PhD Position: Materials properties Predictions using machine learning and Full-time

About UM6P:

Mohammed VI Polytechnic University (UM6P) is a Moroccan non-profit private research university located in the Green City of Benguerir, with a mission to promote education, training, and teaching, as well as applied research and innovation. UM6P boasts state-of-the-art infrastructure and an extensive academic and research network and is dedicated to economic and human development. The university places research and innovation at the service of the African continent and is committed to providing relevant skills training to advance Morocco and Africa’s innovation ecosystem. UM6P’s unique partnership approach strengthens its position as an avant-garde in these areas, and the university aims to shine nationally, continentally, and internationally as a leading institution for education and research. UM6P offers highly competitive incentives to its current and future talented research staff.

Entity: LIMSET (UM6P)

We are seeking highly motivated and talented PhD student to join our research team at Muhammad VI Polytechnic University (UM6P) to work on exciting thesis title;

Thesis Subject Title : Materials properties Predictions using machine learning and Density Functional Theory

Density Functional Theory (DFT) serves as a potent computational tool extensively applied in physics, chemistry, and materials science to investigate the electronic properties of atoms, molecules, and solids. At its core, DFT aims to predict the properties of a system by considering the electron density rather than individual electron wave functions. This method offers a balance between accuracy and computational efficiency, making it suitable for investigating large and complex systems. In DFT, the total energy of a system is expressed as a functional of the electron density, allowing for the determination of the ground-state properties such as atomic and molecular geometries, electronic energies, and response properties. To tackle more complex scenarios, various approximations and computational packages have been suggested. The associated packages enable the calculation of a wide range of properties, including the electronic properties like density of states and band structures, optical properties such as absorption, conductivity, loss energy function, and reflectivity. Furthermore, DFT extends its applicability to thermodynamic properties like entropy, Debye vibrational energy, and specific heat. Notably, DFT stands as the most relevant theory to address the notorious many-body problem, offering insights into diverse materials and their properties.

The integration of DFT with machine learning presents promising avenues for accelerating electronic structure applications, notably in silico like-material discoveries and the exploration of novel chemical reaction pathways [1]. This synergistic fusion extends its applicability across diverse domains, encompassing Dry Reforming, Steam Reforming, Partial Oxidation, Autothermal Reforming, Gasification, and Methane Pyrolysis [2]. Leveraging machine learning methodologies alongside these processes can effectively mitigate resource constraints and facilitate simulations of expansive systems, thereby assuming a pivotal role in addressing critical scientific and technological challenges. The realization of large-scale electronic structure simulations owes its feasibility to the advent of contemporary, high-performance computational resources [1]. Additionally, by elucidating electronic structure dynamics, novel materials can be engineered to offer substantial optimizations and enhancements, particularly in industrial and multidisciplinary sectors, thereby reshaping material utilization paradigms and performance benchmarks.

The main responsibility of this post will be to carry out independent research on the integration of DFT with machine learning for accelerating engineering applications. The PhD student will be responsible for writing up their work for publication.

Candidate Profile:

– A Master’s degree (or equivalent) in Physics, Mathematics, or a related area.

– Robust knowledge in materials physics, DFT and machine learning.

– Strengths in analytical calculations, numerical methods, interpretation of the results and communication in English