Pub Date : 2026-02-16DOI: 10.1038/s41524-026-01976-4
Yu Xie, Menghang Wang, Senja Ramakers, Frans Spaepen, Boris Kozinsky
{"title":"Incongruent melting and phase diagram of SiC from machine learning molecular dynamics","authors":"Yu Xie, Menghang Wang, Senja Ramakers, Frans Spaepen, Boris Kozinsky","doi":"10.1038/s41524-026-01976-4","DOIUrl":"https://doi.org/10.1038/s41524-026-01976-4","url":null,"abstract":"","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"24 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146205083","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}
The disordered nature of amorphous materials like metallic glasses has long hindered the establishment of well-defined structure-property relationships. Although it is widely recognized that short-range orders (SROs) within the first nearest-neighbor shell do not sufficiently characterize these materials, identifying the optimal characteristic length scale for capturing richer structural information remains elusive. Here, we resolve this ambiguity using a dual machine learning (ML) approach, which identifies the Radius of Informative Structural Environments (RISE) in a prototypical Zr-Cu metallic glass system. A top-down, reductionist approach, integrating SOAP descriptor with XGBoost model, demonstrates that the atomic environments within 5 Å radius entail maximal structural diversity and information density, leading to the optimal performance of the model on predicting given samples’ configurational energies. Concurrently, a bottom-up, emergentist Vision Transformer (ViT) architecture, designed to autonomously learn structural patterns from voxelized atomic configurations, shows that its predictive performance saturates when the effective communication length between its input patches reaches an equivalent spherical radius of ~5 Å. The striking convergence of these independent ML strategies provides compelling, data-driven evidence for the existence of an intrinsic, structurally informative length scale in metallic glasses. Additional robustness checks across multiple glassy materials with various elements numbers and bonding types confirm such RISE is not an artifact of encoding parameters or system size and aligns with existing experimental and computational insights.
{"title":"Dual machine learning pinpoints the Radius of Informative Structural Environments in metallic glasses","authors":"Muchen Wang, Yuchu Wang, Minhazul Islam, Yuchi Wang, Yunzhi Wang, Jinwoo Hwang, Yue Fan","doi":"10.1038/s41524-026-01997-z","DOIUrl":"https://doi.org/10.1038/s41524-026-01997-z","url":null,"abstract":"The disordered nature of amorphous materials like metallic glasses has long hindered the establishment of well-defined structure-property relationships. Although it is widely recognized that short-range orders (SROs) within the first nearest-neighbor shell do not sufficiently characterize these materials, identifying the optimal characteristic length scale for capturing richer structural information remains elusive. Here, we resolve this ambiguity using a dual machine learning (ML) approach, which identifies the Radius of Informative Structural Environments (RISE) in a prototypical Zr-Cu metallic glass system. A top-down, reductionist approach, integrating SOAP descriptor with XGBoost model, demonstrates that the atomic environments within 5 Å radius entail maximal structural diversity and information density, leading to the optimal performance of the model on predicting given samples’ configurational energies. Concurrently, a bottom-up, emergentist Vision Transformer (ViT) architecture, designed to autonomously learn structural patterns from voxelized atomic configurations, shows that its predictive performance saturates when the effective communication length between its input patches reaches an equivalent spherical radius of ~5 Å. The striking convergence of these independent ML strategies provides compelling, data-driven evidence for the existence of an intrinsic, structurally informative length scale in metallic glasses. Additional robustness checks across multiple glassy materials with various elements numbers and bonding types confirm such RISE is not an artifact of encoding parameters or system size and aligns with existing experimental and computational insights.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"52 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146196794","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}
Pub Date : 2026-02-13DOI: 10.1038/s41524-026-01958-6
Sanghyeon Park, Yoonsu Shim, Junpyo Hur, Sanghyeon Ji, Dongmin Jeon, Jong Min Yuk, Chan-Woo Lee
Bayesian optimization (BO) helps in efficiently navigating complex and high-dimensional design spaces. Recently, it has been applied to materials science to discover novel materials with high performances. However, the application of BO to material design has been hindered by the challenges in handling discrete input variables, such as elements. This study introduces a novel element mapping strategy that encodes elemental identities into chemically meaningful continuous values, enabling the creation of easy-to-predict chemical spaces. This new framework is used to design high-capacity Na3V2(PO4)2F3 cathode materials for sodium-ion batteries, aiming to shift all working voltages into the desired operational voltage window (2.5–4.3 V). The proposed framework successfully suggested 16 optimal compositions within 50 iterations. The proposed approach can overcome the limitation of categorical input and broaden the applicability of BO to a wider range of material discoveries.
{"title":"Element mapping-based Bayesian optimization framework enabling direct materials design: a case study on NASICON-type cathode materials","authors":"Sanghyeon Park, Yoonsu Shim, Junpyo Hur, Sanghyeon Ji, Dongmin Jeon, Jong Min Yuk, Chan-Woo Lee","doi":"10.1038/s41524-026-01958-6","DOIUrl":"https://doi.org/10.1038/s41524-026-01958-6","url":null,"abstract":"Bayesian optimization (BO) helps in efficiently navigating complex and high-dimensional design spaces. Recently, it has been applied to materials science to discover novel materials with high performances. However, the application of BO to material design has been hindered by the challenges in handling discrete input variables, such as elements. This study introduces a novel element mapping strategy that encodes elemental identities into chemically meaningful continuous values, enabling the creation of easy-to-predict chemical spaces. This new framework is used to design high-capacity Na3V2(PO4)2F3 cathode materials for sodium-ion batteries, aiming to shift all working voltages into the desired operational voltage window (2.5–4.3 V). The proposed framework successfully suggested 16 optimal compositions within 50 iterations. The proposed approach can overcome the limitation of categorical input and broaden the applicability of BO to a wider range of material discoveries.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"36 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146196786","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}
Pub Date : 2026-02-10DOI: 10.1038/s41524-025-01924-8
Evan R. Antoniuk, Peggy Li, Nathan Keilbart, Stephen Weitzner, Bhavya Kailkhura, Anna M. Hiszpanski
Although generative models hold promise for discovering molecules with optimized desired properties, they often fail to suggest synthesizable molecules that improve upon the properties of the structures represented in the training distribution. We find that this limitation arises not only from the molecule generation process itself, but also from the poor generalization capabilities of molecular property predictors. We address this challenge by creating a closed-loop molecule generation pipeline with iterative retraining on new quantum chemical simulation data. Compared against static, single-pass generative modeling approaches, only our closed-loop iterative workflow generates molecules with properties extending beyond the training distribution (up to 0.44 standard deviations beyond the original range) and achieves a 79% improvement in out-of-distribution molecule classification accuracy. Furthermore, by conditioning molecular generation on thermodynamic stability data obtained during the iterative loop, the proportion of stable and hence potentially synthesizable molecules generated is 3.5x higher than the next-best model.
{"title":"Active learning enables generation of molecules that advance the known Pareto front","authors":"Evan R. Antoniuk, Peggy Li, Nathan Keilbart, Stephen Weitzner, Bhavya Kailkhura, Anna M. Hiszpanski","doi":"10.1038/s41524-025-01924-8","DOIUrl":"https://doi.org/10.1038/s41524-025-01924-8","url":null,"abstract":"Although generative models hold promise for discovering molecules with optimized desired properties, they often fail to suggest synthesizable molecules that improve upon the properties of the structures represented in the training distribution. We find that this limitation arises not only from the molecule generation process itself, but also from the poor generalization capabilities of molecular property predictors. We address this challenge by creating a closed-loop molecule generation pipeline with iterative retraining on new quantum chemical simulation data. Compared against static, single-pass generative modeling approaches, only our closed-loop iterative workflow generates molecules with properties extending beyond the training distribution (up to 0.44 standard deviations beyond the original range) and achieves a 79% improvement in out-of-distribution molecule classification accuracy. Furthermore, by conditioning molecular generation on thermodynamic stability data obtained during the iterative loop, the proportion of stable and hence potentially synthesizable molecules generated is 3.5x higher than the next-best model.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"111 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146152271","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}
Pub Date : 2026-02-09DOI: 10.1038/s41524-026-01984-4
Dionysios Sema, Ngoc Cuong Nguyen, Spencer Wyant, Nicolas Hadjiconstantinou
Advances in machine-learned interatomic potentials have enabled the prediction of complex material properties with accuracy approaching that of ab initio methods. However, it is unclear how the finite capacity of such models affects their ability to achieve consistent accuracy across diverse thermodynamic conditions without introducing trade-offs. In this paper, we present two computationally efficient interatomic potentials capable of accurately simulating the behavior of hafnium and hafnium dioxide across a very wide variety of thermodynamic conditions. Our approach combines Latin Hypercube and Monte Carlo Sampling for generating diverse data sets, with an extended formulation of the recently-developed environment-adaptive proper orthogonal descriptors. Molecular dynamics simulations show that the resulting potentials accurately reproduce density functional theory results and experimental data for pressure- and temperature-induced phase transitions as well as other properties associated with the materials’ polymorphs and liquid phases. We further showcase the versatility of the environment-adaptive formulation by using our potential to compute the shock Hugoniot of hafnium up to temperatures and pressures of 1 MK and 1 TPa, respectively; good agreement with available experimental data is observed.
{"title":"Environment-adaptive machine-learned force fields for materials under extreme conditions: hafnium and hafnium dioxide polymorphs","authors":"Dionysios Sema, Ngoc Cuong Nguyen, Spencer Wyant, Nicolas Hadjiconstantinou","doi":"10.1038/s41524-026-01984-4","DOIUrl":"https://doi.org/10.1038/s41524-026-01984-4","url":null,"abstract":"Advances in machine-learned interatomic potentials have enabled the prediction of complex material properties with accuracy approaching that of ab initio methods. However, it is unclear how the finite capacity of such models affects their ability to achieve consistent accuracy across diverse thermodynamic conditions without introducing trade-offs. In this paper, we present two computationally efficient interatomic potentials capable of accurately simulating the behavior of hafnium and hafnium dioxide across a very wide variety of thermodynamic conditions. Our approach combines Latin Hypercube and Monte Carlo Sampling for generating diverse data sets, with an extended formulation of the recently-developed environment-adaptive proper orthogonal descriptors. Molecular dynamics simulations show that the resulting potentials accurately reproduce density functional theory results and experimental data for pressure- and temperature-induced phase transitions as well as other properties associated with the materials’ polymorphs and liquid phases. We further showcase the versatility of the environment-adaptive formulation by using our potential to compute the shock Hugoniot of hafnium up to temperatures and pressures of 1 MK and 1 TPa, respectively; good agreement with available experimental data is observed.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"9 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146152253","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}
Pub Date : 2026-02-09DOI: 10.1038/s41524-026-01992-4
Joseph Ngugi Kahiu, Ho Seong Lee
Reducing lattice thermal conductivity (κlatt) is essential for advancing thermoelectric materials. Achieving this requires deeper insight into how microstructural defects influence phonon scattering and the ability to model these interactions effectively via the Debye–Callaway model. However, the mathematical complexity of its nonlinear integral form has historically limited its use to specialists with advanced coding skills. In this study, we present a comprehensive review of the Debye–Callaway model, emphasizing the physical parameters governing nine key phonon scattering mechanisms. Building on this, we introduce a novel, standalone simulation program with an intuitive, slider-based graphical interface that enables real-time visualization of how variations in microstructural parameters affect κlatt. The tool features editable inputs for experimental datasets, temperature ranges, and material-specific parameters, with instant graphical feedback. Through three case studies, we demonstrate its capabilities in deconvoluting defect contributions, identifying modelling errors, and predicting defect impacts, providing a significant advance in phonon transport analysis.
{"title":"Debye-Callaway model simulator: an interactive slider-based program for fitting theoretical and experimental lattice thermal conductivity","authors":"Joseph Ngugi Kahiu, Ho Seong Lee","doi":"10.1038/s41524-026-01992-4","DOIUrl":"https://doi.org/10.1038/s41524-026-01992-4","url":null,"abstract":"Reducing lattice thermal conductivity (κlatt) is essential for advancing thermoelectric materials. Achieving this requires deeper insight into how microstructural defects influence phonon scattering and the ability to model these interactions effectively via the Debye–Callaway model. However, the mathematical complexity of its nonlinear integral form has historically limited its use to specialists with advanced coding skills. In this study, we present a comprehensive review of the Debye–Callaway model, emphasizing the physical parameters governing nine key phonon scattering mechanisms. Building on this, we introduce a novel, standalone simulation program with an intuitive, slider-based graphical interface that enables real-time visualization of how variations in microstructural parameters affect κlatt. The tool features editable inputs for experimental datasets, temperature ranges, and material-specific parameters, with instant graphical feedback. Through three case studies, we demonstrate its capabilities in deconvoluting defect contributions, identifying modelling errors, and predicting defect impacts, providing a significant advance in phonon transport analysis.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"51 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146152254","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}
Pub Date : 2026-02-08DOI: 10.1038/s41524-026-01979-1
Yury Lysogorskiy, Anton Bochkarev, Ralf Drautz
Foundational machine learning interatomic potentials that can accurately and efficiently model a vast range of materials are critical for accelerating atomistic discovery. We introduce universal potentials based on the graph atomic cluster expansion (GRACE) framework, trained on several of the largest available materials datasets. Through comprehensive benchmarks, we demonstrate that the GRACE models establish a new Pareto front for accuracy versus efficiency among foundational interatomic potentials. We further showcase their exceptional versatility by adapting them to specialized tasks and simpler architectures via fine-tuning and knowledge distillation, achieving high accuracy while preventing catastrophic forgetting. This work establishes GRACE as a robust and adaptable foundation for the next generation of atomistic modeling, enabling high-fidelity simulations across the periodic table.
{"title":"Graph atomic cluster expansion for foundational machine learning interatomic potentials","authors":"Yury Lysogorskiy, Anton Bochkarev, Ralf Drautz","doi":"10.1038/s41524-026-01979-1","DOIUrl":"https://doi.org/10.1038/s41524-026-01979-1","url":null,"abstract":"Foundational machine learning interatomic potentials that can accurately and efficiently model a vast range of materials are critical for accelerating atomistic discovery. We introduce universal potentials based on the graph atomic cluster expansion (GRACE) framework, trained on several of the largest available materials datasets. Through comprehensive benchmarks, we demonstrate that the GRACE models establish a new Pareto front for accuracy versus efficiency among foundational interatomic potentials. We further showcase their exceptional versatility by adapting them to specialized tasks and simpler architectures via fine-tuning and knowledge distillation, achieving high accuracy while preventing catastrophic forgetting. This work establishes GRACE as a robust and adaptable foundation for the next generation of atomistic modeling, enabling high-fidelity simulations across the periodic table.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"9 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135609","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}
Pub Date : 2026-02-06DOI: 10.1038/s41524-026-01991-5
Jiaxuan Guo, Simin Nie, Fritz B. Prinz
{"title":"Layer-dependent and gate-tunable Chern numbers in 2D kagome ferromagnet Yb2(C6H4)3 with a large band gap","authors":"Jiaxuan Guo, Simin Nie, Fritz B. Prinz","doi":"10.1038/s41524-026-01991-5","DOIUrl":"https://doi.org/10.1038/s41524-026-01991-5","url":null,"abstract":"","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"94 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135587","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}
Pub Date : 2026-02-06DOI: 10.1038/s41524-026-01987-1
John Mark P. Martirez
{"title":"Optical properties of a diamond NV color center from capped embedded multiconfigurational correlated wavefunction theory","authors":"John Mark P. Martirez","doi":"10.1038/s41524-026-01987-1","DOIUrl":"https://doi.org/10.1038/s41524-026-01987-1","url":null,"abstract":"","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"312 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135588","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：