In material design, traditional crystal structure prediction approaches are expensive as they require extensive structural sampling through expensive energy minimization methods. Emerging artificial intelligence (AI) generative models have shown great promise in rapidly generating realistic crystals, but they typically handle only a few tens of atoms per unit cell. To overcome this limitation, we introduce a symmetry-informed approach, the Local Environment Geometry-Oriented Crystal Generator (LEGO-xtal). Our method generates initial structures using AI models trained on an augmented dataset, and then optimizes them using structure descriptors rather than energy-based optimization. We demonstrate its effectiveness by expanding from 25 known low-energy sp2 carbon allotropes to over 1700, all within 0.5 eV/atom of the ground-state energy of graphite. This framework offers a generalizable strategy for the targeted design of materials with modular building blocks, such as metal-organic frameworks and battery materials.
{"title":"AI-assisted rapid crystal structure generation towards a target local environment","authors":"Osman Goni Ridwan, Sylvain Pitié, Monish Soundar Raj, Dong Dai, Gilles Frapper, Hongfei Xue, Qiang Zhu","doi":"10.1038/s41524-025-01931-9","DOIUrl":"https://doi.org/10.1038/s41524-025-01931-9","url":null,"abstract":"In material design, traditional crystal structure prediction approaches are expensive as they require extensive structural sampling through expensive energy minimization methods. Emerging artificial intelligence (AI) generative models have shown great promise in rapidly generating realistic crystals, but they typically handle only a few tens of atoms per unit cell. To overcome this limitation, we introduce a symmetry-informed approach, the Local Environment Geometry-Oriented Crystal Generator (LEGO-xtal). Our method generates initial structures using AI models trained on an augmented dataset, and then optimizes them using structure descriptors rather than energy-based optimization. We demonstrate its effectiveness by expanding from 25 known low-energy sp2 carbon allotropes to over 1700, all within 0.5 eV/atom of the ground-state energy of graphite. This framework offers a generalizable strategy for the targeted design of materials with modular building blocks, such as metal-organic frameworks and battery materials.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"18 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145903745","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 : 2026-01-05DOI: 10.1038/s41524-025-01926-6
M. Cepeda-Arancibia, F. Brevis, S. J. R. Holt, D. Cortés-Ortuño, H. Fangohr, P. Landeros
Chiral spin textures in ferromagnetic materials with Dzyaloshinskii-Moriya interactions (DMIs) have attracted significant interest in recent years owing to their potential applications in nanodevices. This work focuses on describing stable conical-helix configurations hosted in ultrathin films with DMI and perpendicular anisotropy. These states are studied for different kinds of DMIs, including symmetry classes <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${mathcal{T}}$$</jats:tex-math> <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>T</mml:mi> </mml:math> </jats:alternatives> </jats:inline-formula> , <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${{mathcal{C}}}_{nv}$$</jats:tex-math> <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> </mml:mrow> <mml:mrow> <mml:mi>n</mml:mi> <mml:mi>v</mml:mi> </mml:mrow> </mml:msub> </mml:math> </jats:alternatives> </jats:inline-formula> , isotropic and anisotropic <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${{mathcal{D}}}_{2d}$$</jats:tex-math> <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>D</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>2</mml:mn> <mml:mi>d</mml:mi> </mml:mrow> </mml:msub> </mml:math> </jats:alternatives> </jats:inline-formula> , <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${{mathcal{D}}}_{n}$$</jats:tex-math> <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>D</mml:mi> </mml:mrow> <mml:mrow> <mml:mi>n</mml:mi> </mml:mrow> </mml:msub> </mml:math> </jats:alternatives> </jats:inline-formula> , <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${{mathcal{C}}}_{n}$$</jats:tex-math> <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> </mml:mrow> <mml:mrow> <mml:mi>n</mml:mi> </mml:mrow> </mml:msub> </mml:math> </jats:alternatives> </jats:inline-formula> , and <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${{mathcal{S}}}_{4}$$</jats:tex-math> <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>S</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:math> </jats:alternatives> </jats:inline-formula> . A parameterised analytical model of these configurations is proposed, enabling the determination of optimal parameters characterising the magnetic texture, such as the pitch vector or nucleation field. To substantiate the results, micromagnetic simulations are developed for comparison with the theoretical solutions. Numerical solutions are optimised by implementing finite-difference codes that use next-nearest neighbours and explicit Robin boundary conditions stemming from symmetric exchange and DMI. It is shown that these numerical enhancements decrease anisotropic effects in helical solutions. This study establishes a method to analyse conical-helix textures in thin-film systems with
近年来，具有Dzyaloshinskii-Moriya相互作用的铁磁材料的手性自旋织构由于其在纳米器件中的潜在应用而引起了人们的极大兴趣。这项工作的重点是描述具有DMI和垂直各向异性的超薄膜中稳定的锥形螺旋结构。这些状态研究了不同类型的dmi，包括对称类$${mathcal{T}}$$ T, $${{mathcal{C}}}_{nv}$$ C n v，各向同性和各向异性$${{mathcal{D}}}_{2d}$$ d2 D, $${{mathcal{D}}}_{n}$$ D n, $${{mathcal{C}}}_{n}$$ C n和$${{mathcal{S}}}_{4}$$ s4。提出了这些构型的参数化分析模型，从而确定表征磁性织构的最佳参数，如节距矢量或成核场。为了证实结果，进行了微磁模拟，并与理论解进行了比较。数值解决方案是通过实现有限差分代码，使用下近邻和明确的罗宾边界条件源于对称交换和DMI优化。结果表明，这些数值增强降低了螺旋解的各向异性效应。本研究建立了一种分析具有任意DMI的薄膜系统中的锥形螺旋织构的方法，使用本文开发的开放获取代码可以以更高的精度模拟。
{"title":"Micromagnetics of conical-helix textures in thin films with different kinds of Dzyaloshinskii-Moriya interactions","authors":"M. Cepeda-Arancibia, F. Brevis, S. J. R. Holt, D. Cortés-Ortuño, H. Fangohr, P. Landeros","doi":"10.1038/s41524-025-01926-6","DOIUrl":"https://doi.org/10.1038/s41524-025-01926-6","url":null,"abstract":"Chiral spin textures in ferromagnetic materials with Dzyaloshinskii-Moriya interactions (DMIs) have attracted significant interest in recent years owing to their potential applications in nanodevices. This work focuses on describing stable conical-helix configurations hosted in ultrathin films with DMI and perpendicular anisotropy. These states are studied for different kinds of DMIs, including symmetry classes <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${mathcal{T}}$$</jats:tex-math> <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:mi>T</mml:mi> </mml:math> </jats:alternatives> </jats:inline-formula> , <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${{mathcal{C}}}_{nv}$$</jats:tex-math> <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> </mml:mrow> <mml:mrow> <mml:mi>n</mml:mi> <mml:mi>v</mml:mi> </mml:mrow> </mml:msub> </mml:math> </jats:alternatives> </jats:inline-formula> , isotropic and anisotropic <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${{mathcal{D}}}_{2d}$$</jats:tex-math> <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:msub> <mml:mrow> <mml:mi>D</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>2</mml:mn> <mml:mi>d</mml:mi> </mml:mrow> </mml:msub> </mml:math> </jats:alternatives> </jats:inline-formula> , <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${{mathcal{D}}}_{n}$$</jats:tex-math> <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:msub> <mml:mrow> <mml:mi>D</mml:mi> </mml:mrow> <mml:mrow> <mml:mi>n</mml:mi> </mml:mrow> </mml:msub> </mml:math> </jats:alternatives> </jats:inline-formula> , <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${{mathcal{C}}}_{n}$$</jats:tex-math> <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> </mml:mrow> <mml:mrow> <mml:mi>n</mml:mi> </mml:mrow> </mml:msub> </mml:math> </jats:alternatives> </jats:inline-formula> , and <jats:inline-formula> <jats:alternatives> <jats:tex-math>$${{mathcal{S}}}_{4}$$</jats:tex-math> <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:msub> <mml:mrow> <mml:mi>S</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:math> </jats:alternatives> </jats:inline-formula> . A parameterised analytical model of these configurations is proposed, enabling the determination of optimal parameters characterising the magnetic texture, such as the pitch vector or nucleation field. To substantiate the results, micromagnetic simulations are developed for comparison with the theoretical solutions. Numerical solutions are optimised by implementing finite-difference codes that use next-nearest neighbours and explicit Robin boundary conditions stemming from symmetric exchange and DMI. It is shown that these numerical enhancements decrease anisotropic effects in helical solutions. This study establishes a method to analyse conical-helix textures in thin-film systems with ","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"27 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145903108","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 : 2026-01-03DOI: 10.1038/s41524-025-01929-3
Anyang Peng, Chun Cai, Mingyu Guo, Duo Zhang, Chengqian Zhang, Wanrun Jiang, Yinan Wang, Antoine Loew, Chengkun Wu, Weinan E, Linfeng Zhang, Han Wang
Large Atomistic Models (LAMs) have undergone remarkable progress recently, emerging as universal or fundamental representations of the potential energy surface defined by the first-principles calculations of atomistic systems. However, our understanding of the extent to which these models achieve true universality, as well as their comparative performance across different models, remains limited. This gap is largely due to the lack of comprehensive benchmarks capable of evaluating the effectiveness of LAMs as approximations to the universal potential energy surface. In this study, we introduce LAMBench, a benchmarking system designed to evaluate LAMs in terms of their generalizability, adaptability, and applicability. These attributes are crucial for deploying LAMs as ready-to-use tools across a diverse array of scientific discovery contexts. We benchmark ten state-of-the-art LAMs released prior to August 1, 2025, using LAMBench. Our findings reveal a significant gap between the current LAMs and the ideal universal potential energy surface. They also highlight the need for incorporating cross-domain training data, supporting multi-fidelity modeling, and ensuring the models’ conservativeness and differentiability. As a dynamic and extensible platform, LAMBench is intended to continuously evolve, thereby facilitating the development of robust and generalizable LAMs capable of significantly advancing scientific research. The LAMBench code is open-sourced at https://github.com/deepmodeling/lambench, and an interactive leaderboard is available at https://www.aissquare.com/openlam?tab=Benchmark.
{"title":"LAMBench: a benchmark for large atomistic models","authors":"Anyang Peng, Chun Cai, Mingyu Guo, Duo Zhang, Chengqian Zhang, Wanrun Jiang, Yinan Wang, Antoine Loew, Chengkun Wu, Weinan E, Linfeng Zhang, Han Wang","doi":"10.1038/s41524-025-01929-3","DOIUrl":"https://doi.org/10.1038/s41524-025-01929-3","url":null,"abstract":"Large Atomistic Models (LAMs) have undergone remarkable progress recently, emerging as universal or fundamental representations of the potential energy surface defined by the first-principles calculations of atomistic systems. However, our understanding of the extent to which these models achieve true universality, as well as their comparative performance across different models, remains limited. This gap is largely due to the lack of comprehensive benchmarks capable of evaluating the effectiveness of LAMs as approximations to the universal potential energy surface. In this study, we introduce LAMBench, a benchmarking system designed to evaluate LAMs in terms of their generalizability, adaptability, and applicability. These attributes are crucial for deploying LAMs as ready-to-use tools across a diverse array of scientific discovery contexts. We benchmark ten state-of-the-art LAMs released prior to August 1, 2025, using LAMBench. Our findings reveal a significant gap between the current LAMs and the ideal universal potential energy surface. They also highlight the need for incorporating cross-domain training data, supporting multi-fidelity modeling, and ensuring the models’ conservativeness and differentiability. As a dynamic and extensible platform, LAMBench is intended to continuously evolve, thereby facilitating the development of robust and generalizable LAMs capable of significantly advancing scientific research. The LAMBench code is open-sourced at https://github.com/deepmodeling/lambench, and an interactive leaderboard is available at https://www.aissquare.com/openlam?tab=Benchmark.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"15 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2026-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145893788","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 : 2025-12-30DOI: 10.1038/s41524-025-01918-6
Hossein Mashhadimoslem, Peyman Karimi, Ali Elkamel, Aiping Yu
{"title":"Toward high entropy material discovery for energy applications using computational and machine learning methods","authors":"Hossein Mashhadimoslem, Peyman Karimi, Ali Elkamel, Aiping Yu","doi":"10.1038/s41524-025-01918-6","DOIUrl":"https://doi.org/10.1038/s41524-025-01918-6","url":null,"abstract":"","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"94 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145893798","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 : 2025-12-29DOI: 10.1038/s41524-025-01925-7
Namjung Kim, Dongseok Lee, Jongbin Yu, Sung Woong Cho, Dosung Lee, Yesol Park, Youngjoon Hong
Advances in material functionalities drive innovations across various fields, where metamaterials—defined by structure rather than composition—are leading the way. Despite the rise of artificial intelligence (AI)-driven design strategies, their impact is limited by task-specific retraining, poor out-of-distribution (OOD) generalization, and the need for separate models for forward and inverse design. To address these limitations, we introduce the Metamaterial FOundation Model (MetaFO), a Bayesian transformer-based foundation model inspired by large language models. MetaFO learns the underlying mechanics of metamaterials, enabling probabilistic, zero-shot predictions across diverse, unseen combinations of material properties and structural responses. It also excels in nonlinear inverse design, even under OOD conditions. By treating metamaterials as an operator that maps material properties to structural responses, MetaFO uncovers intricate structure-property relationships and significantly expands the design space. This scalable and generalizable framework marks a paradigm shift in AI-driven metamaterial discovery, paving the way for next-generation innovations.
{"title":"Toward a robust and generalizable metamaterial foundation model","authors":"Namjung Kim, Dongseok Lee, Jongbin Yu, Sung Woong Cho, Dosung Lee, Yesol Park, Youngjoon Hong","doi":"10.1038/s41524-025-01925-7","DOIUrl":"https://doi.org/10.1038/s41524-025-01925-7","url":null,"abstract":"Advances in material functionalities drive innovations across various fields, where metamaterials—defined by structure rather than composition—are leading the way. Despite the rise of artificial intelligence (AI)-driven design strategies, their impact is limited by task-specific retraining, poor out-of-distribution (OOD) generalization, and the need for separate models for forward and inverse design. To address these limitations, we introduce the Metamaterial FOundation Model (MetaFO), a Bayesian transformer-based foundation model inspired by large language models. MetaFO learns the underlying mechanics of metamaterials, enabling probabilistic, zero-shot predictions across diverse, unseen combinations of material properties and structural responses. It also excels in nonlinear inverse design, even under OOD conditions. By treating metamaterials as an operator that maps material properties to structural responses, MetaFO uncovers intricate structure-property relationships and significantly expands the design space. This scalable and generalizable framework marks a paradigm shift in AI-driven metamaterial discovery, paving the way for next-generation innovations.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"36 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145895481","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}
Sintered neodymium-iron-boron (NdFeB) magnets are indispensable in high-performance applications, but their optimization is challenged by complex structure-property relationships and limited data. In this work, we curate the first multi-domain database for this system (1994 industrial and academic samples) and systematically evaluate active learning (AL) strategies on classical and quantum-enhanced regressors. First, our “domain-aware” analysis reveals quantitative differences in design heuristics between industrial and academic data. Second, we present a methodological blueprint for integrating quantum kernel regression into an AL framework using a bootstrapped ensemble for uncertainty quantification. Finally, and most significantly, our results reveal AL effectiveness is strongly model-dependent. Its advantage ranges from significant acceleration (Random Forest, SVR) to being diminished (XGBoost), or even inverted—proving detrimental compared to random sampling—as shown in our quantum-enhanced SVR case study. This finding provides critical new insights for the strategic application of machine learning in materials discovery.
{"title":"A framework of active data selection and quantum-enhanced regression for predicting magnetic properties of sintered NdFeB magnets","authors":"Lianhua He, Qichao Liang, Kaifan Pan, Tianyan Li, Qiang Ma, Xin Wang, Haibo Xu, Yingjin Ma","doi":"10.1038/s41524-025-01914-w","DOIUrl":"https://doi.org/10.1038/s41524-025-01914-w","url":null,"abstract":"Sintered neodymium-iron-boron (NdFeB) magnets are indispensable in high-performance applications, but their optimization is challenged by complex structure-property relationships and limited data. In this work, we curate the first multi-domain database for this system (1994 industrial and academic samples) and systematically evaluate active learning (AL) strategies on classical and quantum-enhanced regressors. First, our “domain-aware” analysis reveals quantitative differences in design heuristics between industrial and academic data. Second, we present a methodological blueprint for integrating quantum kernel regression into an AL framework using a bootstrapped ensemble for uncertainty quantification. Finally, and most significantly, our results reveal AL effectiveness is strongly model-dependent. Its advantage ranges from significant acceleration (Random Forest, SVR) to being diminished (XGBoost), or even inverted—proving detrimental compared to random sampling—as shown in our quantum-enhanced SVR case study. This finding provides critical new insights for the strategic application of machine learning in materials discovery.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"24 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145895519","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}
Theoretical simulation of phase change materials such as Ge-Sb-Te has suffered from two methodological issues. On the one hand, there is a lack of efficient band gap correction method for density functional theory that is suitable for these materials in both crystalline and amorphous phases, while maintaining the computational complexity comparable to local density approximation. On the other hand, analysis of the coordination number in amorphous phases relies on an integration involving the radial distribution function, which adds to the complexity. In this work, we find that the shell DFT-1/2 method offers overall band gap accuracy for phase-change materials comparable to that of the HSE06 hybrid functional, while its computational cost is orders of magnitude lower. Moreover, the mixed length-angle coordination number theory enables calculating the coordination numbers in the amorphous phase directly from the structure, with definite outcomes. The two methodologies could be helpful for high-throughput simulations of phase change materials.
{"title":"High-efficiency computational methodologies for electronic properties and structural characterization of Ge-Sb-Te based phase-change materials","authors":"Shanzhong Xie, Kan-Hao Xue, Shaojie Yuan, Zijian Zhou, Shengxin Yang, Heng Yu, Rongchuan Gu, Ming Xu, Xiangshui Miao","doi":"10.1038/s41524-025-01922-w","DOIUrl":"https://doi.org/10.1038/s41524-025-01922-w","url":null,"abstract":"Theoretical simulation of phase change materials such as Ge-Sb-Te has suffered from two methodological issues. On the one hand, there is a lack of efficient band gap correction method for density functional theory that is suitable for these materials in both crystalline and amorphous phases, while maintaining the computational complexity comparable to local density approximation. On the other hand, analysis of the coordination number in amorphous phases relies on an integration involving the radial distribution function, which adds to the complexity. In this work, we find that the shell DFT-1/2 method offers overall band gap accuracy for phase-change materials comparable to that of the HSE06 hybrid functional, while its computational cost is orders of magnitude lower. Moreover, the mixed length-angle coordination number theory enables calculating the coordination numbers in the amorphous phase directly from the structure, with definite outcomes. The two methodologies could be helpful for high-throughput simulations of phase change materials.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"86 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145893799","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}
With the rapid advancement of AI technologies, generative models have been increasingly employed in the exploration of novel materials. By integrating traditional computational approaches such as density functional theory (DFT) and molecular dynamics (MD), existing generative models — including diffusion models and autoregressive models — have demonstrated remarkable potential in the discovery of novel materials. However, their efficiency in goal-directed materials design remains suboptimal. In this work we developed a highly transferable, efficient and robust conditional generation framework, PODGen, by integrating a general generative model with multiple property prediction models. Based on PODGen, we designed a workflow for the high-throughput crystals conditional generation which is used to search new topological insulators (TIs). Our results show that the success rate of generating TIs using our framework is approximately 5 times higher than that of the unconstrained approach. This demonstrates that conditional generation significantly enhances the efficiency of targeted material discovery. Using this method, we generated tens of thousands of new topological materials and conducted further first-principles calculations on those with promising application potential. Furthermore, we identified promising, synthesizable topological (crystalline) insulators such as CsHgSb, NaLaB12, Bi4Sb2Se3, Be3Ta2Si and Be2W.
{"title":"Materials discovery acceleration by using conditional generative methodology","authors":"Caiyuan Ye, Yuzhi Wang, Xintian Xie, Tiannian Zhu, Jiaxuan Liu, Yuqing He, Lili Zhang, Junwei Zhang, Zhong Fang, Lei Wang, Zhipan Liu, Hongming Weng, Quansheng Wu","doi":"10.1038/s41524-025-01930-w","DOIUrl":"https://doi.org/10.1038/s41524-025-01930-w","url":null,"abstract":"With the rapid advancement of AI technologies, generative models have been increasingly employed in the exploration of novel materials. By integrating traditional computational approaches such as density functional theory (DFT) and molecular dynamics (MD), existing generative models — including diffusion models and autoregressive models — have demonstrated remarkable potential in the discovery of novel materials. However, their efficiency in goal-directed materials design remains suboptimal. In this work we developed a highly transferable, efficient and robust conditional generation framework, PODGen, by integrating a general generative model with multiple property prediction models. Based on PODGen, we designed a workflow for the high-throughput crystals conditional generation which is used to search new topological insulators (TIs). Our results show that the success rate of generating TIs using our framework is approximately 5 times higher than that of the unconstrained approach. This demonstrates that conditional generation significantly enhances the efficiency of targeted material discovery. Using this method, we generated tens of thousands of new topological materials and conducted further first-principles calculations on those with promising application potential. Furthermore, we identified promising, synthesizable topological (crystalline) insulators such as CsHgSb, NaLaB12, Bi4Sb2Se3, Be3Ta2Si and Be2W.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"11 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145893800","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 : 2025-12-24DOI: 10.1038/s41524-025-01920-y
Zhi Li, Huiju Lee, Chris Wolverton, Yi Xia
Accurate first-principles prediction of lattice thermal conductivity (κL) remains challenging in identifying materials with extreme thermal behavior. While the harmonic approximation with three-phonon scattering (HA + 3ph) is now routine, reliable κL prediction often requires higher-order anharmonic effects, including self-consistent phonon renormalization, three- and four-phonon scattering, and off-diagonal heat flux (SCPH + 3, 4ph + OD). We present a state-of-the-art high-throughput workflow that unifies these effects and apply it to 773 cubic and tetragonal crystals spanning diverse chemistries and structures. From 562 dynamically stable compounds, we assess the hierarchical impacts of higher-order anharmonicity. For around 60% of materials, HA + 3ph predictions closely match those from SCPH + 3, 4ph + OD. SCPH generally increases κL, by over 8 times in extreme cases, whereas four-phonon scattering universally suppresses κL, sometimes to 15% of the HA + 3ph value. Off-diagonal contributions are negligible in high-κL systems but can rival diagonal terms in highly anharmonic low-κL compounds. We highlight four case studies, Rb2TlAlH6, Cu3VSe4, CuBr, and KTlCl4, that exhibit distinct extreme behaviors. This work delivers not only a robust workflow for high-fidelity κL dataset but also a quantitative framework to determine when higher-order effects are essential. The hierarchy of κL results, from the HA + 3ph to SCPH + 3, 4ph + OD level, offers a scalable, interpretable route to discovering next-generation extreme thermal materials.
{"title":"High-throughput computational framework for high-order anharmonic thermal transport in cubic and tetragonal crystals","authors":"Zhi Li, Huiju Lee, Chris Wolverton, Yi Xia","doi":"10.1038/s41524-025-01920-y","DOIUrl":"https://doi.org/10.1038/s41524-025-01920-y","url":null,"abstract":"Accurate first-principles prediction of lattice thermal conductivity (κL) remains challenging in identifying materials with extreme thermal behavior. While the harmonic approximation with three-phonon scattering (HA + 3ph) is now routine, reliable κL prediction often requires higher-order anharmonic effects, including self-consistent phonon renormalization, three- and four-phonon scattering, and off-diagonal heat flux (SCPH + 3, 4ph + OD). We present a state-of-the-art high-throughput workflow that unifies these effects and apply it to 773 cubic and tetragonal crystals spanning diverse chemistries and structures. From 562 dynamically stable compounds, we assess the hierarchical impacts of higher-order anharmonicity. For around 60% of materials, HA + 3ph predictions closely match those from SCPH + 3, 4ph + OD. SCPH generally increases κL, by over 8 times in extreme cases, whereas four-phonon scattering universally suppresses κL, sometimes to 15% of the HA + 3ph value. Off-diagonal contributions are negligible in high-κL systems but can rival diagonal terms in highly anharmonic low-κL compounds. We highlight four case studies, Rb2TlAlH6, Cu3VSe4, CuBr, and KTlCl4, that exhibit distinct extreme behaviors. This work delivers not only a robust workflow for high-fidelity κL dataset but also a quantitative framework to determine when higher-order effects are essential. The hierarchy of κL results, from the HA + 3ph to SCPH + 3, 4ph + OD level, offers a scalable, interpretable route to discovering next-generation extreme thermal materials.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"8 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145814067","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 : 2025-12-24DOI: 10.1038/s41524-025-01917-7
Yunhua Lu, Mingyue Chen, Qingwei Zhang, Junan Zhang, Chao Zhang, Shiai Xu, Qiuyan Bi
The targeted design of functional materials often requires the concurrent optimization of multiple interdependent properties. For boron-doped graphene (BDG), both the band gap and work function critically influence performance in electronic and catalytic applications, yet existing machine learning (ML) approaches typically focus on single-property prediction and rely on hand-crafted features, limiting their generality. Here we present an adaptive edge-aware graph convolutional neural network with multi-task learning (AEGCNN-MTL) for simultaneous prediction of multiple material properties. On a DFT-computed BDG dataset of 2613 structures, AEGCNN-MTL achieved high accuracy (R² = 0.9905 for band gap and 0.9778 for work function), and under identical training budgets, outperformed representative single-task GNN baselines. When transferred to the QM9 benchmark, the framework delivered competitive performance across 12 diverse quantum chemical properties, demonstrating strong generalization capability. These results highlight the potential of AEGCNN-MTL as a scalable and accurate tool for high-throughput, multi-property screening and the data-driven discovery of multifunctional materials.
{"title":"Adaptive edge-aware graph convolutional with multi-task learning for simultaneous prediction of material properties","authors":"Yunhua Lu, Mingyue Chen, Qingwei Zhang, Junan Zhang, Chao Zhang, Shiai Xu, Qiuyan Bi","doi":"10.1038/s41524-025-01917-7","DOIUrl":"https://doi.org/10.1038/s41524-025-01917-7","url":null,"abstract":"The targeted design of functional materials often requires the concurrent optimization of multiple interdependent properties. For boron-doped graphene (BDG), both the band gap and work function critically influence performance in electronic and catalytic applications, yet existing machine learning (ML) approaches typically focus on single-property prediction and rely on hand-crafted features, limiting their generality. Here we present an adaptive edge-aware graph convolutional neural network with multi-task learning (AEGCNN-MTL) for simultaneous prediction of multiple material properties. On a DFT-computed BDG dataset of 2613 structures, AEGCNN-MTL achieved high accuracy (R² = 0.9905 for band gap and 0.9778 for work function), and under identical training budgets, outperformed representative single-task GNN baselines. When transferred to the QM9 benchmark, the framework delivered competitive performance across 12 diverse quantum chemical properties, demonstrating strong generalization capability. These results highlight the potential of AEGCNN-MTL as a scalable and accurate tool for high-throughput, multi-property screening and the data-driven discovery of multifunctional materials.","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"28 1","pages":""},"PeriodicalIF":9.7,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145814066","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：