Research highlights

Li-ion conductivity of a material determines its applicability in battery technologies. We aggregate reported experimental data on Li-ion conductors into a new database and present a machine learning (ML) model that can predict ionic conductivity for novel candidate materials.

I have been working on the automation of the workflows for discovery of novel materials and developing machine learning tools that assist human experts in decision-making in the workflows. Here, I highlight the selected publications and software, which is provided with permissive licenses. Please feel free to use these tools in your research; the appropriate citations would be greatly appreciated.

The first decision in the materials discovery workflow that chemists have to make is what chemical elements to combine that would result in a new functional material. The number of possible combinations is huge: the exhaustive exploration would take a lifetime of several generations of scientists.
I have developed a Variational Autoencoder-based model that ranks the candidates by their synthetic accessibility. Synthetic focus on the top-ranked candidates has led to the discovery of a number of new materials.

Selection of chemical elements can depend on the desired functional properties of the resulting materials. I have developed the PhaseSelect model that learns the contribution of different chemical elements to functional properties of materials (e.g., superconductivity, magnetism or energy band gap) and employs this knowledge to represent combinations of elements and predict their properties values. PhaseSelects can assess the functional performance of candidate materials at the early stage of materials discovery and reduces the search space by several orders of magnitude.

Element selection for materials discovery

Elements contribution and embedding for function

Any selected set of chemical elements represents a vast field of possible compositions - chemical formulae. For the discovery, the objective is a formula that stands for synthetically accessible material. An exhaustive investigation is impossible, and I have proposed an algorithm that employs Bayesian optimisation and discovers stable materials up to 100% faster than random sampling.

Bayesian optimisation of the search for stable materials

Machine learning model for ionic conductivity

Scalable outlier detection

Outliers may be present in any data - these are the data points that deviate significantly from the majority in a dataset. They can arise due to various reasons such as measurement errors, experimental anomalies, or genuine rare events. Outlier detection is important because these data points can distort statistical analysis leading to inaccurate results. I have implemented a Variational Autoencoder (VAE) to tackle this problem by learning a probabilistic representation of the data. By modeling the underlying distribution of the data, VAE can identify outliers as data points with low probability under the learned distribution, helping to detect and handle them effectively. This method is a part of the library for the outliers detection.

Yao, Zain Nasrullah, Zheng Li

Yue Zhao et. al., PyOD: A python toolbox for scalable outlier detection, J. Mach. Learn. Res. 20, 1-7, 2019

Increased electrochemical stability in extended ultraphosphate frameworks

Multi-element metal alloys can maintain their stability by evenly distributing hundreds of atoms in a crystal structure in a non-equilibrium dynamic growth. Ceramics of such high-entropy alloys can produce extremely hard materials even in a thin film. In this work, we demonstrate that the mechanical properties of these materials can be fine-tuned by deviations from the equimolar composition.

I have been applying computational techniques to model materials and calculate their properties from first principles. Here, I highlight the selected publications, in which the routes to enhance materials' properties are identified by computational modelling, complemented or validated by experiment.

Materials modelling

Hardness design in high-entropy thin film alloys

Thermoelectric peak in extreme confinement

This works presents the discovery of two new lithium ultraphosphates. Extended layered structure of Li3P5O14 enables three-dimensional lithium migration that affords the highest ionic conductivity in comparison to commercialized analogous. Both new lithium ultraphosphates are computationally predicted to have high thermodynamic stability against oxidation and offer a new route to optimize the interplay of conductivity and electrochemical stability required, for example, in cathode coatings for lithium-ion batteries.

Boosting electronic transport in carbon nanotubes

Functional properties of materials can be modified by controlling materials' structure. We demonstrate how the structure of the smallest possible nano-materials evolves in the increasing volume of confinement, and how this relationship can be employed to control the materials' properties. In particular, extraordinarily high values of thermoelectric figure of merit can be achieved in SnTe, when its crystal is forced to adopt a structure of a 1-D nanowire.

In this work, I theorise that the major cause of electrical resistance in metallic carbon nanotubes - atomic vibrations (phonons) - can be battled by providing an additional channel for their decay, for example by encapsulated nanowires. In 2022, my conclusions were supported by experimental evidence in Z. Hu et. al, "Zigzag HgTe Nanowires Modify the Electron–Phonon Interaction in Chirality-Refined Single-Walled Carbon Nanotubes", ACS Nano 16, 4 (2022).

Tailoring electronic properties in ZnO-polyacrylonitrile nanofibers

Computationally, I demonstrate that electronic properties, such as work function in nano-grained materials depend on the curvature of the grain surface; this relationship offers a route for electronic properties control. These findings are in good agreement with experimental observations of the synthesizes ZnO-polyacrylonitrile nanofibers.