Considering all possible crystal structures is essential in computer simulations of alloy properties, but using Density Functional Theory (DFT) is computationally impractical. To address this, four structural descriptors were evaluated using machine learning (ML) models to predict formation energy, elasticity and hardness of MoTa alloys. A total of 612 configurations were generated by the Clusters Approach to Statistical Mechanics (CASM) software and their corresponding material properties were calculated by DFT. As input features of ML models, the CORR and SOAP performed best (R2 > 0.90, some up to 0.99), followed by ACSF, while CM performed worst. Furthermore, SOAP shows excellent performance in extrapolation for larger supercell structures of the MoTa alloy system and transfer learning for the MoNb alloy system.
在对合金特性进行计算机模拟时,必须考虑所有可能的晶体结构,但使用密度泛函理论(DFT)在计算上并不现实。为了解决这个问题,我们使用机器学习(ML)模型对四种结构描述符进行了评估,以预测钼钽合金的形成能、弹性和硬度。统计力学聚类方法(CASM)软件共生成了 612 种构型,并通过 DFT 计算了其相应的材料属性。作为 ML 模型的输入特征,CORR 和 SOAP 表现最好(R2 > 0.90,有些高达 0.99),其次是 ACSF,而 CM 表现最差。此外,SOAP 在对 MoTa 合金体系的较大超晶胞结构进行外推以及对 MoNb 合金体系进行迁移学习方面表现出色。
{"title":"Structural descriptors evaluation for MoTa mechanical properties prediction with machine learning","authors":"Tingpeng Tao, Shu Li, Dechuang Chen, Shuai Li, Dongrong Liu, Xin Liu, Minghua Chen","doi":"10.1088/1361-651x/ad1cd1","DOIUrl":"https://doi.org/10.1088/1361-651x/ad1cd1","url":null,"abstract":"\u0000 Considering all possible crystal structures is essential in computer simulations of alloy properties, but using Density Functional Theory (DFT) is computationally impractical. To address this, four structural descriptors were evaluated using machine learning (ML) models to predict formation energy, elasticity and hardness of MoTa alloys. A total of 612 configurations were generated by the Clusters Approach to Statistical Mechanics (CASM) software and their corresponding material properties were calculated by DFT. As input features of ML models, the CORR and SOAP performed best (R2 > 0.90, some up to 0.99), followed by ACSF, while CM performed worst. Furthermore, SOAP shows excellent performance in extrapolation for larger supercell structures of the MoTa alloy system and transfer learning for the MoNb alloy system.","PeriodicalId":18648,"journal":{"name":"Modelling and Simulation in Materials Science and Engineering","volume":"26 5","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139444131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-29DOI: 10.1088/1361-651x/ad16ef
Pan Zheng, Yiru Huang, Lei Zhang
The A4BX6 molecular halide perovskites have received attention owing to their interesting optoelectronic properties at the molecular scale; however, a comprehensive dataset of their atomic structures and electronic properties and associated data-driven investigation are still unavailable now, which makes it difficult for inverse materials design for semiconductor applications (e.g. wide band gap semiconductor). In this manuscript, we employ data-driven methods to predict band gaps of A4BX6 molecular halide perovskites via machine learning. A large virtual design database including 246 904 A4BX6 perovskite samples is predicted via machine learning, based on the model trained using 2740 first-principles results of A4BX6 molecular halide perovskites. In addition, symbolic regression-based machine learning is employed to identify more physically intuitive descriptors based on the starting first-principles dataset of A4BX6 molecular halide perovskites. In addition, different ranking methods are employed to offer a comprehensive feature importance analysis for the halide perovskite materials. This study highlights the efficacy of machine learning-assisted compositional design of A4BX6 perovskites, and the multi-dimensional database established here is valuable for future experimental validation toward perovskite-based wide band gap semiconductor materials.
{"title":"First-principles and machine learning investigation on A4BX6 halide perovskites","authors":"Pan Zheng, Yiru Huang, Lei Zhang","doi":"10.1088/1361-651x/ad16ef","DOIUrl":"https://doi.org/10.1088/1361-651x/ad16ef","url":null,"abstract":"The A<sub>4</sub>BX<sub>6</sub> molecular halide perovskites have received attention owing to their interesting optoelectronic properties at the molecular scale; however, a comprehensive dataset of their atomic structures and electronic properties and associated data-driven investigation are still unavailable now, which makes it difficult for inverse materials design for semiconductor applications (e.g. wide band gap semiconductor). In this manuscript, we employ data-driven methods to predict band gaps of A<sub>4</sub>BX<sub>6</sub> molecular halide perovskites via machine learning. A large virtual design database including 246 904 A<sub>4</sub>BX<sub>6</sub> perovskite samples is predicted via machine learning, based on the model trained using 2740 first-principles results of A<sub>4</sub>BX<sub>6</sub> molecular halide perovskites. In addition, symbolic regression-based machine learning is employed to identify more physically intuitive descriptors based on the starting first-principles dataset of A<sub>4</sub>BX<sub>6</sub> molecular halide perovskites. In addition, different ranking methods are employed to offer a comprehensive feature importance analysis for the halide perovskite materials. This study highlights the efficacy of machine learning-assisted compositional design of A<sub>4</sub>BX<sub>6</sub> perovskites, and the multi-dimensional database established here is valuable for future experimental validation toward perovskite-based wide band gap semiconductor materials.","PeriodicalId":18648,"journal":{"name":"Modelling and Simulation in Materials Science and Engineering","volume":"8 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2023-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139094110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-19DOI: 10.1088/1361-651x/ad111f
Yunhai Liu, Benteng Che, Xiaowen Wang, Yiyao Luo, Hu Zhang, Ligao Liu, Penghui Xu
In order to further explore the influence of temperature on the face-centered cubic (FCC) single-phase crystal CoCrFeNiAl0.1, we conducted a series of Nano-indentation experiments on CoCrFeNiAl0.1 at different temperatures. At room temperature, the effects of indentation can convert a portion of CoCrFeNiAl0.1’s FCC phase into a funnel-shaped hexagonal close-packed (HCP) phase, resulting less deformation on the sides of the indenter. What we analyzed shows that CoCrFeNiAl0.1’s HCP phase has excellent heat resistance and mechanics, allowing CoCrFeNiAl0.1 to maintain great properties in high-temperature environments. However, if T ⩾ 1500 K, high temperature will decrease the number of the HCP phases and dislocation density, leading to an accelerated decline in material strength. This research can provide a theoretical relationship between temperature and microstructural evolution for the research and application of CoCrFeNiAl0.1 in high-temperature environments.
{"title":"Exploring the effects of temperature on the mechanical properties of high-entropy alloy (CoCrFeNiAl0.1) based on molecular dynamics simulation","authors":"Yunhai Liu, Benteng Che, Xiaowen Wang, Yiyao Luo, Hu Zhang, Ligao Liu, Penghui Xu","doi":"10.1088/1361-651x/ad111f","DOIUrl":"https://doi.org/10.1088/1361-651x/ad111f","url":null,"abstract":"In order to further explore the influence of temperature on the face-centered cubic (FCC) single-phase crystal CoCrFeNiAl<sub>0.1</sub>, we conducted a series of Nano-indentation experiments on CoCrFeNiAl<sub>0.1</sub> at different temperatures. At room temperature, the effects of indentation can convert a portion of CoCrFeNiAl<sub>0.1</sub>’s FCC phase into a funnel-shaped hexagonal close-packed (HCP) phase, resulting less deformation on the sides of the indenter. What we analyzed shows that CoCrFeNiAl<sub>0.1</sub>’s HCP phase has excellent heat resistance and mechanics, allowing CoCrFeNiAl<sub>0.1</sub> to maintain great properties in high-temperature environments. However, if <italic toggle=\"yes\">T</italic> ⩾ 1500 K, high temperature will decrease the number of the HCP phases and dislocation density, leading to an accelerated decline in material strength. This research can provide a theoretical relationship between temperature and microstructural evolution for the research and application of CoCrFeNiAl<sub>0.1</sub> in high-temperature environments.","PeriodicalId":18648,"journal":{"name":"Modelling and Simulation in Materials Science and Engineering","volume":"18 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139055808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-15DOI: 10.1088/1361-651x/ad104e
Aparna Thankappan
Perovskite solar cells (PSCs) have garnered extensive research interest due to their potential for efficient, flexible, and cost-effective solar energy production, making them suitable for wearable and low-cost applications. In this study, we successfully synthesized layered copper-based perovskite materials, and subsequently conducted simulations using the Solar Cell Capacitance Simulator SCAPS-1D. This study introduces, a PSC structure with (CH3NH3)2CuCl4 as the active layer. By employing a two-step chemical method, we have successfully synthesized (CH3NH3)2CuCl4, and its optical band gap was determined using Tauc’s extrapolation method. Utilizing the experimentally determined bandgap as the simulation input, we predicted a solar architecture consisting of glass substrate/fluorine-doped tin oxide/TiO2/(CH3NH3)2CuCl4/spiro-OMeTAD/Pt, which exhibited an impressive conversion efficiency of 27.93% along with a fill factor of 62.04%, J