PhD in Materials Science and AI (M/F)

Job Description

Thesis Subject

High-throughput X-ray diffraction data analysis with deep-learning algorithms

Current Artificial Intelligence (AI) is constrained by the Von Neumann bottleneck, where the separation of processing and memory units leads to massive energy inefficiency. The SYNEART project aims to address this issue by leveraging the physics of relaxor ferroelectric thin films to produce neuromorphic devices. As compared to conventional ferroelectrics, relaxor ferroelectrics are characterized by polar nanoregions and a "flat" energy landscape, which allows them to experience multiple stable states, making them ideal candidates for building artificial synapses and neurons with much lower power consumption than traditional CMOS technology. To accelerate the discovery of optimal "composition/thickness/electrode" combinations, the project utilizes high-throughput synthesis (Combinatorial Pulsed Laser Deposition - CPLD) and AI-assisted characterization.

Objectives
The PhD student will specifically contribute to AI-accelerated high-throughput characterization and analysis. The primary objectives are:
- high-throughput XRD analysis: microbeam X-ray diffraction (XRD) will be performed on compositional libraries synthesized by CPLD, with a special interest for 2D and 3D reciprocal space maps (RSMs), recorded in several geometries. Efficient data handling workflows will be developed.
- deep learning implementation: a central challenge is the massive volume of data generated that poses a challenge to conventional analysis methods. The objective is to develop and implement deep neural networks to automate data analysis, enabling fast recognition of phases, symmetry (polar/non-polar, cubic, etc.), and lattice parameters.
The recruited student will be able to draw on the expertise of IRCER and GREMAN in the field of thin film growth and characterization [1, 2] and advanced XRD data analysis, including the development of deep learning algorithms [3, 4].

Profile of the applicant
Education: a Master's degree (or equivalent) in Materials Science, Solid State Physics, Crystallography, or Applied Mathematics/Data Science with a strong interest in physical applications.
Technical expertise: proficiency in programming for data handling and scientific computing.
Soft skills: ability to work in a highly interdisciplinary environment. Good communication skills for collaborating across the project's various research units (SPMS, IRCER, GREMAN, LPMC). A good command of the English language is required, both written and oral.

References
[1] C. Daumont, Q. Simon, S. Payan, P. Gardes, P. Poveda, M. Maglione, B. Negulescu, N. Jaber, J. Wolfman, “Tunability Investigation in the BaTiO3 -CaTiO3 -BaZrO3 Phase Diagram Using a Refined Combinatorial Thin Film Approach”, Coatings 11, 1082 (2021).
[2] Nadaud, G. F. Nataf, N. Jaber, B. Negulescu, F. Giovannelli, P. Andreazza, P. Birnal, J. Wolfman “Enhancement of piezoelectric properties in a narrow cerium doping range of Ba(1–x)CaxTi(1–y)ZryO3 evidenced by high throughput experiment”, ACS Applied Electronic Materials 6, 7392 (2024).
[3] A. Boulle, A. Debelle, “Convolutional neural network analysis of x-ray diffraction data: strain profile retrieval in ion beam modified materials”, Machine Learning: Science and Technology 4, 015002 (2023). https://doi.org/10.1088/2632-2153/acab4c
[4] A. Souesme, R. Guinebretière, O. Castelnau, A. Boulle, “High-throughput determination of crystallite size and microstrain from X-ray diffraction data with deep neural networks”, Machine Learning: Science and Technology (2026). https://doi.org/10.1088/2632-2153/ae55f9

Your Work Environment

This PhD position is offered within the framework of the SYNEART project, a multi-partner initiative funded under the France 2030 investment plan and the PEPR DIADEM exploratory program. The position is available within the Multiscale Structural Organisation of Materials team at IRCER (Ceramics Research Institute – Limoges, France), working in close collaboration with GREMAN (Materials, Microelectronics, Acoustics and Nanotechnologies – Tours, France). IRCER has recognised expertise in crystallography and materials analysis using X-ray diffraction, as well as in the development of data processing algorithms, including deep neural networks. The successful candidate will join this team and will have access to X-ray diffraction facilities and high-performance computing resources.

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