Computational Materials Science最新文献_第4页

Hyperparameter optimization and neural architecture search algorithms for graph Neural Networks in cheminformatics 化学信息学中图神经网络的超参数优化和神经结构搜索算法

IF 3.1 3区材料科学

Computational Materials Science Pub Date : 2025-04-16 DOI: 10.1016/j.commatsci.2025.113904

Ali Ebadi, Manpreet Kaur, Qian Liu

{"title":"Hyperparameter optimization and neural architecture search algorithms for graph Neural Networks in cheminformatics","authors":"Ali Ebadi, Manpreet Kaur, Qian Liu","doi":"10.1016/j.commatsci.2025.113904","DOIUrl":"10.1016/j.commatsci.2025.113904","url":null,"abstract":"<div><div>Cheminformatics, an interdisciplinary field bridging chemistry and information science, leverages computational tools to analyze and interpret chemical data, playing a critical role in drug discovery, material science, and environmental chemistry. Traditional methods, reliant on rule-based algorithms and expert-curated datasets, face challenges in scalability and adaptability. Recently, machine learning and deep learning have revolutionized cheminformatics by offering data-driven approaches that uncover complex patterns in vast chemical datasets, advancing molecular property prediction, chemical reaction modeling, and de novo molecular design. Among the most promising techniques are Graph Neural Networks (GNNs), which have emerged as a powerful tool for modeling molecules in a manner that mirrors their underlying chemical structures. Despite their success, the performance of GNNs is highly sensitive to architectural choices and hyperparameters, making optimal configuration selection a non-trivial task. Neural Architecture Search (NAS) and Hyperparameter Optimization (HPO) are crucial for improving GNN performance, but the complexity and computational cost of these processes have traditionally hindered progress. This review examines various strategies for automating NAS and HPO in GNNs, highlighting their potential to enhance model performance, scalability, and efficiency in key cheminformatics applications. As the field evolves, automated optimization techniques are expected to play a pivotal role in advancing GNN-based solutions in cheminformatics.</div></div>","PeriodicalId":10650,"journal":{"name":"Computational Materials Science","volume":"254 ","pages":"Article 113904"},"PeriodicalIF":3.1,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A high accuracy machine-learning potential model for Mo-Re binary alloy Mo-Re二元合金高精度机器学习电位模型

IF 3.1 3区材料科学

Computational Materials Science Pub Date : 2025-04-16 DOI: 10.1016/j.commatsci.2025.113870

ZhiPeng Sun , YiNan Wang , WenJie Li , Xi Qiu , Ben Xu , XiaoYang Wang

{"title":"A high accuracy machine-learning potential model for Mo-Re binary alloy","authors":"ZhiPeng Sun , YiNan Wang , WenJie Li , Xi Qiu , Ben Xu , XiaoYang Wang","doi":"10.1016/j.commatsci.2025.113870","DOIUrl":"10.1016/j.commatsci.2025.113870","url":null,"abstract":"<div><div>Molybdenum is a promising candidate material for advanced nuclear reactors. However, its application in nuclear energy facilities is limited by its intrinsic brittleness, a common characteristic of body-centered cubic transition metals, which often exhibit poor plasticity and workability. The addition of Re to Mo can exploit the “Re softening effect” to enhance plasticity. To better understand the physical origin of this effect and explore the nanoscale atomistic mechanisms in Mo-Re alloys under service conditions, atomic-scale simulation methods, such as molecular dynamics (MD), are widely used as a complementary theoretical tool to experimental studies. However, the reliability of MD simulations is constrained by the limitations of existing empirical interatomic potentials. To address this challenge, this study employs state-of-the-art deep-potential methods to develop a machine learning-based interatomic potential for Mo-Re alloys. This advanced potential model achieves first-principles accuracy across a wide range of material properties, including elastic constants, surface energies, point defects, dislocations, and melting points, within a single potential. It enables high-accuracy atomic-scale simulations and investigations into the microstructural evolution of Mo-Re alloys under complex multi-field coupling conditions (irradiation, heat, and stress), which will establish the theoretical foundation for understanding the Re softening effect.</div></div>","PeriodicalId":10650,"journal":{"name":"Computational Materials Science","volume":"254 ","pages":"Article 113870"},"PeriodicalIF":3.1,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143834588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effect of Nb element on onset of deformation-induced martensitic transformation in iron: Insight from molecular dynamics simulations Nb元素对铁中变形诱发马氏体转变的影响：来自分子动力学模拟的见解

IF 3.1 3区材料科学

Computational Materials Science Pub Date : 2025-04-15 DOI: 10.1016/j.commatsci.2025.113892

Hao Sun , Jianfeng Jin , Weiyao Liang , Shaojie Li , Chen Chen , Mingtao Wang , Gaowu Qin

{"title":"Effect of Nb element on onset of deformation-induced martensitic transformation in iron: Insight from molecular dynamics simulations","authors":"Hao Sun , Jianfeng Jin , Weiyao Liang , Shaojie Li , Chen Chen , Mingtao Wang , Gaowu Qin","doi":"10.1016/j.commatsci.2025.113892","DOIUrl":"10.1016/j.commatsci.2025.113892","url":null,"abstract":"<div><div>Niobium (Nb) is a crucial alloying element in advanced steels, influencing deformation-induced martensitic transformation (DIMT) in advanced high-strength multiphase steels. In this work, molecular dynamics (MD) simulations were used to investigate the effects of Nb on DIMT characteristics in iron, focusing on the onset strain (<span><math><msub><mrow><mi>ε</mi></mrow><mrow><mi>S</mi></mrow></msub></math></span>), final strain (<span><math><msub><mrow><mi>ε</mi></mrow><mrow><mi>F</mi></mrow></msub></math></span>) and complete transformation rate <span><math><mrow><mo>(</mo><msub><mrow><mi>η</mi></mrow><mrow><mi>C</mi></mrow></msub></mrow></math></span>) of DIMT at atomic level. MD simulations reveal that Nb stabilizes residual face-centered cubic (FCC) austenite at 300 K, maintaining approximately 56 vol% austenite with Nb concentrations between 0.05 and 0.4 at.%. Tensile simulations at 300 K for these Nb concentrations show the yield stresses ranging from 7.55GPa to 8.94GPa, attributed to a combination of phase transformation and dislocation mechanisms. Across these Nb concentrations, the <span><math><msub><mrow><mi>ε</mi></mrow><mrow><mi>S</mi></mrow></msub></math></span> remains consistent at approximately 4.34 %, and the <span><math><msub><mrow><mi>η</mi></mrow><mrow><mi>C</mi></mrow></msub></math></span> is about 98 %. The formation of Lomer-Cottrell (LC) dislocations during yielding acts as a precursor for DIMT. Varying Nb content alters the competition between interface- and LC-triggered DIMT mechanisms. These findings provide valuable insights into the role of Nb in controlling DIMT and offer theoretical guidance for designing and developing high-performance Nb-alloyed steels.</div></div>","PeriodicalId":10650,"journal":{"name":"Computational Materials Science","volume":"253 ","pages":"Article 113892"},"PeriodicalIF":3.1,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effects of surface termination and tensile strain on the thermal conductivity of the Ti3C2Tx MXene 表面终止和拉伸应变对Ti3C2Tx MXene导热性能的影响

IF 3.1 3区材料科学

Computational Materials Science Pub Date : 2025-04-14 DOI: 10.1016/j.commatsci.2025.113890

Jun Jiang, Hao Jin, Ziye Xia, Yitong Zong, Jingwei Sun, Bo Liu

{"title":"Effects of surface termination and tensile strain on the thermal conductivity of the Ti3C2Tx MXene","authors":"Jun Jiang, Hao Jin, Ziye Xia, Yitong Zong, Jingwei Sun, Bo Liu","doi":"10.1016/j.commatsci.2025.113890","DOIUrl":"10.1016/j.commatsci.2025.113890","url":null,"abstract":"<div><div>This study investigates the effects of surface termination and tensile strain on the thermal conductivity of Ti<sub>3</sub>C<sub>2</sub>T<sub>x</sub> MXene nanosheets using ReaxFF molecular dynamics (MD) simulations. The results demonstrate that the thermal conductivity of Ti<sub>3</sub>C<sub>2</sub>O<sub>2</sub> MXene is significantly higher than that of Ti<sub>3</sub>C<sub>2</sub>(OH)<sub>2</sub> MXene, primarily due to its higher phonon group velocity and longer phonon mean free path (MFP). The presence of <img>OH functional groups in Ti<sub>3</sub>C<sub>2</sub>(OH)<sub>2</sub> MXene results in reduced thermal conductivity compared to the <img>O groups in Ti<sub>3</sub>C<sub>2</sub>O<sub>2</sub>. This reduction is attributed to high-frequency vibrations of hydrogen atoms, which enhance phonon scattering and suppress low-frequency phonon modes. Furthermore, the thermal conductivity of Ti<sub>3</sub>C<sub>2</sub>T<sub>x</sub> MXenes exhibits a nonmonotonic dependence on the fraction of <img>OH groups. Specifically, it decreases initially with increasing <img>OH content up to a fraction of 0.8, followed by a slight increase at higher concentrations. This behavior is explained by the interplay between phonon scattering and the uniformity of <img>OH group distribution. The application of tensile strain further reduces thermal conductivity by broadening the C-atom projected phonon spectrum and inducing phonon peak splitting, which enhances phonon scattering and shortens phonon lifetime. These findings offer critical insights into the tunability of thermal conductivity in MXenes, providing a foundation for optimizing their performance in applications such as electronics, energy conversion, and thermoelectric devices.</div></div>","PeriodicalId":10650,"journal":{"name":"Computational Materials Science","volume":"253 ","pages":"Article 113890"},"PeriodicalIF":3.1,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143825633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Spin filtering and rectifying behaviors in the super narrow borophene nanoribbon heterojunctions 超窄硼罗芬纳米带异质结的自旋过滤和整流行为

IF 3.1 3区材料科学

Computational Materials Science Pub Date : 2025-04-14 DOI: 10.1016/j.commatsci.2025.113898

Yang Song, Zi-Han Niu, En-Fei Xing, Wen-Shuo Liu, Chuan-Kui Wang, Gang Chen, Guang-Ping Zhang

引用次数: 0

Reinforcement of topological gels through physical crosslinking: A coarse-grained molecular dynamics study 通过物理交联强化拓扑凝胶：粗粒度分子动力学研究

IF 3.1 3区材料科学

Computational Materials Science Pub Date : 2025-04-14 DOI: 10.1016/j.commatsci.2025.113894

Yan Tang , Zechuan Yu , D.M. Li , Jia Chen , Jiahui Liu

引用次数: 0

IPFLSTM: Enhancing physics-informed neural networks with LSTM and Informer for efficient long-term prediction of dynamic multiphysics fields IPFLSTM：利用LSTM和Informer增强物理信息神经网络，实现动态多物理场的有效长期预测

IF 3.1 3区材料科学

Computational Materials Science Pub Date : 2025-04-12 DOI: 10.1016/j.commatsci.2025.113874

Chen Bai , Quan Qian

{"title":"IPFLSTM: Enhancing physics-informed neural networks with LSTM and Informer for efficient long-term prediction of dynamic multiphysics fields","authors":"Chen Bai , Quan Qian","doi":"10.1016/j.commatsci.2025.113874","DOIUrl":"10.1016/j.commatsci.2025.113874","url":null,"abstract":"<div><div>Multi-physics coupling, such as in metal solidification, involves complex interactions among physical fields like heat transfer, fluid flow, and phase change. Traditional numerical simulation methods, though accurate, are computationally expensive and struggle with long-term predictions due to the fine resolution required to capture these coupled phenomena. Furthermore, emerging machine learning methods that represent these phenomena for simulation tasks are not subject to complex physical constraints, and are only confined to fitting their numerical distributions. To address these issues, we introduce an enhanced physics-informed neural network framework. First, we employ LSTM as a spatio-temporal coordinates projection layer to transform actual physical positional relationships into positional encodings within the Informer framework. Second, we incorporate a physics-informed function for network parameters adjustment, thereby leveraging the physical constrain and the Informer model’s long-term dynamic prediction capability for final predictions. Experiments on the Cu-1wt.%Ag solidification process show that IPFLSTM reduces prediction L2 errors in velocity (u, v) and temperature fields by 56.8%, 51.74%, and 51.49% relative to PINNsFormer while cutting training time by 23.71%, outperforming traditional PINNs and their variants. This model offers a promising approach for simulating complex dynamic physical fields, addressing challenging boundary conditions, and extending to multi-scale, coupled systems in engineering applications.</div></div>","PeriodicalId":10650,"journal":{"name":"Computational Materials Science","volume":"253 ","pages":"Article 113874"},"PeriodicalIF":3.1,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Electronic and magnetic phase transitions, optimized MAE/ TC, and high thermoelectric response in Y2NiIrO6: Strain effects Y2NiIrO6的电子和磁性相变、优化的MAE/ TC和高热电响应：应变效应

IF 3.1 3区材料科学

Computational Materials Science Pub Date : 2025-04-10 DOI: 10.1016/j.commatsci.2025.113880

Usman Saeed , A. Islam , Bassem F. Felemban , Hafiz Tauqeer Ali , S. Nazir

引用次数: 0

Optical image analysis of WSe2 − thresholding for layer detection 用于层检测的WSe2−阈值光学图像分析

IF 3.1 3区材料科学

Computational Materials Science Pub Date : 2025-04-10 DOI: 10.1016/j.commatsci.2025.113888

Miah Abdullah Sahriar , Abdul Hamid Rumman , Ahammad Ullah , Kaushik Barua , Shohaib Ibne Monju , Munim Shahriar Jawad , Md. Atik Faisal , Ridwan Radit Ahsan , Houk Jang , Saquib Ahmed

{"title":"Optical image analysis of WSe2 − thresholding for layer detection","authors":"Miah Abdullah Sahriar , Abdul Hamid Rumman , Ahammad Ullah , Kaushik Barua , Shohaib Ibne Monju , Munim Shahriar Jawad , Md. Atik Faisal , Ridwan Radit Ahsan , Houk Jang , Saquib Ahmed","doi":"10.1016/j.commatsci.2025.113888","DOIUrl":"10.1016/j.commatsci.2025.113888","url":null,"abstract":"<div><div>The fast and reliable layer identification of two-dimensional transition metal dichalcogenide (TMD), such as WSe<sub>2,</sub> is essential to investigating their thickness-dependent electronic and optical properties. This article presents efficient optical image thresholding methodology designed to segment the mono, bi, and tri-layer regions of WSe<sub>2</sub> flakes mechanically exfoliated onto a SiO<sub>2</sub>/Si substrate. The optical images were first preprocessed to exclude the background effect and analyzed using the pixel medians and interquartile ranges for fundamental color channels—red, green, and blue (RGB). The analysis of red channel pixel intensities yielded three distinct ranges, serving as thresholds for layer segmentation: monolayer (111.0–118.0), bilayer (103.0–110.0), and tri-layer (93.0–103.0). Similarly, thresholds were established for each color channel, facilitating a comparative study of the segmentation performances. The intersection-over-union (<span><math><mrow><mi>IoU</mi></mrow></math></span>) calculations revealed that the red and green channels demonstrated greater than 99 % and 90 % accuracy in differentiating each layer, respectively. This approach yields remarkable results without substantial data calibration that utilizes time-intensive heuristic techniques. Moreover, the proposed methodology offers the flexibility to compare performances across different color channels, expanding the applicability for other 2D material systems.</div></div>","PeriodicalId":10650,"journal":{"name":"Computational Materials Science","volume":"253 ","pages":"Article 113888"},"PeriodicalIF":3.1,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Revealing Photo-electrochemical, Piezoelectric, and Ferroelectric Properties of γ-SnTe Monolayer via Density Functional Theory 利用密度泛函理论揭示γ-SnTe单层的光电化学、压电和铁电性质

IF 3.1 3区材料科学

Computational Materials Science Pub Date : 2025-04-10 DOI: 10.1016/j.commatsci.2025.113879

Nguyen Hoang Linh , Nguyen Xuan Dong , Tran The Quang , Dinh The Hung , Do Van Truong

{"title":"Revealing Photo-electrochemical, Piezoelectric, and Ferroelectric Properties of γ-SnTe Monolayer via Density Functional Theory","authors":"Nguyen Hoang Linh , Nguyen Xuan Dong , Tran The Quang , Dinh The Hung , Do Van Truong","doi":"10.1016/j.commatsci.2025.113879","DOIUrl":"10.1016/j.commatsci.2025.113879","url":null,"abstract":"<div><div>In this work, Density Functional Theory (DFT) calculations were performed to explore the photo-electrochemical, piezoelectric, and ferroelectric properties of the <em>γ</em>-SnTe monolayer. The optimized structure is confirmed to be dynamically and mechanically stable, exhibiting isotropic elastic behavior with an elastic modulus of 18.92 N/m and a shear modulus of 7.56 N/m. Electronic band structure analysis reveals that the <em>γ</em>-SnTe monolayer is an indirect semiconductor with a band gap of 2.56 eV, and the separation between charge carriers is clearly observed, with an effective mass mobility of approximately 0.44 <em>m<sub>0</sub></em>. Under biaxial strain, the band states continuously shift, optimizing redox potentials for surface chemical reactions. The material also demonstrates high piezoelectric coefficients, enabling efficient conversion of mechanical energy into electrical energy. Additionally, ferroelectricity is confirmed with a residual polarization of <em>P<sub>z</sub></em> = 5 pC/m and a low-energy switching barrier, making <em>γ</em>-SnTe highly suitable for low-power memory devices. These findings establish the <em>γ</em>-SnTe monolayer as a promising multifunctional material with potential applications in green energy technologies, electromechanical systems, and next-generation memory devices.</div></div>","PeriodicalId":10650,"journal":{"name":"Computational Materials Science","volume":"253 ","pages":"Article 113879"},"PeriodicalIF":3.1,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0