Frugal Machine Learning and Density Functional Theory for the Design of Sustainable Catalytic Materials

Univ. Lorraine CNRS; Nancy; On-site; EUR 20,000 - 26,000; Full time

Job summary

Université de Lorraine invites applications for a PhD project focused on Frugal Machine Learning and Density Functional Theory for sustainable catalytic materials. The study is based in Nancy (Grand Est, France) and combines CO2 hydrogenation modeling and advanced ML approaches to reduce data needs while maintaining accuracy.

The project explores transfer learning and machine-learning interaction potentials, collaborating with IJL and LORIA, with an international network including Jožef Stefan

Qualifications

• Strong background in chemistry, physical chemistry, materials science, or condensed matter physics.
• Experience in data science and Python programming is desirable.
• Excellent communication skills in English, both written and spoken.

Skills

Chemistry background

Data science

Python

High-performance computing

Quantum chemistry

English communication

Education

PhD in chemistry, materials science, or physics

Tools

Python

DFT/quantum chemistry packages

Job description

Frugal Machine Learning and Density Functional Theory for the Design of Sustainable Catalytic Materials

09/10/2026 Contrat doctoral

Nancy - Grand Est - France

Frugal Machine Learning and Density Functional Theory for the Design of Sustainable Catalytic Materials

density functional theory, machine learning, materials science

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.

The Université de Lorraine is a leading multidisciplinary university in France, renowned for the quality of its research and its strong ties to national and international scientific networks. It brings together numerous laboratories of excellence, including the Jean Lamour Institute (IJL) and LORIA (Lorraine Laboratory for Research in Computer Science and its Applications). The IJL is one of the largest European laboratories in materials science and engineering, covering a broad spectrum of topics ranging from materials physics to their development and characterization. LORIA, for its part, is a leading laboratory in computer science, particularly in the fields of artificial intelligence, algorithms, robotics, and data science. The collaboration between the IJL and LORIA offers a particularly stimulating interdisciplinary research environment at the interface between materials science and advanced computer science, and provides an ideal framework for developing innovative research projects within the context of a doctoral thesis.

As part of this PhD project, the research is embedded in a dynamic and well-structured scientific environment at both the national and international levels. In France, the project is connected to major research networks such as the GDR IA-MAT and the PEPR DIADEM community, which promote interdisciplinary collaborations at the interface between materials science, artificial intelligence, and data science. Internationally, the work also benefits from active collaborations, notably through a joint associated laboratory with the Jožef Stefan Institute in Slovenia and participation in the European ECMetAC network dedicated to metallic alloys. This ecosystem provides the PhD candidate with a rich research environment that encourages collaboration, knowledge exchange, and strong connections with leading experts in materials science.

A Applicant 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.