Using machine learning to predict and design materials is an important mean of accelerating material development.One way to improve the accuracy of machine learning predictions is to introduce material structures as d...Using machine learning to predict and design materials is an important mean of accelerating material development.One way to improve the accuracy of machine learning predictions is to introduce material structures as descriptors.However,thecomplexity ofcomputing material structures limits the practical use of these models.To address this challenge and improve prediction accuracy in small data sets,we develop a generative network framework:Elemental Features enhanced and Transferring corrected data augmentation in Generative Adversarial Networks(EFTGAN).Combining the elemental convolution technique with Generative Adversarial Networks(GAN),EFTGAN provides a robust and efficient approach for generating data containing elemental and structural information that can be used not only for data augmentation to improve model accuracy,but also for prediction when the structures are unknown.Applying this framework to the FeNiCoCrMn/Pd high-entropy alloys,we successfully improve the prediction accuracy in a small data set and predict the concentrationdependent formation energies,lattices,and magnetic moments in quinary systems.This study provides a new algorithm to improve the performance and usability of deep learning with structures as inputs,which is effective and accurate for the prediction and development of materials for small data sets.展开更多
Drought can greatly impact the biodiversity of an ecosystem and play a crucial role in regulating its functioning.However,the specific mechanisms by which drought mediate the biodiversity effect(BE)on community biomas...Drought can greatly impact the biodiversity of an ecosystem and play a crucial role in regulating its functioning.However,the specific mechanisms by which drought mediate the biodiversity effect(BE)on community biomass in above-and belowground through functional traits remain poorly understood.Here,we conducted a common garden experiment in a greenhouse,which included two plant species richness levels and two water addition levels,to analyze the effects of biodiversity on aboveground biomass(AGB),belowground biomass(BGB)and total biomass(TB),and to quantify the relationship between BEs and functional traits under drought conditions.Our analysis focused on partitioning BEs into above-and belowground complementarity effect(CE)and selection effect(SE)at the species level,which allowed us to better understand the impacts of biodiversity on community biomass and the underlying mechanisms.Our results showed that plant species richness stimulated AGB,BGB and TB through CEs.Drought decreased AGB,BGB and TB,simultaneously.In addition,the aboveground CE was positively associated with the variation in plant height.SEs in above-and belowground were negatively correlated with the community mean plant height and root length,respectively.Furthermore,drought weakened the aboveground CE by decreasing variation in plant height,resulting in a reduction in AGB and TB.Our findings demonstrate that the complementarity of species is an important regulator of community biomass in above-and belowground,the dynamics of biomass under environmental stress are associated with the response of sensitive compartments.展开更多
基金supported by the National Natural Science Foundation ofChina(grant no.92270104)partially by Grant-in-Aids for Scientific Research on innovative Areas on High Entropy Alloys through the grant number P18H05454 of JSPS,Japan.Authors acknowledge the Center of High Performance Computing,Tsinghua University and the Center for Computational Materials Science of the Institute for Materials Research,Tohoku University for the support of the supercomputing facilities.Figure 1 is drawn by FigDraw.
文摘Using machine learning to predict and design materials is an important mean of accelerating material development.One way to improve the accuracy of machine learning predictions is to introduce material structures as descriptors.However,thecomplexity ofcomputing material structures limits the practical use of these models.To address this challenge and improve prediction accuracy in small data sets,we develop a generative network framework:Elemental Features enhanced and Transferring corrected data augmentation in Generative Adversarial Networks(EFTGAN).Combining the elemental convolution technique with Generative Adversarial Networks(GAN),EFTGAN provides a robust and efficient approach for generating data containing elemental and structural information that can be used not only for data augmentation to improve model accuracy,but also for prediction when the structures are unknown.Applying this framework to the FeNiCoCrMn/Pd high-entropy alloys,we successfully improve the prediction accuracy in a small data set and predict the concentrationdependent formation energies,lattices,and magnetic moments in quinary systems.This study provides a new algorithm to improve the performance and usability of deep learning with structures as inputs,which is effective and accurate for the prediction and development of materials for small data sets.
基金supported by the Natural Science Foundation of Beijing Municipality(5232006)the Beijing Academy of Agriculture and Forestry Sciences Special Project on Hi-Tech Innovation Capacity(QNJJ202217 and KJCX20230305).
文摘Drought can greatly impact the biodiversity of an ecosystem and play a crucial role in regulating its functioning.However,the specific mechanisms by which drought mediate the biodiversity effect(BE)on community biomass in above-and belowground through functional traits remain poorly understood.Here,we conducted a common garden experiment in a greenhouse,which included two plant species richness levels and two water addition levels,to analyze the effects of biodiversity on aboveground biomass(AGB),belowground biomass(BGB)and total biomass(TB),and to quantify the relationship between BEs and functional traits under drought conditions.Our analysis focused on partitioning BEs into above-and belowground complementarity effect(CE)and selection effect(SE)at the species level,which allowed us to better understand the impacts of biodiversity on community biomass and the underlying mechanisms.Our results showed that plant species richness stimulated AGB,BGB and TB through CEs.Drought decreased AGB,BGB and TB,simultaneously.In addition,the aboveground CE was positively associated with the variation in plant height.SEs in above-and belowground were negatively correlated with the community mean plant height and root length,respectively.Furthermore,drought weakened the aboveground CE by decreasing variation in plant height,resulting in a reduction in AGB and TB.Our findings demonstrate that the complementarity of species is an important regulator of community biomass in above-and belowground,the dynamics of biomass under environmental stress are associated with the response of sensitive compartments.
