Following the Materials Genome Initiative project, materials research has embarked a new research paradigm centered around material repositories, significantly accelerating the discovery of novel materials, such as thermoelectrics. Thermoelectric materials, capable of directly converting heat into electricity, are garnering increasing attention in applications like waste heat recovery and refrigeration. To facilitate research in this emerging paradigm, we have established the Materials Hub with Three-Dimensional Structures (MatHub-3d) repository, which serves as the foundation for high-throughput (HTP) calculations, property analysis, and the design of thermoelectric materials. In this review, we summarize recent advancements in thermoelectric materials powered by the MatHub-3d, specifically HTP calculations of transport properties and material design on key factors. For HTP calculations, we develop the electrical transport package for HTP purpose, and utilize it for materials screening. In some works, we investigate the relationship between transport properties and chemical bonds for particular types of thermoelectric compounds based on HTP results, enhancing the fundamental understanding about interested compounds. In our work associated with material design, we primarily utilize key factors beyond transport properties to further expedite materials screening and speedily identify specific materials for further theoretical/experimental analyses. Finally, we discuss the future developments of the MatHub-3d and the evolving directions of database-driven thermoelectric research.
Mg alloy suffers from its poor corrosion resistance as a result of anodic dissolution of Mg and hydrogen evolution reaction (HER) in humid environments. In this study, the effects of alloying elements (Al, Zn, Y, Ce, and Mn) on both processes in Mg alloys have been quantitatively predicted. Using first-principle calculations, we first obtained the substitution energies of alloying elements to compare their segregation preference, and then analyzed the influence of solutes at different layers on the stability and hydrogen adsorption properties of Mg(0001) surface by calculating the formation enthalpy, surface energy, vacancy formation energy, work function, Bader charge, deformation charge density, and adsorption free energy of H atom. It has been found that, on the one hand, the interior Mn solute atoms reduce the dissolution of Mg atoms and the transfer of electrons, consequently slowing down the anodic dissolution process. On another hand, the Mn, Y, and Ce elements on the surface inhibit the cathodic HER process by elevating the absolute value of hydrogen adsorption free energy, as a result of those solutes effectively controlling H adsorption behavior on Mg(0001) surface. In contrast, all five elements dissolved inside the Mg grain do not show significant effects on the H adsorption behavior.
The energy landscape represents a high-dimensional mapping of the configurational states of an atomic system with their respective energies. Under isobaric conditions, enthalpy landscapes can be used to account for volumetric changes of the system. Understanding the energy or enthalpy landscape holds the key for discovering materials with targeted properties, since the landscape encapsulates the complete thermodynamic and kinetic behavior of a system, including relaxation, metastable phases, and reactivity. However, the curse of dimensionality prohibits one from enumerating and visualizing the energy landscape—the energy landscape of an N-atom system has 3N dimensions. Here, we outline the emerging computational techniques that allow the exploration of complex energy landscapes of materials in three distinct categories: the classical, metaheuristic, and machine learning approaches. We discuss the advantages and disadvantages associated with each of these methods, with a focus on the nature of problems where they can provide excellent solutions (and vice versa). Altogether, in addition to giving an overview of existing approaches, we hope the review provides an impetus to develop novel methods to explore the energy landscapes that can, in turn, provide both a fundamental understanding of the physics of materials and accelerate the discovery of novel materials.
Exploring the “composition-microstructure-property” relationship is a longstanding theme in materials science. However, complex interactions make this area of research challenging. Based on the image processing and machine learning techniques, this paper proposes a multimodal fusion learning framework that comprehensively considers both composition and microstructure in prediction of the ultimate tensile strength (UTS) of Al-Si alloys. Firstly, the composition and image information are collected from the literature and supplementary experiments, followed by the image segmentation and quantitative analysis of eutectic Si images. Subsequently, the quantitative analysis results are combined with other features for three-step feature screening, and 12 key features are obtained. Finally, four machine-learning models (i.e., decision tree, random forest, adaptive boosting, and extreme gradient boosting [XGBoost]) are used to predict the UTS of Al-Si alloys. The results show that the quantitative analysis method proposed in this paper is superior to Image-Pro Plus (IPP) software in some aspects. The XGBoost model has the best prediction performance with R2 = 0.94. Furthermore, five mixed features and their critical values that significantly affect UTS are identified. Our study provides enlightenment for the prediction of UTS of Al-Si alloys from composition and microstructure, and would be applicable to other alloys.
Hierarchical clustering algorithm has been applied to identify the X-ray diffraction (XRD) patterns from a high-throughput characterization of the combinatorial materials chips. As data quality is usually correlated with acquisition time, it is important to study the hierarchical clustering performance as a function of data quality in order to optimize the efficiency of high-throughput experiments. This work investigated the effects of signal-to-noise ratio on the performance of hierarchical clustering using 29 distance metrics for the XRD patterns from Fe–Co–Ni ternary combinatorial materials chip. It is found that the clustering accuracies evaluated by the F1 score only fluctuate slightly with signal-to-noise ratio varying from 15.5 to 22.3 (dB) under the experimental condition. This suggests that although it may take 40-50 s to collect a visually high-quality diffraction pattern, the measurement time could be significantly reduced to as low as 4 s without substantial loss in phase identification accuracy by hierarchical clustering. Among the 29 distance metrics, Pearson χ2 shows the highest mean F1 score of 0.77 and lowest standard deviation of 0.008. It shows that the distance matrixes calculated by Pearson χ2 are mainly controlled by the XRD peak shifting characteristics and visualized by the metric multidimensional data scaling.
The emerging photovoltaic (PV) technologies, such as organic and perovskite PVs, have the characteristics of complex compositions and processing, resulting in a large multidimensional parameter space for the development and optimization of the technologies. Traditional manual methods are time-consuming and laborintensive in screening and optimizing material properties. Materials genome engineering (MGE) advances an innovative approach that combines efficient experimentation, big database and artificial intelligence (AI) algorithms to accelerate materials research and development. High-throughput (HT) research platforms perform multidimensional experimental tasks rapidly, providing a large amount of reliable and consistent data for the creation of materials databases. Therefore, the development of novel experimental methods combining HT and AI can accelerate materials design and application, which is beneficial for establishing material-processing-property relationships and overcoming bottlenecks in the development of emerging PV technologies. This review introduces the key technologies involved in MGE and overviews the accelerating role of MGE in the field of organic and perovskite PVs.
Enhancing the interpretability of machine learning methods for predicting material properties is a key, yet complex topic in materials science. This study proposes an interpretable convolutional neural network (CNN) to establish the relationship between the microstructural evolution and mechanical properties of non-uniform and nonlinear multisystem dual-phase steel materials and achieve an inverse analysis of the elastic-plastic mechanism. This study demonstrates that the developed CNN model achieves an accuracy of 94% in predicting the stress-strain curves of dual-phase steel microstructures with different compositions and processes, with the mean absolute error not exceeding 50 MPa, representing merely 5.26% of the average tensile strength of dual-phase steels in the dataset. The reverse visualization results of the CNN model indicate that, during tensile deformation, the grain boundaries maintain deformation coordination within the grains by impeding dislocation slip. This results in a significant stress concentration at the grain boundaries, with stresses at the boundaries being higher than those borne by the martensitic phase and minimal stresses in the ferrite phase. Moreover, compared with traditional crystal plasticity models, the CNN model exhibits a substantial improvement in computational efficiency. This method provides a generic plan for improving the interpretability of machine learning methods for predicting material properties and can be easily applied to other alloy systems.
Generative adversarial networks (GANs), as a powerful tool for inverse materials discovery, are being increasingly applied in various fields of materials science. This review provides systematic investigations on the applications of GANs from a group of different aspects. The basic principles of GANs are first introduced; then a detailed review of GANs-based studies regarding distinct scenarios across composition design, processing optimization, crystal structure search, microstructure characterization and defect detection is presented. At the end, several challenges and possible solutions are discussed and outlined. This overview highlights the efficacy of GANs in materials science, and may stimulate the further use of GANs for more intriguing achievements.
Additive friction stir deposition (AFSD) provides strong flexibility and better performance in component design, which is controlled by the process parameters. It is an essential and difficult task to tune those parameters. The recent exploration of machine learning (ML) exhibits great potential to obtain a suitable balance between productivity and set parameters. In this study, ML techniques, including support vector machine (SVM), random forest (RF) and artificial neural network (ANN), are applied to predict the mechanical properties of the AFSD-based AA6061 deposition. Expect for the stable parameters (temperature, force and torque) in situ monitored by the self-developed process-aware kit during the AFSD process and the other factors (rotation speed, traverse speed, feed rate and layer thickness) are also set as input variables. The output variables are microhardness and ultimate tensile strength (UTS). Prediction results show that the ANN model performs the best prediction accuracy with the highest R2 (0.9998) and the lowest mean absolute error (MAE, 0.0050) and root mean square error (RMSE, 0.0063). Furthermore, analysis suggests that the feed rate (24.8%/24.1%) and layer thickness (25.6%/26.6%) indicate a higher contribution that affects the mechanical properties.