Automatic identification of crystal structures and interfaces via artificial-intelligence-based electron microscopy

Characterizing crystal structures and interfaces down to the atomic level is an important step for designing advanced materials.Modern electron microscopy routinely achieves atomic resolution and is capable to resolve complex arrangements of atoms with picometer precision.Here,we present AI-STEM,an automatic,artificial-intelligence based method,for accurately identifying key characteristics from atomic-resolution scanning transmission electron microscopy(STEM)images of polycrystalline materials.The method is based on a Bayesian convolutional neural network(BNN)that is trained only on simulated images.AI-STEM automatically and accurately identifies crystal structure,lattice orientation,and location of interface regions in synthetic and experimental images.The model is trained on cubic and hexagonal crystal structures,yielding classifications and uncertainty estimates,while no explicit information on structural patterns at the interfaces is included during training.This work combines principles from probabilistic modeling,deep learning,and information theory,enabling automatic analysis of experimental,atomic-resolution images.

The NOMAD Artificial-Intelligence Toolkit:turning materials-science data into knowledge and understanding

We present the Novel-Materials-Discovery(NOMAD)Artificial-Intelligence(AI)Toolkit,a web-browser-based infrastructure for the interactive AI-based analysis of materials-science findable,accessible,interoperable,and reusable(FAIR)data.The AI Toolkit readily operates on the FAIR data stored in the central server of the NOMAD Archive,the largest database of materials-science data worldwide,as well as locally stored,users’owned data.The NOMAD Oasis,a local,stand-alone server can be also used to run the AI Toolkit.By using Jupyter notebooks that run in a web-browser,the NOMAD data can be queried and accessed;data mining,machine learning,and other AI techniques can be then applied to analyze them.This infrastructure brings the concept of reproducibility in materials science to the next level,by allowing researchers to share not only the data contributing to their scientific publications,but also all the developed methods and analytics tools.Besides reproducing published results,users of the NOMAD AI toolkit can modify the Jupyter notebooks toward their own research work.

Accelerating materials-space exploration for thermal insulators by mapping materials properties via artificial intelligence

Reliable artificial-intelligence models have the potential to accelerate the discovery of materials with optimal properties for various applications,including superconductivity,catalysis,and thermoelectricity.Advancements in this field are often hindered by the scarcity and quality of available data and the significant effort required to acquire new data.For such applications,reliable surrogate models that help guide materials space exploration using easily accessible materials properties are urgently needed.Here,we present a general,data-driven framework that provides quantitative predictions as well as qualitative rules for steering data creation for all datasets via a combination of symbolic regression and sensitivity analysis.We demonstrate the power of the framework by generating an accurate analytic model for the lattice thermal conductivity using only 75 experimentally measured values.By extracting the most influential material properties from this model,we are then able to hierarchically screen 732 materials and find 80 ultra-insulating materials.

Numerical quality control for DFT-based materials databases

Electronic-structure theory is a strong pillar of materials science.Many different computer codes that employ different approaches are used by the community to solve various scientific problems.Still,the precision of different packages has only been scrutinized thoroughly not long ago,focusing on a specific task,namely selecting a popular density functional,and using unusually high,extremely precise numerical settings for investigating 71 monoatomic crystals^(1).Little is known,however,about method- and code-specific uncertainties that arise under numerical settings that are commonly used in practice.We shed light on this issue by investigating the deviations in total and relative energies as a function of computational parameters.Using typical settings for basis sets and k-grids,we compare results for 71 elemental^(1) and 63 binary solids obtained by three different electronic-structure codes that employ fundamentally different strategies.On the basis of the observed trends,we propose a simple,analytical model for the estimation of the errors associated with the basis-set incompleteness.We cross-validate this model using ternary systems obtained from the Novel Materials Discovery (NOMAD) Repository and discuss how our approach enables the comparison of the heterogeneous data present in computational materials databases.