Dielectric laser accelerators(DLAs)are considered promising candidates for on-chip particle accelerators that can achieve high acceleration gradients.This study explores various combinations of dielectric materials an...Dielectric laser accelerators(DLAs)are considered promising candidates for on-chip particle accelerators that can achieve high acceleration gradients.This study explores various combinations of dielectric materials and accelerated structures based on the inverse Cherenkov effect.The designs utilize conventional processing methods and laser parameters currently in use.We optimize the structural model to enhance the gradient of acceleration and the electron energy gain.To achieve higher acceleration gradients and energy gains,the selection of materials and structures should be based on the initial electron energy.Furthermore,we observed that the variation of the acceleration gradient of the material is different at different initial electron energies.These findings suggest that on-chip accelerators are feasible with the help of these structures and materials.展开更多
The extended Brinkman Darcy model for momentum equations and an energy equation is used to calculate the unsteady natural convection Couette flow of a viscous incompressible heat generating/absorbing fluid in a vertic...The extended Brinkman Darcy model for momentum equations and an energy equation is used to calculate the unsteady natural convection Couette flow of a viscous incompressible heat generating/absorbing fluid in a vertical channel （formed by two infinite vertical and parallel plates） filled with the fluid-saturated porous medium. The flow is triggered by the asymmetric heating and the accelerated motion of one of the bounding plates. The governing equations are simplified by the reasonable dimensionless parameters and solved analytically by the Laplace transform techniques to obtain the closed form solutions of the velocity and temperature profiles. Then, the skin friction and the rate of heat transfer are consequently derived. It is noticed that, at different sections within the vertical channel, the fluid flow and the temperature profiles increase with time, which are both higher near the moving plate. In particular, increasing the gap between the plates increases the velocity and the temperature of the fluid, however, reduces the skin friction and the rate of heat transfer.展开更多
The transformative impact of artificial intelligence(AI)technologies on materials science has revolutionized the study of materials problems.By leveraging well-characterized datasets derived from the scientific litera...The transformative impact of artificial intelligence(AI)technologies on materials science has revolutionized the study of materials problems.By leveraging well-characterized datasets derived from the scientific literature,AI-powered tools such as Natural Language Processing(NLP)have opened new avenues to accelerate materials research.The advances in NLP techniques and the development of large language models(LLMs)facilitate the efficient extraction and utilization of information.This review explores the application of NLP tools in materials science,focusing on automatic data extraction,materials discovery,and autonomous research.We also discuss the challenges and opportunities associated with utilizing LLMs and outline the prospects and advancements that will propel the field forward.展开更多
Electrostatic accelerator is a powerflfl tool in many research fields, such as nuclear physics, radiation biology, material science a.rchaeology and earth sciences. Two electrostatic accelerators, one is the single st...Electrostatic accelerator is a powerflfl tool in many research fields, such as nuclear physics, radiation biology, material science a.rchaeology and earth sciences. Two electrostatic accelerators, one is the single stage Vail de Gi＇aaff with terminal voltage of 4.5 MV and another one is tile EN tamteIn with terminal voltage of 6 MV, were installed in 1980s and had been put into operation since the early 1990s at tile Institute of Heavy Ion Physics. Marly applications have been carried out since then. These two accelerators are described and summaries of the most important applications on neutron physics and technology, radiation biology and material science, as well as accelerator mass spectrometry （AMS） are presented.展开更多
Boron doping,combined with neutron capture in fission reactors,has been used to simulate the helium effect on fusion structural materials.However,inhomogeneous helium bubble formation was often observed due to boron s...Boron doping,combined with neutron capture in fission reactors,has been used to simulate the helium effect on fusion structural materials.However,inhomogeneous helium bubble formation was often observed due to boron segregation to grain boundaries.The excess radiation displacements due to^(10)B(n,α)^(7)Li reaction,the high-energy lithium and helium ions,also were not accounted for,which can significantly accelerate the displacements-per-atom(dpa)accumulation alongside helium production(appm).Hereby an isotopically pure^(10)B doping approach is proposed to simulate the extreme envi-ronment inside fusion reactors with a high He appm-to-dpa ratio of about 10,which is about 10^(2)×larger than in fission reactors.Computational modeling showed that~13%of total radiation displacement was induced by^(10)B(n,α)^(7)Li in the case of 1000 appm^(10)B doped Fe samples,which becomes even greater with increasing^(10)B loading.Spatially homogenous radiation damage and helium generation are pre-dicted for grain sizes less than 1 mm,even if the boron partially formed precipitates or segregates on grain boundaries.Feasibility studies with various^(10)B doping(and^(235)U-codoping)levels in research reactors showed the estimated helium generation and radiation damage would significantly mimic fusion conditions and greatly expedite fusion materials testing,from many years down to months.展开更多
Zhongjin Lingnan’s main business is mining,smelting and sales of non-ferrous metals such as lead,zinc,copper and silver.In its nonpublic offering scheme released earlier,a total of about 658 million yuan,including 46...Zhongjin Lingnan’s main business is mining,smelting and sales of non-ferrous metals such as lead,zinc,copper and silver.In its nonpublic offering scheme released earlier,a total of about 658 million yuan,including 460million yuan of raised funds will be invested in a new materials project.The construction projects include a high-performance展开更多
Materials informatics,which combines data science and artificial intelligence(AI),has garnered significant attention owing to its ability to accelerate material development.However,human involvement is often limited t...Materials informatics,which combines data science and artificial intelligence(AI),has garnered significant attention owing to its ability to accelerate material development.However,human involvement is often limited to the initiation and oversight of machine learning processes and rarely includes roles that capitalize on human intuition or domain expertise.In this study,taking the problem of heat conduction in a two-dimensional nanostructure as a case study,an integrated human-AI collaboration framework is designed and used to construct a model to predict the thermal conductivity.This approach is used to determine the parameters that govern phonon transmission over frequencies and incidence angles.The self-learning entropic population annealing technique,which combines entropic sampling with a surrogate machine learning model,generates a global dataset that can be interpreted by a human.This allows humans to develop parameters with physical interpretations,which can guide nanostructural design for specific properties.展开更多
Autonomous high-throughput combinatorial experimentation is a key approach for accelerating materials discovery.However,achieving a fully closed-loop system remains a challenge due to the lack of effective optimizatio...Autonomous high-throughput combinatorial experimentation is a key approach for accelerating materials discovery.However,achieving a fully closed-loop system remains a challenge due to the lack of effective optimization strategies for combinatorial experimentation.Here,we developed a Bayesian optimization method specifically designed for composition-spread films,enabling the selection of promising composition-spread films and identifying which elements should be compositionally graded.Using this approach,we demonstrated an autonomous closed-loop exploration of composition-spread films to enhance the anomalous Hall effect(AHE).Our method optimized the composition of a five-element alloy system consisting of three 3d ferromagnetic elements of Fe,Co,and Ni and two 5d heavy elements from Ta,W,or Ir to maximize the AHE.Through our autonomous exploration,we achieved a maximum anomalous Hall resistivity of 10.9μΩcm in Fe_(44.9)Co_(27.9)Ni_(12.1)Ta_(3.3)Ir_(11.7)amorphous thin film on thermally oxidized Si substrates deposited at room temperature.展开更多
Autonomous experimentation–or self-driving labs–offers a systematic approach to accelerate materials discovery by integrating automated synthesis,characterization,and data-driven decisionmaking.We present a closed-l...Autonomous experimentation–or self-driving labs–offers a systematic approach to accelerate materials discovery by integrating automated synthesis,characterization,and data-driven decisionmaking.We present a closed-loop workflow for the on-demand synthesis and structural characterization of colloidal gold nanoparticles,enabling direct mapping from composition to nanoscale structure.Our framework leverages differentiable models of spectral shape to address two central tasks in self-driving labs:(a)phase mapping,or identifying compositional regions with distinct structural behavior;and(b)material retrosynthesis,or optimizing compositions for target structure.Using functional data analysis,we develop a data-driven model with generative pre-training,active learning,and high-throughput experiments to predict spectral responses across composition space.We demonstrate the approach on seed-mediated growth of gold nanoparticles,showcasing its ability to extract design rules,reveal secondary interactions,and efficiently navigate morphology space.Gradient-based optimization of the models enables inverse design,making this a unified platform.展开更多
SeeBand is an interactive tool for extracting microscopic material parameters by fitting temperaturedependent thermoelectric transport properties using Boltzmann transport theory.With real-time comparison between elec...SeeBand is an interactive tool for extracting microscopic material parameters by fitting temperaturedependent thermoelectric transport properties using Boltzmann transport theory.With real-time comparison between electronic band structures and transport data,it analyzes the Seebeck coefficient,resistivity,and Hall coefficient.Neural-network-assisted guesses and efficient fitting routines enable high-throughput processing of large datasets.SeeBand accelerates material design by allowing electronic band structure models to be derived directly from a single sample’s transport measurements.展开更多
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
Since its emergence in 2009,perovskite photovoltaic technology has achieved remarkable progress,with efficiencies soaring from 3.8%to over 26%.Despite these advancements,challenges such as long-term material and devic...Since its emergence in 2009,perovskite photovoltaic technology has achieved remarkable progress,with efficiencies soaring from 3.8%to over 26%.Despite these advancements,challenges such as long-term material and device stability remain.Addressing these challenges requires reproducible,user-independent laboratory processes and intelligent experimental preselection.Traditional trial-and-error methods and manual analysis are inefficient and urgently need advanced strategies.Automated acceleration platforms have transformed this field by improving efficiency,minimizing errors,and ensuring consistency.This review summarizes recent developments in machine learning-driven auto-mation for perovskite photovoltaics,with a focus on its application in new transport material discovery,composition screening,and device preparation optimization.Furthermore,the review introduces the concept of the self-driven Autonomous Material and Device Acceleration Platforms(AMADAP)labora-tory and discusses potential challenges it may face.This approach streamlines the entire process,from material discovery to device performance improve-ment,ultimately accelerating the development of emerging photovoltaic technologies.展开更多
Artificial intelligence(AI)has become an increasingly important propellant for energy materials and energy chemistry research,such as accelerating advanced energy materials discovery[1],analyzing vast amounts of data ...Artificial intelligence(AI)has become an increasingly important propellant for energy materials and energy chemistry research,such as accelerating advanced energy materials discovery[1],analyzing vast amounts of data from both experiments and computations[2],process optimization for materials syntheses,management and monitoring of energy storage devices such as lithium batteries,and algorithm-optimized grid load forecasting.Looking back at recent pioneering works of AI-driven energy chemistry research,constructing a dataset with both large quantity and high quality is almost the first step and largely determines the following success of training AI models and figuring out corresponding scientific issues.展开更多
基金the National Natural Science Foundation of China(Grant No.11975214)。
文摘Dielectric laser accelerators(DLAs)are considered promising candidates for on-chip particle accelerators that can achieve high acceleration gradients.This study explores various combinations of dielectric materials and accelerated structures based on the inverse Cherenkov effect.The designs utilize conventional processing methods and laser parameters currently in use.We optimize the structural model to enhance the gradient of acceleration and the electron energy gain.To achieve higher acceleration gradients and energy gains,the selection of materials and structures should be based on the initial electron energy.Furthermore,we observed that the variation of the acceleration gradient of the material is different at different initial electron energies.These findings suggest that on-chip accelerators are feasible with the help of these structures and materials.
文摘The extended Brinkman Darcy model for momentum equations and an energy equation is used to calculate the unsteady natural convection Couette flow of a viscous incompressible heat generating/absorbing fluid in a vertical channel （formed by two infinite vertical and parallel plates） filled with the fluid-saturated porous medium. The flow is triggered by the asymmetric heating and the accelerated motion of one of the bounding plates. The governing equations are simplified by the reasonable dimensionless parameters and solved analytically by the Laplace transform techniques to obtain the closed form solutions of the velocity and temperature profiles. Then, the skin friction and the rate of heat transfer are consequently derived. It is noticed that, at different sections within the vertical channel, the fluid flow and the temperature profiles increase with time, which are both higher near the moving plate. In particular, increasing the gap between the plates increases the velocity and the temperature of the fluid, however, reduces the skin friction and the rate of heat transfer.
基金supported by the National Key Research and Development Program of China(2022YFB3707502)National Natural Science Foundation of China(92270001,52201061,U22A20106,52350710205)+1 种基金Guangdong Province Key Areas Research and Development Programs(2024B0101080003)Guangdong Basic and Applied Basic Research Foundation(2023A1515140101).
文摘The transformative impact of artificial intelligence(AI)technologies on materials science has revolutionized the study of materials problems.By leveraging well-characterized datasets derived from the scientific literature,AI-powered tools such as Natural Language Processing(NLP)have opened new avenues to accelerate materials research.The advances in NLP techniques and the development of large language models(LLMs)facilitate the efficient extraction and utilization of information.This review explores the application of NLP tools in materials science,focusing on automatic data extraction,materials discovery,and autonomous research.We also discuss the challenges and opportunities associated with utilizing LLMs and outline the prospects and advancements that will propel the field forward.
文摘Electrostatic accelerator is a powerflfl tool in many research fields, such as nuclear physics, radiation biology, material science a.rchaeology and earth sciences. Two electrostatic accelerators, one is the single stage Vail de Gi＇aaff with terminal voltage of 4.5 MV and another one is tile EN tamteIn with terminal voltage of 6 MV, were installed in 1980s and had been put into operation since the early 1990s at tile Institute of Heavy Ion Physics. Marly applications have been carried out since then. These two accelerators are described and summaries of the most important applications on neutron physics and technology, radiation biology and material science, as well as accelerator mass spectrometry （AMS） are presented.
基金supported by Nuclear Global Fellowship Program through the Korea Nuclear International Cooperation Foundation(KONICOF)funded by the Ministry of Science and ICTsupport by DTRA(Award No.HDTRA1-20-2-0002)Interaction of Ionizing Radiation with Matter(IIRM)University Research Alliance(URA).
文摘Boron doping,combined with neutron capture in fission reactors,has been used to simulate the helium effect on fusion structural materials.However,inhomogeneous helium bubble formation was often observed due to boron segregation to grain boundaries.The excess radiation displacements due to^(10)B(n,α)^(7)Li reaction,the high-energy lithium and helium ions,also were not accounted for,which can significantly accelerate the displacements-per-atom(dpa)accumulation alongside helium production(appm).Hereby an isotopically pure^(10)B doping approach is proposed to simulate the extreme envi-ronment inside fusion reactors with a high He appm-to-dpa ratio of about 10,which is about 10^(2)×larger than in fission reactors.Computational modeling showed that~13%of total radiation displacement was induced by^(10)B(n,α)^(7)Li in the case of 1000 appm^(10)B doped Fe samples,which becomes even greater with increasing^(10)B loading.Spatially homogenous radiation damage and helium generation are pre-dicted for grain sizes less than 1 mm,even if the boron partially formed precipitates or segregates on grain boundaries.Feasibility studies with various^(10)B doping(and^(235)U-codoping)levels in research reactors showed the estimated helium generation and radiation damage would significantly mimic fusion conditions and greatly expedite fusion materials testing,from many years down to months.
文摘Zhongjin Lingnan’s main business is mining,smelting and sales of non-ferrous metals such as lead,zinc,copper and silver.In its nonpublic offering scheme released earlier,a total of about 658 million yuan,including 460million yuan of raised funds will be invested in a new materials project.The construction projects include a high-performance
基金partially funded by CREST(Grant No.JPMJCR21O2)provided by the Japan Science and Technology Agency(JST)The numerical calculations were performed at the Supercomputer Center at the Institute for Solid-State Physics,University of Tokyo,and Masamune-IMR at the Center for Computational Materials Science,Institute for Materials Research,Tohoku University(Project No.2112SC0507).The funder played no role in study design,data collection,analysis and interpretation of data,or the writing of this manuscript.
文摘Materials informatics,which combines data science and artificial intelligence(AI),has garnered significant attention owing to its ability to accelerate material development.However,human involvement is often limited to the initiation and oversight of machine learning processes and rarely includes roles that capitalize on human intuition or domain expertise.In this study,taking the problem of heat conduction in a two-dimensional nanostructure as a case study,an integrated human-AI collaboration framework is designed and used to construct a model to predict the thermal conductivity.This approach is used to determine the parameters that govern phonon transmission over frequencies and incidence angles.The self-learning entropic population annealing technique,which combines entropic sampling with a surrogate machine learning model,generates a global dataset that can be interpreted by a human.This allows humans to develop parameters with physical interpretations,which can guide nanostructural design for specific properties.
基金supported by JST CREST (Grant No. JPMJCR21O1)JST ERATO “Magnetic Thermal Management Materials Project” (Grant No. JPMJER2201)+3 种基金JST PRESTO (Grant No. JPMJPR24T8)MEXT Program: Data Creation and Utilization-Type Material Research and Development Project (Digital Transformation Initiative Center for Magnetic Materials, Grant No. JPMXP1122715503Digital Transformation Initiative for Green Energy Materials, Grant No. JPMXP1121467561)JSPS KAKENHI Grants-in-Aid for Scientific Research (B) (Grant No. JP21H01608).
文摘Autonomous high-throughput combinatorial experimentation is a key approach for accelerating materials discovery.However,achieving a fully closed-loop system remains a challenge due to the lack of effective optimization strategies for combinatorial experimentation.Here,we developed a Bayesian optimization method specifically designed for composition-spread films,enabling the selection of promising composition-spread films and identifying which elements should be compositionally graded.Using this approach,we demonstrated an autonomous closed-loop exploration of composition-spread films to enhance the anomalous Hall effect(AHE).Our method optimized the composition of a five-element alloy system consisting of three 3d ferromagnetic elements of Fe,Co,and Ni and two 5d heavy elements from Ta,W,or Ir to maximize the AHE.Through our autonomous exploration,we achieved a maximum anomalous Hall resistivity of 10.9μΩcm in Fe_(44.9)Co_(27.9)Ni_(12.1)Ta_(3.3)Ir_(11.7)amorphous thin film on thermally oxidized Si substrates deposited at room temperature.
基金funded primarily by the US Department of Energy (DOE), Office of Science, and Office of Basic Energy Sciences (BES) under award number DE-SC0019911Funding for H.T.C. was provided through the Energy Frontier Research Centers program: CSSAS—The Center for the Science of Synthesis Across Scales—under Award Number DE-SC0019288+2 种基金A.G. was supported by the University of Washington Molecular Engineering Materials Center (MEM-C, NSF grant DMR-2308979) as a part of the Academic Year Research Acceleration Research Experience for Undergraduates program. This work was also facilitated by the advanced computational, storage, and networking infrastructure provided by the Hyak supercomputer system and the Department of Chemical Engineering at the University of Washington. Part of this work was conducted at the Molecular Analysis Facility, a National Nanotechnology Coordinated Infrastructure (NNCI) site at the University of Washingtonsupported in part by funds from the National Science Foundation (awards NNCI-2025489, NNCI-1542101)the Molecular Engineering & Sciences Institute, and the Clean Energy Institute.
文摘Autonomous experimentation–or self-driving labs–offers a systematic approach to accelerate materials discovery by integrating automated synthesis,characterization,and data-driven decisionmaking.We present a closed-loop workflow for the on-demand synthesis and structural characterization of colloidal gold nanoparticles,enabling direct mapping from composition to nanoscale structure.Our framework leverages differentiable models of spectral shape to address two central tasks in self-driving labs:(a)phase mapping,or identifying compositional regions with distinct structural behavior;and(b)material retrosynthesis,or optimizing compositions for target structure.Using functional data analysis,we develop a data-driven model with generative pre-training,active learning,and high-throughput experiments to predict spectral responses across composition space.We demonstrate the approach on seed-mediated growth of gold nanoparticles,showcasing its ability to extract design rules,reveal secondary interactions,and efficiently navigate morphology space.Gradient-based optimization of the models enables inverse design,making this a unified platform.
基金supported by the Japan Science and Technology Agency (JST) programs MIRAI, No. JPMJMI19A1. The authors thank Nikolas Reumann for fruitful discussions regarding the theoretical framework of SeeBand. We thank the anonymous reviewers for their constructive feedback, which significantly improved both the manuscript and the SeeBand softwareThe authors acknowledge TU Wien Bibliothek for financial support through its Open Access Funding Programme.
文摘SeeBand is an interactive tool for extracting microscopic material parameters by fitting temperaturedependent thermoelectric transport properties using Boltzmann transport theory.With real-time comparison between electronic band structures and transport data,it analyzes the Seebeck coefficient,resistivity,and Hall coefficient.Neural-network-assisted guesses and efficient fitting routines enable high-throughput processing of large datasets.SeeBand accelerates material design by allowing electronic band structure models to be derived directly from a single sample’s transport measurements.
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support of“ELF-PV-Design and development of solution processed functional materials for the next generations of PV technologies”(No.44-6521a/20/4)and“Solar Factory of the Future”(FKZ 20.2-3410.5-4-5)by the Bavarian State Governmentthe German Federal Ministry for Economic Affairs and Climate Action(project Pero4PV,FKZ:03EE1092A)+3 种基金SolMAP and SolarTAP-a Technology Acceleration Platform for emerging Photovoltaics project by Helmholtz Associationsupport from the China Scholarship Council(CSC)support from the Sino-German Postdoc Scholarship Program(CSC-DAAD)support from the Villum Foundation,Grant no.50440.Open Access funding enabled and organized by Projekt DEAL.
文摘Since its emergence in 2009,perovskite photovoltaic technology has achieved remarkable progress,with efficiencies soaring from 3.8%to over 26%.Despite these advancements,challenges such as long-term material and device stability remain.Addressing these challenges requires reproducible,user-independent laboratory processes and intelligent experimental preselection.Traditional trial-and-error methods and manual analysis are inefficient and urgently need advanced strategies.Automated acceleration platforms have transformed this field by improving efficiency,minimizing errors,and ensuring consistency.This review summarizes recent developments in machine learning-driven auto-mation for perovskite photovoltaics,with a focus on its application in new transport material discovery,composition screening,and device preparation optimization.Furthermore,the review introduces the concept of the self-driven Autonomous Material and Device Acceleration Platforms(AMADAP)labora-tory and discusses potential challenges it may face.This approach streamlines the entire process,from material discovery to device performance improve-ment,ultimately accelerating the development of emerging photovoltaic technologies.
基金supported by the National Key Research and Development Program of China(2021YFB2500300)the National Natural Science Foundation of China(T2322015,92472101,22393903,22393900,52394170)the Beijing Municipal Natural Science Foundation(L247015,L233004)。
文摘Artificial intelligence(AI)has become an increasingly important propellant for energy materials and energy chemistry research,such as accelerating advanced energy materials discovery[1],analyzing vast amounts of data from both experiments and computations[2],process optimization for materials syntheses,management and monitoring of energy storage devices such as lithium batteries,and algorithm-optimized grid load forecasting.Looking back at recent pioneering works of AI-driven energy chemistry research,constructing a dataset with both large quantity and high quality is almost the first step and largely determines the following success of training AI models and figuring out corresponding scientific issues.
