npj Computational Materials最新文献_第2页

Graph attention networks decode conductive network mechanism and accelerate design of polymer nanocomposites 图关注网络解码导电网络机制，加速聚合物纳米复合材料的设计

IF 9.7 1区材料科学

npj Computational Materials Pub Date : 2025-08-28 DOI: 10.1038/s41524-025-01773-5

Tang Sui, Shaolong Liu, Bihui Cong, Xiaoke Xu, Dongjing Shan, Giuseppe Milano, Ying Zhao, Shuang Xu, Jiashun Mao

{"title":"Graph attention networks decode conductive network mechanism and accelerate design of polymer nanocomposites","authors":"Tang Sui, Shaolong Liu, Bihui Cong, Xiaoke Xu, Dongjing Shan, Giuseppe Milano, Ying Zhao, Shuang Xu, Jiashun Mao","doi":"10.1038/s41524-025-01773-5","DOIUrl":"https://doi.org/10.1038/s41524-025-01773-5","url":null,"abstract":"Conductive polymer nanocomposites have emerged as essential materials for wearable devices. In this study, we propose a novel approach that combines graph attention networks (GAT) with an improved global pooling strategy and incremental learning. We train the GAT model on homopolymer/carbon nanotube (CNT) nanocomposite data simulated by hybrid particle-field molecular dynamics (hPF-MD) method within the CNT concentration range of 1–8%. We further analyze the conductive network structure by integrating the resistor network approach with the GAT’s attention scores, revealing optimal connectivity at a 7% concentration. The comparative analysis of trained data and the reconstructed network, based on the attention scores, underscores the GAT model’s ability in learning network structural representations. This work not only validates the efficacy of the GAT model in property prediction and interpretable network structure analysis of polymer nanocomposites but also lays a cornerstone for the reverse engineering of polymer composites.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"22 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144910810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 physics-informed machine learning framework for accelerated discovery of single-phase B2 multi-principal element intermetallics 用于加速发现单相B2多主元素金属间化合物的物理信息机器学习框架

IF 9.7 1区材料科学

npj Computational Materials Pub Date : 2025-08-27 DOI: 10.1038/s41524-025-01775-3

Weijiang Zhao, Zhaoqi Chen, Yinghui Shang, Qing Wang, Li Wang, Bin Liu, Yong Liu, Yong Yang

引用次数: 0

NEP-MB-pol: a unified machine-learned framework for fast and accurate prediction of water’s thermodynamic and transport properties NEP-MB-pol：一个统一的机器学习框架，用于快速准确地预测水的热力学和输运性质

IF 9.7 1区材料科学

npj Computational Materials Pub Date : 2025-08-27 DOI: 10.1038/s41524-025-01777-1

Ke Xu, Ting Liang, Nan Xu, Penghua Ying, Shunda Chen, Ning Wei, Jianbin Xu, Zheyong Fan

{"title":"NEP-MB-pol: a unified machine-learned framework for fast and accurate prediction of water’s thermodynamic and transport properties","authors":"Ke Xu, Ting Liang, Nan Xu, Penghua Ying, Shunda Chen, Ning Wei, Jianbin Xu, Zheyong Fan","doi":"10.1038/s41524-025-01777-1","DOIUrl":"https://doi.org/10.1038/s41524-025-01777-1","url":null,"abstract":"The complex interatomic interactions and strong nuclear quantum effects in water pose significant challenges for accurately modeling its structural, thermodynamic, and transport behavior across varied conditions. While machine-learned potentials have improved the prediction of either static or transport properties individually, a unified computational framework that accurately captures both has remained elusive. Here, we introduce a machine-learned framework with a highly accurate and efficient neuroevolution potential trained on extensive many-body polarization reference data approaching coupled-cluster-level accuracy, combined with path-integral molecular dynamics and quantum-correction techniques. By capturing the quantum nature of water, this framework accurately predicts its structural, thermodynamic, and transport properties across a broad temperature range, enabling fast, accurate, and simultaneous prediction of self-diffusion coefficient, viscosity, and thermal conductivity. This work represents a major stride in water modeling, providing a unified and robust approach for exploring water’s thermodynamic and transport properties, with broad applications across multiple scientific disciplines.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"160 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144905804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Giant valley splitting and tunable anisotropic spin plasmons in a Janus ferrovalley monolayer Janus铁谷单层中的巨谷分裂和可调谐各向异性自旋等离子体

IF 9.7 1区材料科学

npj Computational Materials Pub Date : 2025-08-26 DOI: 10.1038/s41524-025-01776-2

Zhihua Zhang, Haotian Sun, Mimi Dong, Yiyi Guo, Mingwen Zhao

{"title":"Giant valley splitting and tunable anisotropic spin plasmons in a Janus ferrovalley monolayer","authors":"Zhihua Zhang, Haotian Sun, Mimi Dong, Yiyi Guo, Mingwen Zhao","doi":"10.1038/s41524-025-01776-2","DOIUrl":"https://doi.org/10.1038/s41524-025-01776-2","url":null,"abstract":"Manipulating the spin and valley degrees of freedom of electrons is crucial for next-generation information technologies. Altermagnets, as an emerging magnetic phase, provide a quantum platform with intrinsic spin-valley locking, enabling multi-state manipulation of both spin and valley. Here, we propose a Janus monolayer CaCoFeN2, achieved through in situ substitution of magnetic transition metal atoms in the two-dimensional (2D) altermagnet Ca(CoN)2 [Phys. Rev. Lett. 133, 056401 (2024)]. Our first-principles calculations identify CaCoFeN2 as an anisotropic spin-plasmon ferrovalley semiconductor, with a large valley splitting of 273 meV solely through crystal symmetry breaking, without any involvement of spin-orbit coupling (SOC). Furthermore, its anisotropic electronic structures facilitate highly directional spin plasmon propagation. Carrier-type switching (n-type ↔ p-type) reverses the anisotropy along orthogonal axes, yielding open equi-frequency contours in n-type CaCoFeN2. The integration of spontaneous spin and valley polarization within a single material without SOC, offers new opportunities for advancements in spintronics and valleytronics.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"27 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144901152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Optimal 3D chemical imaging with multimodal electron tomography 最佳三维化学成像与多模态电子断层扫描

IF 9.7 1区材料科学

npj Computational Materials Pub Date : 2025-08-25 DOI: 10.1038/s41524-025-01750-y

Jason Manassa, William Millsaps, Jonathan Schwartz, Robert Hovden

引用次数: 0

A versatile multimodal learning framework bridging multiscale knowledge for material design 一个多功能的多模态学习框架，连接材料设计的多尺度知识

IF 9.7 1区材料科学

npj Computational Materials Pub Date : 2025-08-25 DOI: 10.1038/s41524-025-01767-3

Yuhui Wu, Minmin Ding, Haonan He, Qijun Wu, Shaohua Jiang, Peng Zhang, Jian Ji

{"title":"A versatile multimodal learning framework bridging multiscale knowledge for material design","authors":"Yuhui Wu, Minmin Ding, Haonan He, Qijun Wu, Shaohua Jiang, Peng Zhang, Jian Ji","doi":"10.1038/s41524-025-01767-3","DOIUrl":"https://doi.org/10.1038/s41524-025-01767-3","url":null,"abstract":"Artificial intelligence has achieved remarkable success in materials science, accelerating novel material design. However, real-world material systems exhibit multiscale complexity—spanning composition, processing, structure, and properties—posing significant challenges for modeling. While some approaches fuse multiscale features to improve prediction, important modalities such as microstructure are often missing due to high acquisition costs. Existing methods struggle with incomplete data and lack a framework to bridge multiscale material knowledge. To address this, we propose MatMCL, a structure-guided multimodal learning framework that jointly analyzes multiscale material information and enables robust property prediction with incomplete modalities. Using a self-constructed multimodal dataset of electrospun nanofibers, we demonstrate that MatMCL improves mechanical property prediction without structural information, generates microstructures from processing parameters, and enables cross-modal retrieval. We further extend it via multi-stage learning and apply it to nanofiber-reinforced composite design. MatMCL uncovers processing-structure-property relationships, suggesting its promise as a generalizable approach for AI-driven material design.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"13 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144901151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

BEACON—automated aberration correction for scanning transmission electron microscopy using Bayesian optimization 利用贝叶斯优化技术对扫描透射电子显微镜进行beacon自动像差校正

IF 9.7 1区材料科学

npj Computational Materials Pub Date : 2025-08-24 DOI: 10.1038/s41524-025-01766-4

Alexander J. Pattison, Stephanie M. Ribet, Marcus M. Noack, Georgios Varnavides, Kunwoo Park, Earl J. Kirkland, Jungwon Park, Colin Ophus, Peter Ercius

引用次数: 0

Transferable dispersion-aware machine learning interatomic potentials for multilayer transition metal dichalcogenide heterostructures 多层过渡金属二硫化物异质结构的可转移色散感知机器学习原子间势

IF 9.7 1区材料科学

npj Computational Materials Pub Date : 2025-08-24 DOI: 10.1038/s41524-025-01761-9

Yusuf Shaidu, Mit H. Naik, Steven G. Louie, Jeffrey B. Neaton

{"title":"Transferable dispersion-aware machine learning interatomic potentials for multilayer transition metal dichalcogenide heterostructures","authors":"Yusuf Shaidu, Mit H. Naik, Steven G. Louie, Jeffrey B. Neaton","doi":"10.1038/s41524-025-01761-9","DOIUrl":"https://doi.org/10.1038/s41524-025-01761-9","url":null,"abstract":"Stacking atomically thin transition metal dichalcogenides (TMDs) into heterostructures enables exploration of exotic quantum phases, particularly through twist-angle-controlled moiré superlattices. These structures exhibit novel electronic and optical behaviors driven by atomic-scale structural reconstruction. However, studying such systems with DFT is computationally demanding due to their large unit cells and van der Waals (vdW) interactions between layers. To address this, we develop a transferable neural network potential (NNP) that includes long-range vdW corrections up to 12Å with minimal overhead. Trained on vdW-corrected DFT data for Mo- and W-based TMDs with S, Se, and Te, the NNP accurately models monolayers, bilayers, heterostructures, and their interaction with h-BN substrates. It reproduces equilibrium structures, energy landscapes, phonon dispersions, and matches experimental atomic reconstructions in twisted WS2 and MoS2/WSe2 systems. We demonstrate that our NNP achieves DFT-level accuracy and high computational efficiency, enabling large-scale simulations of TMD-based moiré superlattices both with and without substrates.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"29 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144901155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Physics-informed neural operators for generalizable and label-free inference of temperature-dependent thermoelectric properties 用于温度相关热电性质的可推广和无标记推理的物理信息神经算子

IF 9.7 1区材料科学

npj Computational Materials Pub Date : 2025-08-22 DOI: 10.1038/s41524-025-01769-1

Hyeonbin Moon, Songho Lee, Wabi Demeke, Byungki Ryu, Seunghwa Ryu

{"title":"Physics-informed neural operators for generalizable and label-free inference of temperature-dependent thermoelectric properties","authors":"Hyeonbin Moon, Songho Lee, Wabi Demeke, Byungki Ryu, Seunghwa Ryu","doi":"10.1038/s41524-025-01769-1","DOIUrl":"https://doi.org/10.1038/s41524-025-01769-1","url":null,"abstract":"Accurate characterization of temperature-dependent thermoelectric properties (TEPs), such as thermal conductivity and the Seebeck coefficient, is essential for modeling and design of thermoelectric devices. However, nonlinear temperature dependence and coupled transport behavior make forward simulation and inverse identification challenging under sparse measurements. We present a physics-informed machine learning framework combining physics-informed neural networks (PINN) and neural operators (PINO) for solving forward and inverse problems in thermoelectric systems. PINN enables field reconstruction and property inference by embedding governing equations into the loss function, while PINO generalizes across materials without retraining. Trained on simulated data for 20 p-type materials and tested on 60 unseen materials, PINO accurately infers TEPs using only sparse temperature and voltage data. This framework provides a scalable, data-efficient, and generalizable solution for thermoelectric property identification, facilitating high-throughput screening and inverse design of advanced thermoelectric materials.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"21 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144901159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Anisotropic temperature-dependent lattice parameters and elastic constants from first principles 基于第一性原理的各向异性温度相关晶格参数和弹性常数

IF 9.7 1区材料科学

npj Computational Materials Pub Date : 2025-08-22 DOI: 10.1038/s41524-025-01765-5

Samare Rostami, Matteo Giantomassi, Xavier Gonze

引用次数: 0