Research Scientist

...


Hi, I'm Andrij Vasylenko.

I am a Research Associate at the Department of Chemistry, University of Liverpool.
My mission is to explore the relationships between atoms, material composition, structure and properties. By uncovering these connections using physics- and data-informed computational approaches, I aim to accelerate the real-world discovery of functional materials to address critical technological and societal challenges, such as sustainable energy solutions.
My research ideas were also influenced by collaborations with physicists and chemists from the Universities of Warwick and Cambridge during my tenure as a Research Fellow from 2015 to 2018, and by my Maria Curie Action Scholarship at Adam Mickiewicz University, where I pursued my PhD in Physics from 2013 to 2015.

...

AI for Materials

Learning atoms and their combinations from historical data offers understanding of what chemical elements can be combined for synthesis and function. To link elemental combinations with synthetical accessiblity and functional properties I have developed a variational autoencoder model for unsupervised learning of these patterns in chemical data. Further, I built Bayesian optimisation algorithm accelerating detailed exploration of the material compositional space in combination with crystal structure prediction. In collaboration with experimentalists, these endeavours have lead to a number of discoveries of new functional materials.
G. Han, A. Vasylenko et. al, Science 383, 6684 (2024)
A. Vasylenko et. al, The Journal of Chemical Physics 160, 5 (2024)
A. Vasylenko et. al, npj Computational Materials 9, 164 (2023)
A. Vasylenko et. al, Nature Communications 12, 5561 (2021)

...

Quantum Mechanics for Materials

Quanum mechanics (QM)-based methods, such as density-functional theory (DFT) and beyond-DFT, remain the standard of accuracy in computational studies of materials at the atomic scale. While developing novel, computationally inexpensive algorithmic alternatives, including through generation and machine learning of synthetic data, I utilize presently indispensible QM-based methods to study materials properties with experimental validation. These include thermodynamic and chemical stability, crystal structure prediction, electronic structure and transport, etc.
A. Pshyk, A. Vasylenko et. al, Materials & Design 219 (2022)
G. Han, A. Vasylenko et. al, JACS 143, 18216 (2021)
A. Vasylenko et. al, ACS Nano 12, 6023 (2018)
A. Vasylenko et. al, Phys. Rev B 95, 121408(R) (2017)

Software and Tools

Computational tools that I develop find their application in the fields far beyond Materials Science: E.g., in detection of anomalies and outliers in data, in general, as a part of the pyod library

For the full list of projects and for collaboration,
check out these resources and please get in touch