Search for: All records

Abstract Machine learning models are susceptible to being misled by biases in training data that emphasize incidental correlations over the intended learning task. In this study, we demonstrate the impact of data bias on the performance of a machine learning model designed to predict the likelihood of synthesizability of crystal compounds. The model performs a binary classification on labeled crystal samples. Despite using the same architecture for the machine learning model, we showcase how the model’s learning and prediction behavior differs once trained on distinct data. We use two data sets for illustration: a mixed-source data set that integrates experimental and computational crystal samples and a single-source data set consisting of data exclusively from one computational database. We present simple procedures to detect data bias and to evaluate its effect on the model’s performance and generalization. This study reveals how inconsistent, unbalanced data can propagate bias, undermining real-world applicability even for advanced machine learning techniques. 

Thermal radiation emission poses a challenge for using most existing ceramics for thermal environmental barrier coatings of gas-turbine engines operating at temperatures approaching 1500 °C and beyond. This study presents a strategy for photon transport mitigation in fully dense ceramic composites by increasing the refractive index mismatch between the matrix and particle oxides. We investigate this strategy by analyzing radiative properties in 118 different rare-earth pyrosilicate–pyrochlore ceramic composites. We use density functional theory to predict the optical properties of homogeneous oxides and Lorentz–Mie theory to model scattering at the interfaces of the composite. Our findings demonstrate that increasing the refractive mismatch between the matrix and oxide phases can significantly reduce radiative heat flux. Furthermore, we show that additional thermal radiation suppression can be achieved by increasing the particle size. Our theoretical investigation has the potential to aid in the discovery of new coating ceramic composites and guide their microstructural design. 

Abstract Emerging machine-learned models have enabled efficient and accurate prediction of compound formation energy, with the most prevalent models relying on graph structures for representing crystalline materials. Here, we introduce an alternative approach based on sparse voxel images of crystals. By developing a sophisticated network architecture, we showcase the ability to learn the underlying features of structural and chemical arrangements in inorganic compounds from visual image representations, subsequently correlating these features with the compounds’ formation energy. Our model achieves accurate formation energy prediction by utilizing skip connections in a deep convolutional network and incorporating augmentation of rotated crystal samples during training, performing on par with state-of-the-art methods. By adopting visual images as an alternative representation for crystal compounds and harnessing the capabilities of deep convolutional networks, this study extends the frontier of machine learning for accelerated materials discovery and optimization. In a comprehensive evaluation, we analyse the predicted convex hulls for 3115 binary systems and introduce error metrics beyond formation energy error. This evaluation offers valuable insights into the impact of formation energy error on the performance of the predicted convex hulls. 

Abstract Emerging machine-learned models have enabled efficient and accurate prediction of compound formation energy. While the prevalent models rely on graph structures for representing crystalline materials, we introduce an alternative approach using voxel images of crystals. By designing a deep and complex convolutional network, we demonstrate the capability to learn the underlying features of structural and chemical arrangements in inorganic compounds from this visual image representation and map them to the compounds’ formation energy. Our model achieves accurate formation energy prediction by utilizing skip connections in a deep convolutional network and incorporating augmentation of rotated crystal samples during training, performing on par with state-of-the-art methods. By adopting visual images as an alternative representation for crystal compounds and harnessing the capabilities of deep convolutional networks, this study extends the frontier of machine learning for accelerated materials discovery and optimization. In a comprehensive evaluation, we analyze the predicted convex hulls for 3,115 binary systems and introduce error metrics beyond formation energy error. This evaluation offers valuable insights into the impact of formation energy error on the performance of the predicted convex hulls. 

Abstract Predicting the synthesizability of hypothetical crystals is challenging because of the wide range of parameters that govern materials synthesis. Yet, exploring the exponentially large space of novel crystals for any future application demands an accurate predictive capability for synthesis likelihood to avoid a haphazard trial-and-error. Typically, benchmarks of synthesizability are defined based on the energy of crystal structures. Here, we take an alternative approach to select features of synthesizability from the latent information embedded in crystalline materials. We represent the atomic structure of crystalline materials by three-dimensional pixel-wise images that are color-coded by their chemical attributes. The image representation of crystals enables the use of a convolutional encoder to learn the features of synthesizability hidden in structural and chemical arrangements of crystalline materials. Based on the presented model, we can accurately classify materials into synthesizable crystals versus crystal anomalies across a broad range of crystal structure types and chemical compositions. We illustrate the usefulness of the model by predicting the synthesizability of hypothetical crystals for battery electrode and thermoelectric applications.