Autonomous material exploration systems that integrate robotics,material simulations,and machine learning have advanced rapidly in recent years.Although their number continues to grow,these systemscurrently operate in...Autonomous material exploration systems that integrate robotics,material simulations,and machine learning have advanced rapidly in recent years.Although their number continues to grow,these systemscurrently operate in isolation,limiting the overall efficiency of autonomous material discovery.In analogy to how human researchers advance materials science by sharing knowledge and collaborating,autonomous systems can also benefit from networking and knowledge exchange.Here,we propose a framework in which multiple autonomous material exploration systems form a network via transfer learning,selectively utilizing relevant knowledge from other systems in real time.We demonstrate this approach using three distinct autonomous systems and show that such networking significantly enhances the efficiency of material discovery.Our results suggest that the proposed framework can enable the development of large-scale autonomous material exploration networks,ultimately accelerating progress in material development.展开更多
The discovery of new superconducting materials,particularly those exhibiting high critical temperature(Tc),has been a vibrant area of study within the field of condensed matter physics.Conventional approaches primaril...The discovery of new superconducting materials,particularly those exhibiting high critical temperature(Tc),has been a vibrant area of study within the field of condensed matter physics.Conventional approaches primarily rely on physical intuition to search for potential superconductors within the existing databases.However,the known materials only scratch the surface of the extensive array of possibilities within the realm of materials.展开更多
Prof.Ye Hengqiang is a pioneer in China,probing the atomic imagery of solids.He has been engaged in this field for more than a decade and attained a series of important results. His work advances the theory and relate...Prof.Ye Hengqiang is a pioneer in China,probing the atomic imagery of solids.He has been engaged in this field for more than a decade and attained a series of important results. His work advances the theory and related techniques when he explores the fine structures of materials on the atomic scale,contributing much to the development of new materials with the aid of electron metalloscopy. In 1963, Ye graduated from the Beijing College of Iron & Steel and was admitted as a post-graduate to the tutelage of Prof.Guo Kexin,a renowned Chinese metal-展开更多
The development of new materials exhibiting large anomalous Hall effect(AHE)is essential for realizing highly efficient spintronic devices.However,this development has been a time-consuming process due to the combinat...The development of new materials exhibiting large anomalous Hall effect(AHE)is essential for realizing highly efficient spintronic devices.However,this development has been a time-consuming process due to the combinatorial explosion for multielement systems and limited experimental throughput.In this study,we identify new materials exhibiting large AHE in heavy-metal-substituted Fe-based alloys using a high-throughput materials exploration method that combines deposition of compositionspread films using combinatorial sputtering,photoresist-free facile multiple-device fabrication using laser patterning,simultaneous AHE measurement of multiple devices using a customized multichannel probe,and prediction of candidate materials using machine learning.Based on experimental AHE data on Fe-based binary system alloyed with various single heavy metals,we perform machine learning analysis to predict the Fe-based ternary system containing two heavy metals for larger AHE.We experimentally confirm larger AHE in the predicted Fe–Ir–Pt system.Using scaling analysis,we reveal that the enhancement of AHE originates from the extrinsic contribution.展开更多
The exploration of high-performance materials presents a fundamental challenge in materials science,particularly in predicting properties for materials beyond the known range of target property values(extrapolation).T...The exploration of high-performance materials presents a fundamental challenge in materials science,particularly in predicting properties for materials beyond the known range of target property values(extrapolation).This study formally investigated the interpolation-extrapolation trade-off phenomenon in the prediction capabilities of machine learning(ML)models.A new ML scheme was proposed,featuring a newly developed ML model and forward cross-validation-based hyperparameter optimization,which demonstrated superior extrapolation prediction across multiple materials datasets.Based on this ML scheme,multi-objective optimization was performed to systematically identify lightweight Mg-Zn-Al alloys with both high bulk modulus and high Debye temperature.Subsequently,the designed alloys were validated through density functional theory calculations.Furthermore,a three-category classification strategy was summarized through the dual-driven approach combining domain knowledge and data,emphasizing their synergistic potential for materials discovery.The practical framework developed in this study provides a novel research perspective for exploring high-performance materials.展开更多
Machine learning(ML)is widely used to explore crystal materials and predict their properties.However,the training is time-consuming for deep-learning models,and the regression process is a black box that is hard to in...Machine learning(ML)is widely used to explore crystal materials and predict their properties.However,the training is time-consuming for deep-learning models,and the regression process is a black box that is hard to interpret.Also,the preprocess to transfer a crystal structure into the input of ML,called descriptor,needs to be designed carefully.To efficiently predict important properties of materials,we propose an approach based on ensemble learning consisting of regression trees to predict formation energy and elastic constants based on small-size datasets of carbon allotropes as an example.Without using any descriptor,the inputs are the properties calculated by molecular dynamics with nine different classical interatomic potentials.Overall,the results from ensemble learning are more accurate than those from classical interatomic potentials,and ensemble learning can capture the relatively accurate properties from the nine classical potentials as criteria for predicting the final properties.展开更多
Graphene grids exhibit exceptional loading capacity for macromolecules,single atoms,and nanoparticles,offering significant potential for exploring the structure and properties of various materials at the nanoscale.How...Graphene grids exhibit exceptional loading capacity for macromolecules,single atoms,and nanoparticles,offering significant potential for exploring the structure and properties of various materials at the nanoscale.However,challenges such as carbon film rupture,contamination,and uneven graphene film coverage frequently occur during grid fabrication.Here wepropose a dual-stage deep learning model integrating U-Net and an enhanced YOLO11 architecture,enabling efficient and accurate defect detection and graphene coverage quantification.A tailored data augmentation strategy expanded the initial defect dataset by more than an order of magnitude,which directly contributed to an overall 11.72%improvement across the model’s performance metrics.With the integration of the multi-scale convolutional attention(MSCA)module and the slicing-aided hyper inference(SAHI)method,the model achieved a 0.67%mean absolute percentage error(MAPE),while reducing the average detection time from 26.6 to 0.1 min per image.The proposed model holds strong potential for extension to various material characterization image analysis tasks,providing a scalable strategy for high-throughput image processing that bridges fundamental research with industrialscale applications.展开更多
文摘Autonomous material exploration systems that integrate robotics,material simulations,and machine learning have advanced rapidly in recent years.Although their number continues to grow,these systemscurrently operate in isolation,limiting the overall efficiency of autonomous material discovery.In analogy to how human researchers advance materials science by sharing knowledge and collaborating,autonomous systems can also benefit from networking and knowledge exchange.Here,we propose a framework in which multiple autonomous material exploration systems form a network via transfer learning,selectively utilizing relevant knowledge from other systems in real time.We demonstrate this approach using three distinct autonomous systems and show that such networking significantly enhances the efficiency of material discovery.Our results suggest that the proposed framework can enable the development of large-scale autonomous material exploration networks,ultimately accelerating progress in material development.
基金financially supported by the National Natural Science Foundation of China(Grant Nos.62476278,12434009,and 12204533)the National Key R&D Program of China(Grant No.2024YFA1408601)the Innovation Program for Quantum Science and Technology(Grant No.2021ZD0302402)。
文摘The discovery of new superconducting materials,particularly those exhibiting high critical temperature(Tc),has been a vibrant area of study within the field of condensed matter physics.Conventional approaches primarily rely on physical intuition to search for potential superconductors within the existing databases.However,the known materials only scratch the surface of the extensive array of possibilities within the realm of materials.
文摘Prof.Ye Hengqiang is a pioneer in China,probing the atomic imagery of solids.He has been engaged in this field for more than a decade and attained a series of important results. His work advances the theory and related techniques when he explores the fine structures of materials on the atomic scale,contributing much to the development of new materials with the aid of electron metalloscopy. In 1963, Ye graduated from the Beijing College of Iron & Steel and was admitted as a post-graduate to the tutelage of Prof.Guo Kexin,a renowned Chinese metal-
基金supported by JST CREST(Grant No.JPMJCR21O1)JST ERATO“Magnetic Thermal Management Materials Project”(Grant No.JPMJER2201)+1 种基金MEXT Program:Data Creation and Utilization-Type Material Research and Development Project(Digital Transformation Initiative Center for Magnetic Materials.Grant No.JPMXP1122715503)JSPS KAKENHI Grants-in-Aid for Scientific Research(B)(Grant Nos.JP21H01608 and JP24K00932).
文摘The development of new materials exhibiting large anomalous Hall effect(AHE)is essential for realizing highly efficient spintronic devices.However,this development has been a time-consuming process due to the combinatorial explosion for multielement systems and limited experimental throughput.In this study,we identify new materials exhibiting large AHE in heavy-metal-substituted Fe-based alloys using a high-throughput materials exploration method that combines deposition of compositionspread films using combinatorial sputtering,photoresist-free facile multiple-device fabrication using laser patterning,simultaneous AHE measurement of multiple devices using a customized multichannel probe,and prediction of candidate materials using machine learning.Based on experimental AHE data on Fe-based binary system alloyed with various single heavy metals,we perform machine learning analysis to predict the Fe-based ternary system containing two heavy metals for larger AHE.We experimentally confirm larger AHE in the predicted Fe–Ir–Pt system.Using scaling analysis,we reveal that the enhancement of AHE originates from the extrinsic contribution.
基金supported by National Natural Science Foundation of China(No.51671075 and 51971086)Natural Science Foundation of Heilongjiang Province of China(No.LH2022E081).
文摘The exploration of high-performance materials presents a fundamental challenge in materials science,particularly in predicting properties for materials beyond the known range of target property values(extrapolation).This study formally investigated the interpolation-extrapolation trade-off phenomenon in the prediction capabilities of machine learning(ML)models.A new ML scheme was proposed,featuring a newly developed ML model and forward cross-validation-based hyperparameter optimization,which demonstrated superior extrapolation prediction across multiple materials datasets.Based on this ML scheme,multi-objective optimization was performed to systematically identify lightweight Mg-Zn-Al alloys with both high bulk modulus and high Debye temperature.Subsequently,the designed alloys were validated through density functional theory calculations.Furthermore,a three-category classification strategy was summarized through the dual-driven approach combining domain knowledge and data,emphasizing their synergistic potential for materials discovery.The practical framework developed in this study provides a novel research perspective for exploring high-performance materials.
基金Funding for this research was provided by National Science Foundation (NSF) under award numbers CMMI-1826439, CMMI-1762792 and CMMI-1825739. This support is greatly acknowledged. The authors also thank the Agave Computer Cluster of ASU for providing the computational resources.
文摘Machine learning(ML)is widely used to explore crystal materials and predict their properties.However,the training is time-consuming for deep-learning models,and the regression process is a black box that is hard to interpret.Also,the preprocess to transfer a crystal structure into the input of ML,called descriptor,needs to be designed carefully.To efficiently predict important properties of materials,we propose an approach based on ensemble learning consisting of regression trees to predict formation energy and elastic constants based on small-size datasets of carbon allotropes as an example.Without using any descriptor,the inputs are the properties calculated by molecular dynamics with nine different classical interatomic potentials.Overall,the results from ensemble learning are more accurate than those from classical interatomic potentials,and ensemble learning can capture the relatively accurate properties from the nine classical potentials as criteria for predicting the final properties.
基金supported by National Key Research and Development Program of China(2024YFB4709300)the National Natural Science Foundation of China(No.52130501,52505289)+1 种基金Zhejiang provincial teams of leading talents in Innovation and Entrepreneurship(2024R01002)Guizhou Provincial Science and Technology Projects(XKBF[2025]014,BQW[2024]010).
文摘Graphene grids exhibit exceptional loading capacity for macromolecules,single atoms,and nanoparticles,offering significant potential for exploring the structure and properties of various materials at the nanoscale.However,challenges such as carbon film rupture,contamination,and uneven graphene film coverage frequently occur during grid fabrication.Here wepropose a dual-stage deep learning model integrating U-Net and an enhanced YOLO11 architecture,enabling efficient and accurate defect detection and graphene coverage quantification.A tailored data augmentation strategy expanded the initial defect dataset by more than an order of magnitude,which directly contributed to an overall 11.72%improvement across the model’s performance metrics.With the integration of the multi-scale convolutional attention(MSCA)module and the slicing-aided hyper inference(SAHI)method,the model achieved a 0.67%mean absolute percentage error(MAPE),while reducing the average detection time from 26.6 to 0.1 min per image.The proposed model holds strong potential for extension to various material characterization image analysis tasks,providing a scalable strategy for high-throughput image processing that bridges fundamental research with industrialscale applications.
