Frugal Machine Learning and Density Functional Theory for the Design of Sustainable Catalytic M[...]

Organisation/Company Univ. Lorraine CNRS Research Field Technology » Materials technology Chemistry Physics Researcher Profile Recognised Researcher (R2) Leading Researcher (R4) First Stage Researcher (R1) Established Researcher (R3) Application Deadline 4 Apr 2026 - 22:00 (UTC) Country France Type of Contract Temporary Job Status Full-time Offer Starting Date 1 Oct 2026 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

Scientific Context

The catalytic conversion of carbon dioxide into methanol is widely recognized as a key pathway for carbon valorization and greenhouse gas mitigation. When coupled with renewable hydrogen, this reaction provides a promising route toward sustainable fuel production and long-term decarbonization of the chemical industry.

In recent years, catalysts based on oxide–metal and oxide–intermetallic interfaces have emerged as particularly promising systems, as these interfaces can strongly influence CO₂ activation and methanol selectivity. However, the atomic-scale structure of these interfaces and the mechanisms governing their catalytic activity remain poorly understood. Their structural heterogeneity and chemical complexity make accurate atomistic modeling particularly challenging.(1)

Recent advances in machine learning (ML) approaches offer a powerful framework for modeling complex catalytic materials with near ab initio accuracy while enabling simulations at significantly larger spatial and temporal scales than conventional electronic-structure methods. However, the development of such models typically requires very large training datasets generated from computationally expensive calculations, which represents a major bottleneck for the study of complex catalytic interfaces.

Objectives

The objective of this PhD project is to develop data-efficient machine learning strategies to study CO₂ hydrogenation to methanol catalyzed by oxide–metal interfaces. The work will explore approaches such as transfer learning, machine-learning interaction potentials, and the integration of existing experimental knowledge to reduce the amount of required training data while maintaining high predictive accuracy.

Methods and Techniques :Density Functional Theory,Machine Learning for atomistic modeling

Reference

(1) N. Boulangeot, F. Brix, F. Sur, and É. Gaudry, Hydrogen, Oxygen, and Lead Adsorbates on Al13Co4(100): Accurate Potential Energy Surfaces at Low Computational Cost by Machine Learning and DFT-Based Data, Journal of Chemical Theory and Computation, 2024, 20 (16), 7287–7299.

AApplicant skills: Strong background in chemistry, physical chemistry, materials science, or condensed matter physics. Experience in data science, Python programming, high-performance computing and/or quantum chemistry will be considered an asset. Excellent communication skills are essential, with the ability to work and exchange ideas effectively both orally and in writing. English speaking is required. The application should include a statement of research interest, a CV and Master’s degree transcript.