No abstract

Machine learning (ML) is rapidly revolutionizing many fields and is starting to change landscapes for physics and chemistry. With its ability to solve complex tasks autonomously, ML is being exploited as a radically new way to help find material correlations, understand materials chemistry, and accelerate the discovery of materials. Here, an in‐depth review of the application of ML to energy materials, including rechargeable alkali‐ion batteries, photovoltaics, catalysts, thermoelectrics, piezoelectrics, and superconductors, is presented. A conceptual framework is first provided for ML in materials science, with a broad overview of different ML techniques as well as best practices. This is followed by a critical discussion of how ML is applied in energy materials. This review is concluded with the perspectives on major challenges and opportunities in this exciting field.

Deep learning (DL) is one of the fastest-growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allows analysis of unstructured data and automated identification of features. The recent development of large materials databases has fueled the application of DL methods in atomistic prediction in particular. In contrast, advances in image and spectral data have largely leveraged synthetic data enabled by high-quality forward models as well as by generative unsupervised DL methods. In this article, we present a high-level overview of deep learning methods followed by a detailed discussion of recent developments of deep learning in atomistic simulation, materials imaging, spectral analysis, and natural language processing. For each modality we discuss applications involving both theoretical and experimental data, typical modeling approaches with their strengths and limitations, and relevant publicly available software and datasets. We conclude the review with a discussion of recent cross-cutting work related to uncertainty quantification in this field and a brief perspective on limitations, challenges, and potential growth areas for DL methods in materials science.

No abstract

Predicting the stability of crystals is one of the central problems in materials science. Today, density functional theory (DFT) calculations remain comparatively expensive and scale poorly with system size. Here we show that deep neural networks utilizing just two descriptors—the Pauling electronegativity and ionic radii—can predict the DFT formation energies of C3A2D3O12 garnets and ABO3 perovskites with low mean absolute errors (MAEs) of 7–10 meV atom−1 and 20–34 meV atom−1, respectively, well within the limits of DFT accuracy. Further extension to mixed garnets and perovskites with little loss in accuracy can be achieved using a binary encoding scheme, addressing a critical gap in the extension of machine-learning models from fixed stoichiometry crystals to infinite universe of mixed-species crystals. Finally, we demonstrate the potential of these models to rapidly transverse vast chemical spaces to accurately identify stable compositions, accelerating the discovery of novel materials with potentially superior properties.

No abstract

No abstract

Understanding Li diffusion in solid conductors is essential for the next generation Li batteries. Here we show that density-based clustering of the trajectories computed using molecular dynamics simulations helps elucidate the Li diffusion mechanism within the Li7La3Zr2O12 (LLZO) crystal lattice. This unsupervised learning method recognizes lattice sites, is able to give the site type, and can identify Li hopping events. Results show that, while the cubic LLZO has a much higher hopping rate compared to its tetragonal counterpart, most of the Li hops in the cubic LLZO do not contribute to the diffusivity due to the dominance of back-and-forth type jumps. The hopping analysis and local Li configuration statistics give evidence that Li diffusivity in cubic LLZO is limited by the low vacancy concentration. The hopping statistics also shows uncorrelated Poisson-like diffusion for Li in the cubic LLZO, and correlated diffusion for Li in the tetragonal LLZO in the temporal scale. Further analysis of the spatio-temporal correlation using site-to-site mutual information confirms the weak site dependence of Li diffusion in the cubic LLZO as the origin for the uncorrelated diffusion. This work puts forward a perspective on combining machine learning and information theory to interpret results of molecular dynamics simulations.