Job description
Summary of the PhD research project
Context and objectives
Accelerated urbanization and the urban heat island effect are increasing thermal stress on populations, a phenomenon exacerbated by climate change (IPCC, 2022). In Southern Europe, where demographic aging heightens vulnerabilities, urban adaptation is becoming a priority. By 2070, cities in southern France could experience more than 30 days of heatwaves annually, with temperatures reaching up to 50 °C.
Urban climate modeling is a fundamental tool for anticipating these impacts and designing effective mitigation strategies. However, existing approaches, which rely on the numerical resolution of equations modeling the dynamics and thermodynamics of atmospheric flows, have limitations: while mesoscale models enable simulation of urban processes on a large scale (Redon et al., 2020), they excessively simplify urban morphology and the effects of vegetation. Conversely, microscale models, which are more precise (Salim et al., 2015; Krc et al., 2021), remain limited by their high computational cost, making their operational application at large scale difficult. In this context, the project aligns with recent research efforts aimed at developing operational models that combine accuracy and computational speed through the integration of machine learning methods (Buizza et al., 2022).
The objective of this PhD project is thus to strengthen the capacity for urban climate simulation at the street scale and to apply these digital tools to the assessment of greening scenarios, using Lyon as a case study. Local authorities have a crucial need for insights into the cooling potential of adaptation strategies based on urban greening. The project addresses scientific questions related to the adaptation of territories to climate change and the development of modeling tools for managing climate risks in urban environments. It aims to develop an optimized operational model, integrating machine learning algorithms and field data, to accurately simulate thermal exposure at the metropolitan scale and to evaluate the most effective mitigation levers.
2. Scientific Challenges
Current urban atmospheric simulations rely on various modeling approaches based on the resolution of fluid dynamics equations (Maronga et al., 2020). To accurately simulate microclimatic conditions, these models must incorporate multiphysics modules that account for radiative exchanges between urban surfaces as well as the evapotranspirative and radiative exchanges of vegetation, which presents a major challenge. Simulating the effects of trees in these models is particularly complex: wind resistance of leaves must be represented by a drag force (Salim et al., 2015), while effects on radiative exchanges are modeled through an attenuation factor in specific algorithms (Krc et al., 2021).
Due to their computational cost, these high-fidelity numerical simulations are limited to small domains and specific meteorological conditions. They are therefore not suitable for real-time simulations or for evaluating greening scenarios at the metropolitan scale. To overcome this limitation, operational models are needed. Designed to be accessible to non-experts, these models must (i) require far fewer computational resources and (ii) provide hourly values for variables such as air temperature, humidity, wind speed, and radiation at street level, capturing the main spatial variations (Di Sabatino et al., 2013). These variables are essential for calculating thermal comfort indices, such as the Universal Thermal Climate Index (UTCI) (Blazejczyk et al., 2012). Achieving this requires simplifying urban geometry and parameterizing urban dynamics, potentially by integrating field data through data assimilation (Nguyen and Soulhac, 2021) or machine learning (Buizza et al., 2022). The parameterization will depend on the model’s intended use—whether for real-time simulations (health risk management), scenario analysis (epidemiological studies), or urban planning optimization. While several operational models exist for air quality (Soulhac et al., 2011) and noise (Gabillet, 1990), very few are dedicated to simulating urban climate at the street scale. To address this, we propose in this PhD project to integrate new Artificial Intelligence (AI) algorithms into the operational model for predicting urban thermal stress, with scientific challenges notably including the integration of modalities of different types and scales as well as the need for data efficiency in model training.
Work context
Institution and Laboratories
This PhD will take place at École Centrale de Lyon, a public institution of scientific, cultural, and professional character (EPCSCP). Centrale Lyon trains generalist engineers, specialized engineers, master’s students, and PhD candidates. The institution hosts nearly 3,000 students and has around 500 staff members, including 200 faculty and research staff. It is distinguished by internationally recognized research, supported by six research laboratories, all of which are CNRS Joint Research Units, combining fundamental and applied activities, particularly through numerous industrial contracts.
Given the interdisciplinary nature of the thesis (Fluid Mechanics / Machine Learning), it will be carried out within two laboratories:
● Fluid Mechanics and Acoustics Laboratory (LMFA), UMR 5509
● Laboratory of Computer Science in Image and Information Systems (LIRIS), UMR 5205
The LMFA develops a continuum of research in fluid mechanics and acoustics, ranging from the understanding and modeling of physical phenomena to applied research in partnership with industry and public organizations.
Research at LIRIS aims to address the challenges of the digital world, particularly those posed by artificial intelligence (AI), big data analysis, computer vision, cybersecurity, digital transformation, and human learning. Part of LIRIS’s activities are at the interface of social sciences, engineering, medicine, life sciences, and environmental sciences.
The supervision of the PhD will be provided by three faculty members :
● Pietro Salizzoni, Full Professor, Centrale Lyon, LMFA, pietro.salizzoni@ec-lyon.fr
● Lionel Soulhac, Full Professor, INSA Lyon, LMFA, lionel.soulhac@insa-lyon.fr.
● Emmanuel Dellandrea, Associate Professor, Centrale Lyon, LIRIS, emmanuel.dellandrea@ec-lyon.fr
Founding of the PhD thesis : Bouquet de thèses 2025
The doctoral thesis described above is part of a series of theses designed to build a multidisciplinary scientific approach to the societal challenge of a "responsible digital society", and more specifically, the specific theme of "Data and AI in a sustainable and responsible approach", identified as a priority issue by the 4 institutions of the Lyon Saint-Etienne Engineering College (Centrale Lyon, ENTPE, INSA Lyon, Mines Saint-Étienne) and by the Université Jean Monnet Saint-Étienne, which are providing financial support for the theses making up this 2025 package.
The 2025 theses package includes 6 theses covering different facets of data science and artificial intelligence, addressing the following questions:
● Monitoring crystallization processes using AI-assisted acoustic emission
● AI-assisted design of biodegradable and/or biosourced biopolymers for the sustainable protection of agricultural crops
● Machine learning methods for urban microclimate prediction
● Data-driven non-linear structure identification
● Inference and explicability in confidential mode: towards self-diagnosis via images
● Towards certification of vibration monitoring with explanatory AI
These theses involve a total of 16 supervisors from 11 laboratories on the Lyon Saint-Etienne site (Centre d'Innovation en Télécommunications et Intégration, Centre SPIN - Génie des Procédés, Ingénierie des Matériaux Polymères, Biologie Fonctionnelle, Insectes et Interactions, Institut Camille Jordan, Laboratoire de Mécanique des Fluides et d'Acoustique, Laboratoire de Tribologie et Dynamique des Systèmes, Laboratoire d'InfoRmatique en Image et Systèmes d'information, Laboratoire Hubert Curien, Laboratoire Vibrations Acoustique, Matériaux : Ingénierie & Science) of which the 5 funding institutions are supervisors. The 6 PhD students recruited under this package will be enrolled in 3 Doctoral Schools on the site: MEGA, EDML, SIS.
The teams (doctoral students and their supervisors) involved in these 6 theses form a multi-disciplinary scientific community: regular exchanges between these teams will take place throughout the 3 years of the doctoral pathway, notably in the form of joint seminars to develop the multi-disciplinary systems approach specific to the bouquet and enrich the teams' disciplinary skills in a spirit of sharing and learning. Thesis papers produced at the end of the doctoral program will also reflect the original positioning of the thesis work within a bouquet, by including a chapter analyzing the impact of the work carried out on the "Data and AI in a sustainable and responsible approach" issue.
References
Blazejczyk, K., et al., International Journal of Biometeorology, 2012, 56, p. 515-535.
Buizza, C. et al., Journal of Computational Science, Volume 58, 2022, 101525.
Di Sabatino, S., Buccolieri, R., Salizzoni, P. , 2013, Int. J. of Env. Poll. 2013 52:3-4, 172-191
Ding, Y. et al., Neurocomputing, Volume 501, 2022, P. 246-257.
Dumas, G., 2021, PhD Thesis, https://dumas.ccsd.cnrs.fr/OMP-TEL/tel-03700032
Gabillet., Y. 1990, Cahier 2444. CSTB.
Grard, M., Dellandréa, E., Chen, L., Int. J. of Computer Vision, 2020, 128(5), pp. 1331–1359.
Krc, P., Geoscientific Model Development, 2021, 14, p. 3095-3120.
Maronga, B. et al., Geoscientific Model Development, 2020, 13, p. 1335-1372.
Masson, V., Boundary-Layer Meteorology, 2000, 94, p. 357-397.
Nguyen C.-V., Soulhac L., 2021, Atmos. Environ., 253, 118366.
Redon, E., et al., Geoscientific Model Development, 2020, 13, p. 385-399.
Ronneberger, et al., 2015, MICCAI, Springer, LNCS, Vol.9351: 234–241.
Salim, M.H. et al., Journal of Wind Engineering and Industrial Aerodynamics, 144, p. 84-95.
Schoetter, R., Masson, V. et al., Geoscientific Model Development, 2020, 13, p. 5609-5643.
Soulhac, L., Salizzoni, P. et al., 2011, Atmos. Environ., 45, 7379-7395.
Job requirements
Position Requirements
Desired Profile
Any candidate holding an engineering degree or a Master’s degree, with an excellent academic record, specialized in Computer Science with strong skills in machine learning and a strong interest in multidisciplinary research, particularly in connection with fluid mechanics.
Recruitment process
Interested candidates, or those seeking more information, are strongly encouraged to get in touch by sending an email containing a CV and a short cover letter (introducing themselves and outlining their motivation) to the supervisory team (see addresses above).
Applications can be submitted until May 27, 2025
The documents to be included in the application are: a CV, Master’s transcripts, and a motivation letter.
or
All done!
Your application has been successfully submitted!