PhD Position: AI-driven Surrogate Approaches for Microstructure-aware Structural Modeling University of Lorraine in France

This PhD position is part of the AMMETIS project (AI-assisted Simulations of Microstructure driven Mechanical properties from high Throughput and multiscale analysis), under the PEPR DIADEM framework, at the University of Lorraine's LEM3 laboratory in Metz, France. The project aims to develop an advanced characterization platform for innovative materials by integrating cutting-edge experimental techniques, physics-based mesoscopic modeling, and artificial intelligence.

The research will focus on leveraging high-throughput experiments and large-scale numerical simulations to generate comprehensive datasets that describe the intricate relationships between microstructure, deformation mechanisms, and mechanical response. While advanced mesoscopic crystal plasticity simulations offer predictive power, their computational cost is high for realistic microstructures and large-scale analyses. This PhD will address this challenge by developing efficient AI-based surrogate models capable of rapidly predicting macroscopic mechanical properties from microstructural descriptors, while preserving the underlying physical mechanisms.

The successful candidate will explore various machine learning strategies, including deep learning architectures such as convolutional neural networks for microstructure image analysis, graph-based representations, and physics-oriented descriptors using rank reduction autoencoders (RRAE) and neural operator approaches. Emphasis will be placed on integrating physics-informed constraints to ensure the robustness, interpretability, and extrapolation capabilities of the models. The resulting surrogate models will enable fast prediction of effective mechanical properties and deformation fields for complex microstructures, bridging mesoscale simulations and structural-scale applications. This will accelerate the exploration of microstructure-property relationships and open new avenues for the design and optimization of advanced structural materials.

The PhD will be conducted primarily at PIMM (Laboratoire Procédés et Ingénierie en Mécanique et Matériaux) in Paris, in collaboration with LEM3 in Metz. The position is fully funded for three years, with a gross monthly salary of approximately €2300. The start date is September 2026 (flexible). Applicants should have a Master’s degree in a relevant field, strong background in continuum mechanics and numerical modeling, experience with machine learning and scientific computing, and proficiency in Python and ML frameworks. Excellent English is required. For more information, visit the project and lab websites or contact Dr. Mohamed Jebahi.

Application deadline: 30 June 2026.