In order to understand the charging and discharging processes of sodium-ion batteries, we are interested in the relationship between the size of sodium clusters inserted into the hard carbon anode and the solid-state ²³Na NMR chemical shifts. In this study, we investigated the predictability of the size dependence of ²³Na NMR shielding constants by SchNet, a deep learning model that uses the distance between Na atoms without graph connection information. The data set required for training the neural network was constructed by density functional theory (DFT) calculations. This study shows that the neural network model, which only used structural data, achieved comparable accuracy in predicting the shielding constant to the Lasso model, which utilized gross orbital population predicted from DFT calculations. Moreover, by introducing a penalty term to the neural network's loss function, the neural network was able to reproduce the skewed distribution of the shielding constant without modifying its architecture.

This paper develops an optimized prediction method based on machine learning for optimal process parameters for vacuum carburizing. The critical point is data expansion through machine learning based on a few parameters and data, which leads to optimizing parameters for vacuum carburization in heat treatment. This method extends the data volume by constructing a neural network with data augmentation in the presence of small data samples. In this paper, the database of 213 data is expanded to a database of 2,116,800 data by optimizing the prediction. Finally, we found the optimal vacuum carburizing process parameters through the vast database. The relative error of the three targets is less than that of the target obtained by the simulation of the corresponding parameters. The relative error is less than 5.6%, 1%, and 0.02%, respectively. Compared to simulations and actual experiments, the optimized prediction method in this paper saves much computational time. It provides a large amount of referable process parameter data while ensuring a certain level of accuracy.

Eutectic high entropy alloys (EHEAs) have attracted tremendous research interest over the past decade due to their superior physical and mechanical properties. Given the compositional complexity, there are no well-established phase diagrams for EHEAs. Therefore, the compositional design of EHEAs has been following a trial-and-error empirical approach, which is time-consuming, costly, and ineffective. To accelerate the search for EHEAs, data-driven approaches, particularly machine learning (ML) based modeling, have recently been utilized in lieu of the traditional empirical approach. In this article, we provide a critical overview of the recent efforts in the design and development of EHEAs, which covers the various empirical methods and the state-of-the-art machine learning models developed for EHEAs. In addition, we also briefly discuss the mechanical properties and plasticity strengthening mechanisms in EHEAs which are related to their heterogeneous microstructure, such as heterogeneous deformation induced strengthening, twinning induced strengthening, and phase transformation induced strengthening.

With advancements in automation and high-throughput techniques, we can tackle more complex multi-objective materials discovery problems requiring a higher evaluation budget. Given that experimentation is greatly limited by evaluation budget, maximizing sample efficiency of optimization becomes crucial. We discuss the limitations of using hypervolume as a performance indicator and propose new metrics relevant to materials experimentation: such as the ability to perform well for complex high-dimensional problems, minimizing wastage of evaluations, consistency/robustness of optimization, and ability to scale well to high throughputs. With these metrics, we perform an empirical study of two conceptually different and state-of-the-art algorithms (Bayesian and Evolutionary) on synthetic and real-world datasets. We discuss the merits of both approaches with respect to exploration and exploitation, where fully resolving the Pareto Front provides more knowledge of the best material.

Material molecular representation (MMR) plays an important role in material property or chemical reaction prediction. However, traditional expert-designed MMR methods face challenges in dealing with high dimensionality and heterogeneity of material data, leading to limited generalization capabilities and insufficient information representation. In recent years, graph neural networks (GNNs), a deep learning algorithm specifically designed for graph structures, have made inroads into the field of MMR. It will be instructive and inspiring to conduct a survey on various GNNs used for MMR. To achieve this objective, we compare GNNs with conventional MMR methods and illustrate the advantages of GNNs, such as their expressiveness and adaptability. In addition, we systematically classify and summarize the methods and applications of GNNs. Finally, we provide our insights into future research directions, taking into account the characteristics of molecular data and the inherent drawbacks of GNNs. This comprehensive survey is intended to present a holistic view of GNNs for MMR, focusing on the core concepts, the main techniques, and the future trends in this area.

High optical transmittance (T%) has always been an important indicator of transparent-ferroelectric ceramics for optoelectronic coupling. However, the pathway of pursuing high transparency has been at the experimental trial-and-error stage over the past decades, manifesting major drawbacks of being time-consuming and resource-wasting. The present work introduces a machine learning (ML) accelerated development of highly transparent-ferroelectrics by taking potassium-sodium niobate (KNN)-based ceramics as the model material. It is highlighted that by using a small data set of 118 sample data and four key features, we predict the T% of un-synthesized KNN-based ceramics and evaluate the importance of key features. Meanwhile, the screened (K_0.5Na_0.5)_0.956Tb_0.004Ba_0.04NbO₃ ceramics were successfully realized by the conventional solid-state synthesis, and the experimental measured T% is in full agreement with the predicted results, exhibiting a satisfactory high T% of ~78% at 800 nm. In addition, ML is also used to explore the best experimental parameters, and the prediction results of T% are particularly sensitive to changes in sintering temperature (ST). Eventually, the predicted optimal ST is highly consistent with the experimental one. This study constructs a new avenue for exploring high T% ferroelectric KNN ceramics based on ML, ascertaining optimal process parameters, and guiding the development of other transparent-ferroelectrics in optoelectronic fields.