Development and evaluation of physics-informed machine learning approachs for CO2 capture modeling

This PhD position deals with Physics Informed Machine Learning (PIML) modeling methodologies, a novel generation of deep-learning architectures that combines physical laws with data-driven approaches. Their promise is to be more interpretable, more robust when facing outliers, and to lead to a more physical behavior than their pure-machine-learning counterparts.     
The application case is post-combustion carbon capture, a process of major importance to tackle hard-to-abate greenhouse gas emissions of some key industrial sectors. The absorption column of this type of unit is modeled using a rigorous description of the physical mechanisms responsible for the transfer of acid gas to the liquid solvent. Nonetheless, this model fails to predict some experimental tendencies observed on industrial units, and these discrepancies cannot be explained by a specific phenomenon. 
In this context, the objective of this PhD is to use hybrid modeling approaches to improve the precision of the absorption column description. After a state-of-the-art review, several coupling strategies between the mechanistic model and machine learning algorithms will be investigated. They will be evaluated based on criteria such as accuracy, sensitivity to the amount and quality of data, and extrapolability to operating conditions different to the ones considered during training.  

Keywords: physics-informed machine learning, reactor modelling, CO2 capture.

• Academic supervisor    Prof. Marc SEBBAN, LabHC, ORCID : 0000-0001-6851-169X
• Doctoral School    ED 488 SIS, Université de Lyon
• IFPEN supervisor    Dr. Pierre BACHAUD, pierre.bachaud@ifpen.fr, ORCID : 0000-0003-4128-1016
• PhD location    IFPEN, Lyon, France 
• Duration and start date    3 years, starting in the fourth quarter 2025
• Employer    IFPEN
• Academic requirements    University Master degree in Applied Mathematics / Informatics or Chemical Engineering with a special inclination towards numerical simulation.     
• Language requirements    English level B2 (CEFR)
• Other requirements    Affinity for development of digital tools. Knowledge of a computer language.  

To apply, please send your cover letter and CV to the IFPEN supervisor indicated here below.