Machine learning has the potential to accelerate materials discovery by accurately predicting materials properties at a low computational cost. However, the model inputs remain a key stumbling block. Current methods typically use descriptors constructed from knowledge of either the full crystal structure — therefore only applicable to materials with already characterised structures — or structure-agnostic fixed-length representations hand-engineered from the stoichiometry. We develop a machine learning approach that takes only the stoichiometry as input and automatically learns appropriate and systematically improvable descriptors from data. Our key insight is to treat the stoichiometric formula as a dense weighted graph between elements. Compared to the state of the art for structure-agnostic methods, our approach achieves lower errors with less data.

A fundamental challenge in materials science pertains to elucidating the relationship between stoichiometry, stability, structure, and property. Recent advances have shown that machine learning can be used to learn such relationships, allowing the stability and functional properties of materials to be accurately predicted. However, most of these approaches use atomic coordinates as input and are thus bottlenecked by crystal structure identification when investigating previously unidentified materials. Our approach solves this bottleneck by coarse-graining the infinite search space of atomic coordinates into a combinatorially enumerable search space. The key idea is to use Wyckoff representations, coordinate-free sets of symmetry-related positions in a crystal, as the input to a machine learning model. Our model demonstrates exceptionally high precision in finding unknown theoretically stable materials, identifying 1569 materials that lie below the known convex hull of previously calculated materials from just 5675 ab initio calculations. Our approach opens up fundamental advances in computational materials discovery.

A fundamental challenge in materials science pertains to elucidating the relationship between stoichiometry, stability, structure, and property. Recent advances have shown that machine learning can be used to learn such relationships, allowing the stability and functional properties of materials to be accurately predicted. However, most of these approaches use atomic coordinates as input and are thus bottlenecked by crystal structure identification when investigating novel materials. Our approach solves this bottleneck by coarse-graining the infinite search space of atomic coordinates into a combinatorially enumerable search space. The key idea is to use Wyckoff representationscoordinate-free sets of symmetry-related positions in a crystal -as the input to a machine learning model. Our model demonstrates exceptionally high precision in discovering new stable materials, identifying 1,558 materials that lie below the known convex hull of previously calculated materials from just 5,675 ab-initio calculations. Our approach opens up fundamental advances in computational materials discovery.

A key bottleneck for material discovery is synthesis. While significant advances have been made in computational material design, synthesis pathways are still often determined through trial and error. In this work, we develop a method that predicts the major product of solid-state reactions. The main advance presented here is the construction of fixed-length, learned representations of reactions. Precursors are represented as nodes on a “reaction graph”, and message-passing operations between nodes are used to embody the interactions between precursors in the reaction mixture. We show that this deep learning framework not only outperforms baseline methods but also more reliably assesses the uncertainty in its predictions. Moreover, our approach establishes a quantitative metric for inorganic reaction similarity, allowing the user to explain model predictions and retrieve relevant literature sources.

A central challenge for soft matter is determining interaction potentials that give rise to observed condensed phase structures. Here we tackle this problem by combining the power of Deep Learning with the physics of the Ornstein–Zernike equation.