Flexible dielectric polymers that can withstand high electric field and simultaneously have high dielectric constant are desired for high-density energy storage.Here,we systematically investigated the impact of oxygen...Flexible dielectric polymers that can withstand high electric field and simultaneously have high dielectric constant are desired for high-density energy storage.Here,we systematically investigated the impact of oxygen-containing ether and carbonyl groups in the backbone structure on dielectric properties of a series of cyclic olefin.In comparison to the influence of the-CF3 pendant groups that had more impact on the dielectric constant rather than the band gap,the change of the backbone structure affected both the dielectric constant and band gaps.The one polymer with ether and carbonyl groups in the backbone has the largest band gap and highest discharge efficiency,while it has the lowest dielectric constant.The polymer without any ether groups in the backbone has the smallest band gap and lowest discharge efficiency,but it has the highest dielectric constant.Polymers that have no dipolar relaxation exhibit an inversely correlated dielectric constant and band gap.Enhancing the dipolar relaxation through rational molecular structure design can be a novel way to break through the exclusive constraint of dielectric constant and band gap for high-density energy storage.展开更多
The ever-increasing number of materials science articles makes it hard to infer chemistry-structure-property relations from literature.We used natural language processing methods to automatically extract material prop...The ever-increasing number of materials science articles makes it hard to infer chemistry-structure-property relations from literature.We used natural language processing methods to automatically extract material property data from the abstracts of polymer literature.As a component of our pipeline,we trained MaterialsBERT,a language model,using 2.4 million materials science abstracts,which outperforms other baseline models in three out of five named entity recognition datasets.Using this pipeline,we obtained~300,000 material property records from~130,000 abstracts in 60 hours.The extracted data was analyzed for a diverse range of applications such as fuel cells,supercapacitors,and polymer solar cells to recover non-trivial insights.The data extracted through our pipeline is made available at polymerscholar.org which can be used to locate material property data recorded in abstracts.This work demonstrates the feasibility of an automatic pipeline that starts from published literature and ends with extracted material property information.展开更多
Density functional theory(DFT)has been a critical component of computational materials research and discovery for decades.However,the computational cost of solving the central Kohn–Sham equation remains a major obsta...Density functional theory(DFT)has been a critical component of computational materials research and discovery for decades.However,the computational cost of solving the central Kohn–Sham equation remains a major obstacle for dynamical studies of complex phenomena at-scale.Here,we propose an end-to-end machine learning(ML)model that emulates the essence of DFT by mapping the atomic structure of the system to its electronic charge density,followed by the prediction of other properties such as density of states,potential energy,atomic forces,and stress tensor,by using the atomic structure and charge density as input.Our deep learning model successfully bypasses the explicit solution of the Kohn-Sham equation with orders of magnitude speedup(linear scaling with system size with a small prefactor),while maintaining chemical accuracy.We demonstrate the capability of this ML-DFT concept for an extensive database of organic molecules,polymer chains,and polymer crystals.展开更多
Propelled partly by the Materials Genome Initiative,and partly by the algorithmic developments and the resounding successes of data-driven efforts in other domains,informatics strategies are beginning to take shape wi...Propelled partly by the Materials Genome Initiative,and partly by the algorithmic developments and the resounding successes of data-driven efforts in other domains,informatics strategies are beginning to take shape within materials science.These approaches lead to surrogate machine learning models that enable rapid predictions based purely on past data rather than by direct experimentation or by computations/simulations in which fundamental equations are explicitly solved.Data-centric informatics methods are becoming useful to determine material properties that are hard to measure or compute using traditional methods—due to the cost,time or effort involved—but for which reliable data either already exists or can be generated for at least a subset of the critical cases.Predictions are typically interpolative,involving fingerprinting a material numerically first,and then following a mapping(established via a learning algorithm)between the fingerprint and the property of interest.Fingerprints,also referred to as“descriptors”,may be of many types and scales,as dictated by the application domain and needs.Predictions may also be extrapolative—extending into new materials spaces—provided prediction uncertainties are properly taken into account.This article attempts to provide an overview of some of the recent successful data-driven“materials informatics”strategies undertaken in the last decade,with particular emphasis on the fingerprint or descriptor choices.The review also identifies some challenges the community is facing and those that should be overcome in the near future.展开更多
Simulations based on solving the Kohn-Sham(KS)equation of density functional theory(DFT)have become a vital component of modern materials and chemical sciences research and development portfolios.Despite its versatili...Simulations based on solving the Kohn-Sham(KS)equation of density functional theory(DFT)have become a vital component of modern materials and chemical sciences research and development portfolios.Despite its versatility,routine DFT calculations are usually limited to a few hundred atoms due to the computational bottleneck posed by the KS equation.Here we introduce a machine-learning-based scheme to efficiently assimilate the function of the KS equation,and by-pass it to directly,rapidly,and accurately predict the electronic structure of a material or a molecule,given just its atomic configuration.A new rotationally invariant representation is utilized to map the atomic environment around a grid-point to the electron density and local density of states at that grid-point.This mapping is learned using a neural network trained on previously generated reference DFT results at millions of grid-points.The proposed paradigm allows for the high-fidelity emulation of KS DFT,but orders of magnitude faster than the direct solution.Moreover,the machine learning prediction scheme is strictly linear-scaling with system size.展开更多
Emerging machine learning(ML)-based approaches provide powerful and novel tools to study a variety of physical and chemical problems.In this contribution,we outline a universal strategy to create ML-based atomistic fo...Emerging machine learning(ML)-based approaches provide powerful and novel tools to study a variety of physical and chemical problems.In this contribution,we outline a universal strategy to create ML-based atomistic force fields,which can be used to perform high-fidelity molecular dynamics simulations.This scheme involves(1)preparing a big reference dataset of atomic environments and forces with sufficiently low noise,e.g.,using density functional theory or higher-level methods,(2)utilizing a generalizable class of structural fingerprints for representing atomic environments,(3)optimally selecting diverse and nonredundant training datasets from the reference data,and(4)proposing various learning approaches to predict atomic forces directly(and rapidly)from atomic configurations.From the atomistic forces,accurate potential energies can then be obtained by appropriate integration along a reaction coordinate or along a molecular dynamics trajectory.Based on this strategy,we have created model ML force fields for six elemental bulk solids,including Al,Cu,Ti,W,Si,and C,and show that all of them can reach chemical accuracy.The proposed procedure is general and universal,in that it can potentially be used to generate ML force fields for any material using the same unified workflow with little human intervention.Moreover,the force fields can be systematically improved by adding new training data progressively to represent atomic environments not encountered previously.展开更多
The dielectric constant(ϵ)is a critical parameter utilized in the design of polymeric dielectrics for energy storage capacitors,microelectronic devices,and high-voltage insulations.However,agile discovery of polymer d...The dielectric constant(ϵ)is a critical parameter utilized in the design of polymeric dielectrics for energy storage capacitors,microelectronic devices,and high-voltage insulations.However,agile discovery of polymer dielectrics with desirableϵremains a challenge,especially for high-energy,high-temperature applications.To aid accelerated polymer dielectrics discovery,we have developed a machine-learning(ML)-based model to instantly and accurately predict the frequency-dependentϵof polymers with the frequency range spanning 15 orders of magnitude.Our model is trained using a dataset of 1210 experimentally measuredϵvalues at different frequencies,an advanced polymer fingerprinting scheme and the Gaussian process regression algorithm.展开更多
基金supported by the Office of Naval Research through a multidisciplinary university research initiative(MURI)grant(N00014-17-1-2656)a capacitor program grant(N00014-19-1-2340)。
文摘Flexible dielectric polymers that can withstand high electric field and simultaneously have high dielectric constant are desired for high-density energy storage.Here,we systematically investigated the impact of oxygen-containing ether and carbonyl groups in the backbone structure on dielectric properties of a series of cyclic olefin.In comparison to the influence of the-CF3 pendant groups that had more impact on the dielectric constant rather than the band gap,the change of the backbone structure affected both the dielectric constant and band gaps.The one polymer with ether and carbonyl groups in the backbone has the largest band gap and highest discharge efficiency,while it has the lowest dielectric constant.The polymer without any ether groups in the backbone has the smallest band gap and lowest discharge efficiency,but it has the highest dielectric constant.Polymers that have no dipolar relaxation exhibit an inversely correlated dielectric constant and band gap.Enhancing the dipolar relaxation through rational molecular structure design can be a novel way to break through the exclusive constraint of dielectric constant and band gap for high-density energy storage.
基金This work was supported by the Office of Naval Research through grants N00014-19-1-2103 and N00014-20-1-2175.Helpful discussions and feedback from Dr.Lihua Chen are acknowledged.Pranav Shetty was partially funded by a fellowship by JPMorgan Chase&Co.that helped to support this research.Any views or opinions expressed herein are solely those of the authors listed,and may differ from the views and opinions expressed by JPMorgan Chase&Co.or its affiliates.
文摘The ever-increasing number of materials science articles makes it hard to infer chemistry-structure-property relations from literature.We used natural language processing methods to automatically extract material property data from the abstracts of polymer literature.As a component of our pipeline,we trained MaterialsBERT,a language model,using 2.4 million materials science abstracts,which outperforms other baseline models in three out of five named entity recognition datasets.Using this pipeline,we obtained~300,000 material property records from~130,000 abstracts in 60 hours.The extracted data was analyzed for a diverse range of applications such as fuel cells,supercapacitors,and polymer solar cells to recover non-trivial insights.The data extracted through our pipeline is made available at polymerscholar.org which can be used to locate material property data recorded in abstracts.This work demonstrates the feasibility of an automatic pipeline that starts from published literature and ends with extracted material property information.
基金This work is partially funded by the National Science Foundation under Award Numbers 1900017 and 1941029partially by the Office of Naval Research under Award Number N00014-18-1-2113.We thank Christopher Kuenneth and Huan Doan Tran for their useful discussions and Lihua Chen for proofreading the paper.
文摘Density functional theory(DFT)has been a critical component of computational materials research and discovery for decades.However,the computational cost of solving the central Kohn–Sham equation remains a major obstacle for dynamical studies of complex phenomena at-scale.Here,we propose an end-to-end machine learning(ML)model that emulates the essence of DFT by mapping the atomic structure of the system to its electronic charge density,followed by the prediction of other properties such as density of states,potential energy,atomic forces,and stress tensor,by using the atomic structure and charge density as input.Our deep learning model successfully bypasses the explicit solution of the Kohn-Sham equation with orders of magnitude speedup(linear scaling with system size with a small prefactor),while maintaining chemical accuracy.We demonstrate the capability of this ML-DFT concept for an extensive database of organic molecules,polymer chains,and polymer crystals.
基金financial support from several grants from the Office of Naval Research that allowed them to explore many applications of machine learning within materials science,including N00014-14-1-0098,N00014-16-1-2580,and N00014-10-1-0944.
文摘Propelled partly by the Materials Genome Initiative,and partly by the algorithmic developments and the resounding successes of data-driven efforts in other domains,informatics strategies are beginning to take shape within materials science.These approaches lead to surrogate machine learning models that enable rapid predictions based purely on past data rather than by direct experimentation or by computations/simulations in which fundamental equations are explicitly solved.Data-centric informatics methods are becoming useful to determine material properties that are hard to measure or compute using traditional methods—due to the cost,time or effort involved—but for which reliable data either already exists or can be generated for at least a subset of the critical cases.Predictions are typically interpolative,involving fingerprinting a material numerically first,and then following a mapping(established via a learning algorithm)between the fingerprint and the property of interest.Fingerprints,also referred to as“descriptors”,may be of many types and scales,as dictated by the application domain and needs.Predictions may also be extrapolative—extending into new materials spaces—provided prediction uncertainties are properly taken into account.This article attempts to provide an overview of some of the recent successful data-driven“materials informatics”strategies undertaken in the last decade,with particular emphasis on the fingerprint or descriptor choices.The review also identifies some challenges the community is facing and those that should be overcome in the near future.
基金The authors would like to thank XSEDE for the utilization of Stampede2 cluster via project ID“DMR080058N”This work is supported by the Office of Naval Research through N0014-17-1-2656,a Multi-University Research Initiative(MURI)grant.
文摘Simulations based on solving the Kohn-Sham(KS)equation of density functional theory(DFT)have become a vital component of modern materials and chemical sciences research and development portfolios.Despite its versatility,routine DFT calculations are usually limited to a few hundred atoms due to the computational bottleneck posed by the KS equation.Here we introduce a machine-learning-based scheme to efficiently assimilate the function of the KS equation,and by-pass it to directly,rapidly,and accurately predict the electronic structure of a material or a molecule,given just its atomic configuration.A new rotationally invariant representation is utilized to map the atomic environment around a grid-point to the electron density and local density of states at that grid-point.This mapping is learned using a neural network trained on previously generated reference DFT results at millions of grid-points.The proposed paradigm allows for the high-fidelity emulation of KS DFT,but orders of magnitude faster than the direct solution.Moreover,the machine learning prediction scheme is strictly linear-scaling with system size.
基金supported financially by the Office of Naval Research(Grant No.N00014-14-1-0098)by the National Science Foundation(Grant No.1600218).
文摘Emerging machine learning(ML)-based approaches provide powerful and novel tools to study a variety of physical and chemical problems.In this contribution,we outline a universal strategy to create ML-based atomistic force fields,which can be used to perform high-fidelity molecular dynamics simulations.This scheme involves(1)preparing a big reference dataset of atomic environments and forces with sufficiently low noise,e.g.,using density functional theory or higher-level methods,(2)utilizing a generalizable class of structural fingerprints for representing atomic environments,(3)optimally selecting diverse and nonredundant training datasets from the reference data,and(4)proposing various learning approaches to predict atomic forces directly(and rapidly)from atomic configurations.From the atomistic forces,accurate potential energies can then be obtained by appropriate integration along a reaction coordinate or along a molecular dynamics trajectory.Based on this strategy,we have created model ML force fields for six elemental bulk solids,including Al,Cu,Ti,W,Si,and C,and show that all of them can reach chemical accuracy.The proposed procedure is general and universal,in that it can potentially be used to generate ML force fields for any material using the same unified workflow with little human intervention.Moreover,the force fields can be systematically improved by adding new training data progressively to represent atomic environments not encountered previously.
基金This work is supported by the Office of Naval Research through N0014-17-1-2656,a Multi-University Research Initiative(MURI)grant.
文摘The dielectric constant(ϵ)is a critical parameter utilized in the design of polymeric dielectrics for energy storage capacitors,microelectronic devices,and high-voltage insulations.However,agile discovery of polymer dielectrics with desirableϵremains a challenge,especially for high-energy,high-temperature applications.To aid accelerated polymer dielectrics discovery,we have developed a machine-learning(ML)-based model to instantly and accurately predict the frequency-dependentϵof polymers with the frequency range spanning 15 orders of magnitude.Our model is trained using a dataset of 1210 experimentally measuredϵvalues at different frequencies,an advanced polymer fingerprinting scheme and the Gaussian process regression algorithm.