Analysis and design of periodic structures using artificial intelligence (M/F)

Job Description

Thesis Subject

Satellite communications and Earth observation systems are facing increasingly stringent perfor-mance requirements driven by the deployment of low Earth orbit (LEO) constellations and the growing need for accurate climate monitoring. These applications rely on advanced electromagnetic (EM) periodic structures, such as polarization converters, metasurfaces, and dichroic devices, to enable low-profile, lightweight, and low-cost hardware solutions that are compatible with mass production and space-borne constraints [1]-[2]. However, the analysis and design of these advanced EM devices involve highly parameterized geometries, strong electromagnetic coupling effects, and stringent performance trade-offs across wide frequency bands and incidence angles. This leads to a heavy reliance on computationally expensive full-wave simulations, resulting in long design cycles and limited exploration of the design space.

In this context, artificial intelligence (AI) emerges as a promising solution [3]-[4]: by learning the complex relationships between structural parameters and EM responses, AI-based methods can drasti-cally reduce computational cost and enable rapid optimization, paving the way for efficient develop-ment of next-generation, low-cost, and high-performance components for space communications and Earth observation systems.

The main objective of this PhD project is to develop advanced methods for the analysis and design of EM periodic structures for polarization control and radiometric applications, by combining EM theory, periodic structures, and AI-based optimization techniques.

[1] M. Ettorre, F. F. Manzillo, M. Casaletti, R. Sauleau, L. Le Coq, and N. Capet, “Continuous transverse stub array for Ka-band applications,” IEEE Trans. Antennas Propag., vol. 63, no. 11, pp. 4792–4800, Nov. 2015.
[2] C. Bilitos, X. Morvan, R. Sauleau, E. Martini, S. Maci and D. González-Ovejero, “Series dual-fed continuous transverse stub array with enhanced multibeam operation enabled by a reflective lune-burg lens,” IEEE Trans. Antennas Propag., vol. 72, no. 11, pp. 8420-8432, Nov. 2024.
[3] A. Massa, G. Oliveri, M. Salucci, N. Anselmi, and P. Rocca, “Learning-by-examples techniques as applied to electromagnetics,” J. Electromag. Waves Appl., vol. 32, no. 4, pp. 516-541, 2018.
[4] M. Li and M. Salucci, Applications of Deep Learning in Electromagnetics: Teaching Maxwell's equations to machines. Scitech Publishing, 2023.

Your Work Environment

This thesis is part of the ongoing collaborative activities between IETR and the French space agency CNES (https://cnes.fr). This interdisciplinary project will be carried out at IETR – UMR CNRS 6164 (http://www.ietr.fr) and it will strongly involve two of IETR's technological platforms:
1) nR (NanoRennes) platform, https://www.ietr.fr/en/nr-nanorennes-platform with experience in microfabrication.
2) M²ARS (Manufacturing Measurement Analysis of Radiating Systems) platform https://www.ietr.fr/en/m2ars-manufacturing-measurement-analysis-radiating-systems-platform, with experience in advanced antenna metrology and prototyping.

The PhD student will conduct a literature review on AI tools and on the analysis and synthesis of peri-odic structures to identify the most suitable AI-based optimization techniques for the design phase. This will be followed by the prototyping and experimental characterization of the resulting components, which will be fabricated and tested using IETR's world-class facilities.

Compensation and benefits

Compensation

2300 € gross monthly

Annual leave and RTT

44 jours

Remote Working practice and compensation

Pratique et indemnisation du TT

Transport

Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€

About the offer

About the CNRS

The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.

CNRS

The research professions