Matthew J. Rosseinsky

Samantha Durdy, Michael Gaultois, Vladimir Gusev et al.

With machine learning being a popular topic in current computational materials science literature, creating representations for compounds has become common place. These representations are rarely compared, as evaluating their performance - and the performance of the algorithms that they are used with - is non-trivial. With many materials datasets containing bias and skew caused by the research process, leave one cluster out cross validation (LOCO-CV) has been introduced as a way of measuring the performance of an algorithm in predicting previously unseen groups of materials. This raises the question of the impact, and control, of the range of cluster sizes on the LOCO-CV measurement outcomes. We present a thorough comparison between composition-based representations, and investigate how kernel approximation functions can be used to better separate data to enhance LOCO-CV applications. We find that domain knowledge does not improve machine learning performance in most tasks tested, with band gap prediction being the notable exception. We also find that the radial basis function improves the linear separability of chemical datasets in all 10 datasets tested and provide a framework for the application of this function in the LOCO-CV process to improve the outcome of LOCO-CV measurements regardless of machine learning algorithm, choice of metric, and choice of compound representation. We recommend kernelised LOCO-CV as a training paradigm for those looking to measure the extrapolatory power of an algorithm on materials data.

Andrij Vasylenko, Federico Ottomano, Christopher M. Collins et al.

Discovering materials with previously unreported crystal frameworks is key to achieving transformative functionality. Generative artificial intelligence offers a scalable means to propose candidate crystal structures, however existing approaches mainly reproduce decorated variants of established motifs rather than uncover new configurations. Here we develop a physics-informed diffusion method, supported by chemically grounded validation protocol, which embeds descriptors of compactness and local environment diversity to balance physical plausibility with structural novelty. Conditioning on these metrics improves generative performance across architectures, increasing the fraction of structures outside 100 most common prototypes up to 67%. When crystal structure prediction (CSP) is seeded with generative structures, most candidates (97%) are reconstructed by CSP, yielding 145 (66%) low-energy frameworks not matching any known prototypes. These results show that while generative models are not substitutes for CSP, their chemically informed, diversity-guided outputs can enhance CSP efficiency, establishing a practical generative-CSP synergy for discovery-oriented exploration of chemical space.

Elena Zamaraeva, Christopher M. Collins, George R. Darling et al.

Geometry optimization of atomic structures is a common and crucial task in computational chemistry and materials design. Following the learning to optimize paradigm, we propose a new multi-agent reinforcement learning method called Multi-Agent Crystal Structure optimization (MACS) to address periodic crystal structure optimization. MACS treats geometry optimization as a partially observable Markov game in which atoms are agents that adjust their positions to collectively discover a stable configuration. We train MACS across various compositions of reported crystalline materials to obtain a policy that successfully optimizes structures from the training compositions as well as structures of larger sizes and unseen compositions, confirming its excellent scalability and zero-shot transferability. We benchmark our approach against a broad range of state-of-the-art optimization methods and demonstrate that MACS optimizes periodic crystal structures significantly faster, with fewer energy calculations, and the lowest failure rate.

Federico Ottomano, John Y. Goulermas, Vladimir Gusev et al.

Machine Learning (ML) has offered innovative perspectives for accelerating the discovery of new functional materials, leveraging the increasing availability of material databases. Despite the promising advances, data-driven methods face constraints imposed by the quantity and quality of available data. Moreover, ML is often employed in tandem with simulated datasets originating from density functional theory (DFT), and assessed through in-sample evaluation schemes. This scenario raises questions about the practical utility of ML in uncovering new and significant material classes for industrial applications. Here, we propose a data-driven framework aimed at accelerating the discovery of new transparent conducting materials (TCMs), an important category of semiconductors with a wide range of applications. To mitigate the shortage of available data, we create and validate unique experimental databases, comprising several examples of existing TCMs. We assess state-of-the-art (SOTA) ML models for property prediction from the stoichiometry alone. We propose a bespoke evaluation scheme to provide empirical evidence on the ability of ML to uncover new, previously unseen materials of interest. We test our approach on a list of 55 compositions containing typical elements of known TCMs. Although our study indicates that ML tends to identify new TCMs compositionally similar to those in the training data, we empirically demonstrate that it can highlight material candidates that may have been previously overlooked, offering a systematic approach to identify materials that are likely to display TCMs characteristics.

Michael Moran, Vladimir V. Gusev, Michael W. Gaultois et al.

The scarcity of property labels remains a key challenge in materials informatics, whereas materials data without property labels are abundant in comparison. By pretraining supervised property prediction models on self-supervised tasks that depend only on the "intrinsic information" available in any Crystallographic Information File (CIF), there is potential to leverage the large amount of crystal data without property labels to improve property prediction results on small datasets. We apply Deep InfoMax as a self-supervised machine learning framework for materials informatics that explicitly maximises the mutual information between a point set (or graph) representation of a crystal and a vector representation suitable for downstream learning. This allows the pretraining of supervised models on large materials datasets without the need for property labels and without requiring the model to reconstruct the crystal from a representation vector. We investigate the benefits of Deep InfoMax pretraining implemented on the Site-Net architecture to improve the performance of downstream property prediction models with small amounts (<10^3) of data, a situation relevant to experimentally measured materials property databases. Using a property label masking methodology, where we perform self-supervised learning on larger supervised datasets and then train supervised models on a small subset of the labels, we isolate Deep InfoMax pretraining from the effects of distributional shift. We demonstrate performance improvements in the contexts of representation learning and transfer learning on the tasks of band gap and formation energy prediction. Having established the effectiveness of Deep InfoMax pretraining in a controlled environment, our findings provide a foundation for extending the approach to address practical challenges in materials informatics.

Samantha Durdy, Michael W. Gaultois, Vladimir Gusev et al.

Clustering is a common task in machine learning, but clusters of unlabelled data can be hard to quantify. The application of clustering algorithms in chemistry is often dependant on material representation. Ascertaining the effects of different representations, clustering algorithms, or data transformations on the resulting clusters is difficult due to the dimensionality of these data. We present a thorough analysis of measures for isotropy of a cluster, including a novel implantation based on an existing derivation. Using fractional anisotropy, a common method used in medical imaging for comparison, we then expand these measures to examine the average isotropy of a set of clusters. A use case for such measures is demonstrated by quantifying the effects of kernel approximation functions on different representations of the Inorganic Crystal Structure Database. Broader applicability of these methods is demonstrated in analysing learnt embedding of the MNIST dataset. Random clusters are explored to examine the differences between isotropy measures presented, and to see how each method scales with the dimensionality. Python implementations of these measures are provided for use by the community.

Andrij Vasylenko, Dmytro Antypov, Vladimir Gusev et al.

Fundamental differences between materials originate from the unique nature of their constituent chemical elements. Before specific differences emerge according to the precise ratios of elements in a given crystal structure, a material can be represented by the set of its constituent chemical elements. By working at the level of the periodic table, assessment of materials at the level of their phase fields reduces the combinatorial complexity to accelerate screening, and circumvents the challenges associated with composition-level approaches such as poor extrapolation within phase fields, and the impossibility of exhaustive sampling. This early stage discrimination combined with evaluation of novelty of phase fields aligns with the outstanding experimental challenge of identifying new areas of chemistry to investigate, by prioritising which elements to combine in a reaction. Here, we demonstrate that phase fields can be assessed with respect to the maximum expected value of a target functional property and ranked according to chemical novelty. We develop and present PhaseSelect, an end-to-end machine learning model that combines the representation, classification, regression and ranking of phase fields. First, PhaseSelect constructs elemental characteristics from the co-occurrence of chemical elements in computationally and experimentally reported materials, then it employs attention mechanisms to learn representation for phase fields and assess their functional performance. At the level of the periodic table, PhaseSelect quantifies the probability of observing a functional property, estimates its value within a phase field and also ranks a phase field novelty, which we demonstrate with significant accuracy for three avenues of materials applications for high-temperature superconductivity, high-temperature magnetism, and targeted bandgap energy.