Search

We present an integrated deep machine learning (ML) approach that combines crystal graph convolutional neural networks (CGCNN) for predicting formation energies and artificial neural networks (ANN) for constructing interatomic potentials. Using the La–Si–P ternary system as a proof-of-concept, we achieve a remarkable speed-up of at least 100 times compared to high-throughput first-principles calculations. The ML approach successfully identifies known compounds and uncovers 16 new P-rich compounds with formation energies within 100 meV per atom above the convex hull, including a stable La2SiP3 phase. We also employ the developed ML interatomic potential in a genetic algorithm for efficient structure search, leading to the discovery of more metastable compounds. Moreover, substitution of La atoms with Ba reveals a new stable quaternary compound, BaLaSiP3. Our generic and robust approach holds great promise for accelerating materials discovery in various compounds, enabling more efficient exploration of complex chemical spaces and enhancing the prediction of material properties. [ABSTRACT FROM AUTHOR]

Correction for 'Accelerating materials discovery using integrated deep machine learning approaches' by Weiyi Xia et al., J. Mater. Chem. A, 2023, 11, 25973–25982, https://doi.org/10.1039/d3ta03771a. [ABSTRACT FROM AUTHOR]

Abstract: The effect of Nb addition on the glass-forming ability (GFA), mechanical and soft-magnetic properties in (Co0.942Fe0.058)72−x Nb x B22.4Si5.6 alloys system was investigated. In addition to the increase of glass-forming ability, the increase of Nb content was found to be effective for the improvement of mechanical and soft-magnetic properties. By copper mold casting, Co-based bulk glassy alloys with diameters up to 4mm were formed in (Co0.942Fe0.058)67Nb5B22.4Si5.6 glassy alloy. The bulk glassy alloys exhibit a superhigh fracture strength of 2980–3600MPa and Young''s modulus of 121–166GPa. The bulk glassy alloys also exhibit excellent soft-magnetic properties, i.e., high saturation magnetization of 0.6T, low coercive force within 0.2–0.5A/m, high permeability of 47165 at 1KHz and zero magnetostriction. [Copyright &y& Elsevier]

Abstract: The glass-forming ability (GFA) and soft-magnetic properties of (Co0.6Fe0.3Ni0.1)67B22+x Si6−x Nb5 (x =0–1.5) bulk glassy alloys was investigated. The DSC curves show that the (Co0.6Fe0.3Ni0.1)67B22+x Si6−x Nb5 bulk glassy alloys have a wide supercooled liquid region (ΔT x) of about 60K, and high reduced glass transition temperature (T g/T l) lies in the range from 0.628 to 0.649. By copper mold casting method, the bulk glassy alloys with diameters up to 4.5mm can be formed. In addition to high GFA, the Co-based bulk glassy alloys also exhibit good soft-magnetic properties, i.e., saturation magnetization of 0.58–0.61T, low coercive force of 0.83–1.46A/m, and high permeability of (1.79–2.2)×104 at 1kHz under a field of 1A/m. These Co-based bulk glassy alloys are promising for future applications as a new structural and functional material. [Copyright &y& Elsevier]

Small-scale systems based on periodic boundary conditions often cannot accurately describe real-world situations, especially when conducting molecular dynamics simulations to study phase transitions, where it is very necessary to use large-scale systems. However, studying phase transitions in large-scale systems is an important and difficult task. Though ab initio molecular dynamics (AIMD), based on density functional theory (DFT), provides advantages in terms of accuracy, it is very difficult to study phase transitions in large-scale systems due to the considerable computational time required. In addition, although traditional empirical potentials are faster, their lower calculation accuracy makes it difficult to use them for phase transition studies. It is crucial to devise a method that has enabled a promising fusion of computational efficiency and precision to effectively investigate phase transitions in large-scale systems. In this work, the obtained machine learning potential function of carbon through deep neural networks not only demonstrates strong scalability but also effectively enables the study of the formation mechanisms of amorphous diamond and polycrystalline diamond using C 60 crystals and graphene as precursors under high-pressure high-temperature conditions (HPHT). Furthermore, the structure search software (AIRSS) was used to generate numerous initial structures which were optimized using the machine learning potential, a process which led to finding new structural clusters of carbon. Interestingly, the predictive capabilities of the machine learning potential for symmetric and asymmetric carbon clusters aligned well with the Gaussian approximation potential (GAP), yet the former demonstrated higher computational efficiency, making it more suitable for carbon material research. The results of this work signify significant progress in the field of carbon transition study, opening up new possibilities for exploring and understanding carbon materials with improved computational efficacy.