts [1][2].

At the same time, the emergence of artificial intelligence (AI) in urban analysis opens up new possibilities. Machine learning and deep learning models allow predictions to be accelerated, but they often lack generalization and robustness when applied to diverse urban geometries or changing climatic conditions [3].

There is, therefore, a methodological gap: physical models are accurate but slow; AI models are fast but unreliable. The lack of integration of both approaches limits the development of Urban Digital Twins (UDTs) capable of assisting architectural and urban design in real time.

This project proposes a hybrid AI–Physics framework for urban Digital Twins, combining physical reference simulations with experimental datasets at several scales with AI models trained under physical constraints. The goal is to achieve fast and accurate predictions of the urban microclimate, directly applicable to the design of outdoor spaces in EU cities. A particular focus will be placed on the role of low-carbon and bio- based building materials, especially those enhancing evapotranspiration processes, in order to couple digital simulations with sustainable construction practices.

• Thesis content
• General objective

To develop a hybrid urban microclimate simulation framework, integrating physical models and artificial intelligence algorithms within an Urban Digital Twin, in order to optimize architectural and urban design to improve thermal comfort in EU cities.

• Specific objectives
• Generate a reference dataset using high-fidelity physical simulations (CFD, UMEP,ENVI-met) and in-situ measurements.
• Develop and train AI models capable of approximating microclimatic results with high speed andaccuracy.
• Implement a Physics-Informed Machine Learning (PINNs) approach that combines physical constraints with machine learning.
• Integrate the hybrid model into an operational Urban Digital Twinthat allows for visualization and interactivesimulation.
• Validate the system in EU case studies, evaluating its applicability in urban designdecisions.

Assess the contribution of material properties (e.g., permeability, porosity, emissivity, evapotranspiration capacity) to outdoor thermal comfort, in connection with sustainable low-carbon design strategies.

• References
• Blocken B. (2015). Computational Fluid Dynamics for urban physics: Importance, scales, possibilities, limitations and ten tips and tricks towards accurate and reliable simulations. Building and Environment, 91,219–245.
• Middel A., Lukasczyk J., Maciejewski R. (2017). Sky view factors from synthetic fisheye photos for thermal comfort modeling. Urban Climate, 20,251–267.
• Chen Y.,Hong T.,Piette M.A. (2017). Automatic generation and simulation of urban building energy models. Energy and Buildings, 134,31–40.
• Fabbri K., Zuppiroli M., Ambrogio K. (2020). Urban microclimate and outdoor thermal comfort: A critical review of design approaches and methods. Sustainable Cities and Society, 60,102274.

Where to apply

E-mail [e-mail]

Requirements

Research Field Engineering » Mechanical engineering Education Level Master Degree or equivalent

Additional Information

Selection process

This thesis will take place under the PIONEER+ project a European University Alliance, where UUH is one of its members.

UHU securres funding for 1 PhD thesis linked to the SDG11.

Candidadtes pre-selected by the thesis supervisors will be invited to participate in the public call EPIT 2026 organised by the Vice-rectorate of Research & Strategic Planning of University of Huelva, for the funding.

The PhD contract will start in March 2026.

Additional comments

As part of the European Exchange with PIONEER+ ALLIANCE, the scientific collaboration includes a 6 months of research mobility ar university of Gustave Eiffel to achieve the desened research objetives.

This program is designed for researchers seeking to broaden their academic horizons and to foster international collaboration.