Combining first-principles accuracy and empirical-potential efficiency for the description of the potential energy surface (PES) is the philosopher's stone for unraveling the nature of matter via atomistic simulation. This has been particularly challenging for multi-component alloy systems due to the complex and non-linear nature of the associated PES. In this work, we develop an accurate PES model for the Al-Cu-Mg system by employing deep potential (DP), a neural network based representation of the PES, and DP generator (DP-GEN), a concurrent-learning scheme that generates a compact set of ab initio data for training. The resulting DP model gives predictions consistent with first-principles calculations for various binary and ternary systems on their fundamental energetic and mechanical properties, including formation energy, equilibrium volume, equation of state, interstitial energy, vacancy and surface formation energy, as well as elastic moduli. Extensive benchmark shows that the DP model is ready and will be useful for atomistic modeling of the Al-Cu-Mg system within the full range of concentration.

The lack of the long-range order in the atomic structure challenges the identification of the structural defects, akin to dislocations in crystals, which are responsible for predicting plastic events and mechanical failure in metallic glasses (MGs). Although vast structural indicators have been proposed to identify the structural defects, quantitatively gauging the correlations between these proposed indicators based on the undeformed configuration and the plasticity of MGs upon external loads is still lacking. Here, we systematically analyze the ability of these indicators to predict plastic events in a representative MG model using machine learning method. Moreover, we evaluate the influences of coarse graining method and medium-range order on the predictive power. We demonstrate that indicators relevant to the low-frequency vibrational modes reveal the intrinsic structural characteristics of plastic rearrangements. Our work makes an important step towards quantitative assessments of given indicators, and thereby an effective identification of the structural defects in MGs.

Accelerating materials discovery crucially relies on strategies that efficiently sample the search space to label a pool of unlabeled data. This is important if the available labeled data sets are relatively small compared to the unlabeled data pool. Active learning with efficient sampling methods provides the means to guide the decision making to minimize the number of experiments or iterations required to find targeted properties. We review here different sampling strategies and show how they are utilized within an active learning loop in materials science.

We train a neural network to identify impurities in the experimental images obtained by the scanning tunneling microscope (STM) measurements. The neural network is first trained with a large number of simulated data and then the trained neural network is applied to identify a set of experimental images taken at different voltages. We use the convolutional neural network to extract features from the images and also implement the attention mechanism to capture the correlations between images taken at different voltages. We note that the simulated data can capture the universal Friedel oscillation but cannot properly describe the non-universal physics short-range physics nearby an impurity, as well as noises in the experimental data. And we emphasize that the key of this approach is to properly deal with these differences between simulated data and experimental data. Here we show that even by including uncorrelated white noises in the simulated data, the performance of the neural network on experimental data can be significantly improved. To prevent the neural network from learning unphysical short-range physics, we also develop another method to evaluate the confidence of the neural network prediction on experimental data and to add this confidence measure into the loss function. We show that adding such an extra loss function can also improve the performance on experimental data. Our research can inspire future similar applications of machine learning on experimental data analysis.

Traditional materials discovery is in ‘trial-and-error’ mode, leading to the issues of low-efficiency, high-cost, and unsustainability in materials design. Meanwhile, numerous experimental and computational trials accumulate enormous quantities of data with multi-dimensionality and complexity, which might bury critical ‘structure–properties’ rules yet unfortunately not well explored. Machine learning (ML), as a burgeoning approach in materials science, may dig out the hidden structure–properties relationship from materials bigdata, therefore, has recently garnered much attention in materials science. In this review, we try to shortly summarize recent research progress in this field, following the ML paradigm: (i) data acquisition → (ii) feature engineering → (iii) algorithm → (iv) ML model → (v) model evaluation → (vi) application. In section of application, we summarize recent work by following the ‘material science tetrahedron’: (i) structure and composition → (ii) property → (iii) synthesis → (iv) characterization, in order to reveal the quantitative structure–property relationship and provide inverse design countermeasures. In addition, the concurrent challenges encompassing data quality and quantity, model interpretability and generalizability, have also been discussed. This review intends to provide a preliminary overview of ML from basic algorithms to applications.

In cluster science, it is challenging to identify the ground state structures (GSS) of gold (Au) clusters. Among different search approaches, first-principles method based on density functional theory (DFT) is the most reliable one with high precision. However, as the cluster size increases, it requires more expensive computational cost and becomes impracticable. In this paper, we have developed an artificial neural network (ANN) potential for Au clusters, which is trained to the DFT binding energies and forces of 9000 Au_N clusters (11 ≤ N ≤ 100). The root mean square errors of energy and force are 13.4 meV/atom and 0.4 eV/Å, respectively. We demonstrate that the ANN potential has the capacity to differentiate the energy level of Au clusters and their isomers and highlight the need to further improve the accuracy. Given its excellent transferability, we emphasis that ANN potential is a promising tool to breakthrough computational bottleneck of DFT method and effectively accelerate the pre-screening of Au clusters’ GSS.