PostDoc position on deep learning accelerated multiscale modeling of flows - CDD 18 month at IMT Nord Europe

Job description

Discipline: Machine learning

Line Manager: Modesar SHAKOOR,

Workplace: Douai, Lahure

Type of contract and duration: Postdoctoral fellowship, 18 months


Public establishment belonging to IMT (Institut Mines-Télécom), placed under the supervision of the Ministry of Economy, Finance and Industrial and Digital Sovereignty, IMT Nord Europe has three main objectives: providing our students with ethically responsible engineering practice enabling them to solve 21st century issues, carrying out our R&D activities leading to outstanding innovations and supporting territorial development through innovation and entrepreneurship. Ideally positioned at the heart of Europe, 1 hour away from Paris, 30 min from Brussels and 1h30 from London, IMT Nord Europe has strong ambitions to become a main actor of the current industrial transitions, digital and environmental, by combining education and research on engineering and digital technologies.

Located on two main campuses dedicated to research and education in Douai and Lille, IMT Nord Europe offers research facilities of almost 20,000m² in the following areas:

-           Digital science,

-              Processes for industry and services,

-              Energy and Environment,

-              Materials and Processes.

For more details, visit the School’s website:

The position is vacant within the Centre for Materials & Processes and the Centre for Digital Systems of IMT Nord Europe.


Flows in porous media are of great interest for a wide range of applications such as reservoir engineering or composites manufacturing. The ANR JCJC MISSA project has started in 2023 and targets the development of cutting-edge numerical models for flows in porous media. One of the main research tracks is the design of neural networks to replace conventional computing paradigms. Recently, technologies such as autoencoders and recurrent neural networks have been considered [1]. For these neural networks to be of interest for the considered applications, two issues should be dealt with:

  • Improving the generalization capabilities by estimating the prediction error and carefully designing the training dataset, for instance using active learning [2] or self-supervised learning [3,4],
  • Ensuring the convexity of the neural network prediction with respect to the input data [5,6].

Within this project involving two research centers of IMT Nord Europe as well as a research group of the National University of Singapore, the postdoctoral fellow will focus on accelerating calculations with deep learning. The postdoctoral fellow will develop a deep learning model that will be integrated in a multiscale finite element code developed by other partners of the MISSA project. Challenging applications to real manufacturing processes will be addressed.

The postdoctoral research will be supervised by Prof. Shakoor, Itier and Mennesson from IMT Nord Europe. Participation in teaching activities is possible up to a limit of 64 hours per school year for postdocs who wish to pursue a career in academia. This position offers:

  • A high-level and exciting international research environment in a renowned institution
  • Being part of an international project team with contacts worldwide
  • A thorough scientific education and training on deep learning and its application to fluid mechanics
  • The possibility to participate in local as well as international workshops and conferences

[1] K. Shinde et al., Dimensionality reduction through convolutional autoencoders for fracture patterns prediction, Applied Mathematical Modelling, 114:94-113, 2023
[2] Y. Gal et al., Deep bayesian active learning with image data, Proceedings of the 34th International Conference on Machine Learning, 70:1183-1192, 2017
[3] M. Caron et al., Emerging properties in self-supervised vision transformers, Proceedings of the IEEE/CVF International Conference on Computer Vision, 9650-9660, 2021
[4] T. Chen et al., A Simple Framework for Contrastive Learning of Visual Representations, Proceedings of the 37th International Conference on Machine Learning, 119:1597-1607, 2020
[5] M. Ławryńczuk, Input convex neural networks in nonlinear predictive control: A multi-model approach, Neurocomputing, 513:273-293, 2022
[6] O. Aslan et al., Convex deep learning via normalized kernels, Advances in Neural Information Processing Systems, 27, 2014

Job requirements


  • A PhD degree in machine learning / data science
  • Strong programming skills, preferably in Python
  • Some skills in computational fluid mechanics will be an advantage but are not a requirement
  • Distinguished her- or himself with publications in peer-reviewed international journals and/or presentations in renowned international conferences
  • Strong knowledge of either French or English


The job is to be filled as to January-July 2024 for a period of 18 months (temporary contract).


For any information on the missions, please contact:

SHAKOOR Modesar, Associate Professor, ; +33 3 27 71 23 21
ITIER Vincent, Associate Professor, ; +33 3 20 43 64 18
MENNESSON José, Associate Professor, ; +33 3 20 43 64 21

For any administrative information, please contact the Human Resources Department:

This job is offered to civil servants on a mobility basis, or on a contractual basis under public law. In addition, the position can be adapted for a disabled person.