Element selection for crystalline inorganic solid discovery guided by unsupervised machine learning of experimentally explored chemistry

Abstract

The selection of the elements to combine delimits the possible outcomes of synthetic chemistry because it determines the range of compositions and structures, and thus properties, that can arise. For example, in the solid state, the elemental components of a phase field will determine the likelihood of finding a new crystalline material. Researchers make these choices based on their understanding of chemical structure and bonding. Extensive data are available on those element combinations that produce synthetically isolable materials, but it is difficult to assimilate the scale of this information to guide selection from the diversity of potential new chemistries. Here, we show that unsupervised machine learning captures the complex patterns of similarity between element combinations that afford reported crystalline inorganic materials. This model guides prioritisation of quaternary phase fields containing two anions for synthetic exploration to identify lithium solid electrolytes in a collaborative workflow that leads to the discovery of Li3.3SnS3.3Cl0.7. The interstitial site occupancy combination in this defect stuffed wurtzite enables a low-barrier ion transport pathway in hexagonal close-packing.

Element selection for functional materials discovery by integrated machine learning of atomic contributions to properties

“…At the level of the phase fields, relationships between elemental combinations and their synthetic accessibility have been studied with unsupervised machine learning and validated experimentally 12 .…”

“…In parallel to the classification module, a deep AutoEncoder neural network learns patterns of chemical accessibility from the experimentally verified materials data. Similarly to the procedure in 12 , an unsupervised de-noising AutoEncoder learns the patterns of similarity in data while reducing dimensionality of the phase fields representations. The training consists of two parts: encoding into a reduced dimensionality latent space, where phase fields representations are reorganised, so the similar phase fields are aligned, and decoding from the latent representation into the reconstructed images of original vectors.…”

“…This reorganisation via the AutoEncoder enables ranking of the phase fields by their reconstruction errors, that reflect differences of individual entries from general patterns in data. Hence, elemental combinations that are unlikely to manifest conventional bonding chemistry nor to form synthetically accessible compositions exhibit high reconstruction errors 12 . We also find that predicted reconstruction errors converge to their average values when an ensemble of models is trained (See Supplementary Fig.…”

“…This approach relies on the expert selection of a number of exploited chemical characteristics as well as the relevance of these characteristics and the corresponding weights for the atomic descriptions in materials representations. This selection determines the quality of the model 12 . The composition-based models are predisposed to data leakage between training and validation datasets via compositionally close datapoints, that impedes the extrapolation of patterns in materials-properties relationships onto unexplored materials that have distinct chemistries from those in the training set 13 .…”

A Survey of Datasets, Preprocessing, Modeling Mechanisms, and Simulation Tools Based on AI for Material Analysis and Discovery

“…The outcomes suggest that the model tends to accurately predict crystal formation conditions compared to the human methods, irrespective of the structural similarity of the templating amines to known examples in the database. Another study [64] has proposed an unsupervised machine learning model that finds the crucial identical patterns among the merge, allowing reported crystalline inorganic materials. The study suggests prioritizing quaternary phase fields comprising two anions for the sake of synthetic exploration to locate solid lithium electrolytes in a collaborative framework, which results in Li 3.3 SnS 3.3 Cl 0.7 material discovery.…”