Computational materials science increasingly benefits from data management,automation,and algorithm-based decision-making for the simulation of material properties and behavior.Experimental materials science also chan...Computational materials science increasingly benefits from data management,automation,and algorithm-based decision-making for the simulation of material properties and behavior.Experimental materials science also changes rapidly by incorporation of‘machine learning’in materials discovery campaigns.The benefits including automation,reproducibility,data provenance,and reusability of managed data,however,are not widely available in the experimental domain.We present an implementation of an Active Learning loop with an interface to an experimental measurement device in pyiron as a demonstrator how to combine experimental and simulated data in one framework.Apart from the acceleration provided through active learning,additional acceleration of the experimental characterization is achieved by using prior knowledge from density functional theory simulations as well as predictions based on text mining using correlations in word embeddings.With data from all domains in the same framework,an untapped potential for the acceleration of materials characterization and materials discovery campaigns becomes available.展开更多
Mixtures of chemical ingredients,such as formulations,are ubiquitous in materials science,but optimizing their properties remains challenging due to the vast design space.Computational approaches offer a promising sol...Mixtures of chemical ingredients,such as formulations,are ubiquitous in materials science,but optimizing their properties remains challenging due to the vast design space.Computational approaches offer a promising solution to traverse this space while minimizing trial-and-error experimentation.Using high-throughput classical molecular dynamics simulations,we generated a comprehensive dataset of over 30,000 solvent mixtures to evaluate three machine learning approaches that connect molecular structure and composition to property:formulation descriptor aggregation(FDA),formulation graph(FG),and Set2Set-based method(FDS2S).Our results demonstrate that our new FDS2S approach outperforms other approaches in predicting simulation-derived properties.Formulation-property relationships can reveal important substructures and identify promising formulations at least two to three times faster than random guessing.The models show robust transferability to experimental datasets,accurately predicting properties across energy,pharmaceutical,and petroleum applications.Our research demonstrates the utility of high-throughput simulations and machine learning tools to design formulations with promising properties.展开更多
Pressure-induced phase transformations in materials are of interest in a range of fields,including geophysics,planetary sciences,and shock physics.In addition,the high-pressure phases can exhibit desirable properties,...Pressure-induced phase transformations in materials are of interest in a range of fields,including geophysics,planetary sciences,and shock physics.In addition,the high-pressure phases can exhibit desirable properties,eliciting interest in materials science.Despite its importance,the process of finding new high-pressure phases,either experimentally or computationally,is time-consuming and often driven by intuition.In this study,we use graph neural networks trained on density functional theory(DFT)equation of state data of 2258 materials and 7255 phases to identify potential phase transitions.The model is used to explore possible phase transitions in 7677 pairs of phases and promising cases are confirmed or denied via DFT calculations.Importantly,the new data is added to the training set,the model is refined,and a new cycle of discovery is started.Within 13 iterations,we discovered 28 new high-pressure stable phases(never synthesized through high-pressure routes nor reported in high-pressure computational works)and rediscovered 18 pressure-induced phase transitions.The results provide new insight and classification of pressure-induced phase transitions in terms of the ambient properties of the phases involved.展开更多
基金funding from Deutsche Forschungsgemeinschaft(DFG)through project LU1175/26-1LZ and MS gratefully acknowledge the financial support provided by the China Scholarship Council(CSC number:202208360048)MS,LB,JN,and AL gratefully acknowledge funding by Deutsche Forschungsgemeinschaft(DFG)for CRC1625,project number 506711657,subprojects A01,A04,A05,INF.
文摘Computational materials science increasingly benefits from data management,automation,and algorithm-based decision-making for the simulation of material properties and behavior.Experimental materials science also changes rapidly by incorporation of‘machine learning’in materials discovery campaigns.The benefits including automation,reproducibility,data provenance,and reusability of managed data,however,are not widely available in the experimental domain.We present an implementation of an Active Learning loop with an interface to an experimental measurement device in pyiron as a demonstrator how to combine experimental and simulated data in one framework.Apart from the acceleration provided through active learning,additional acceleration of the experimental characterization is achieved by using prior knowledge from density functional theory simulations as well as predictions based on text mining using correlations in word embeddings.With data from all domains in the same framework,an untapped potential for the acceleration of materials characterization and materials discovery campaigns becomes available.
文摘Mixtures of chemical ingredients,such as formulations,are ubiquitous in materials science,but optimizing their properties remains challenging due to the vast design space.Computational approaches offer a promising solution to traverse this space while minimizing trial-and-error experimentation.Using high-throughput classical molecular dynamics simulations,we generated a comprehensive dataset of over 30,000 solvent mixtures to evaluate three machine learning approaches that connect molecular structure and composition to property:formulation descriptor aggregation(FDA),formulation graph(FG),and Set2Set-based method(FDS2S).Our results demonstrate that our new FDS2S approach outperforms other approaches in predicting simulation-derived properties.Formulation-property relationships can reveal important substructures and identify promising formulations at least two to three times faster than random guessing.The models show robust transferability to experimental datasets,accurately predicting properties across energy,pharmaceutical,and petroleum applications.Our research demonstrates the utility of high-throughput simulations and machine learning tools to design formulations with promising properties.
基金support from the U.S.National Science Foundation FAIROS program(award 2226418)and the computational resources from nanoHUB.
文摘Pressure-induced phase transformations in materials are of interest in a range of fields,including geophysics,planetary sciences,and shock physics.In addition,the high-pressure phases can exhibit desirable properties,eliciting interest in materials science.Despite its importance,the process of finding new high-pressure phases,either experimentally or computationally,is time-consuming and often driven by intuition.In this study,we use graph neural networks trained on density functional theory(DFT)equation of state data of 2258 materials and 7255 phases to identify potential phase transitions.The model is used to explore possible phase transitions in 7677 pairs of phases and promising cases are confirmed or denied via DFT calculations.Importantly,the new data is added to the training set,the model is refined,and a new cycle of discovery is started.Within 13 iterations,we discovered 28 new high-pressure stable phases(never synthesized through high-pressure routes nor reported in high-pressure computational works)and rediscovered 18 pressure-induced phase transitions.The results provide new insight and classification of pressure-induced phase transitions in terms of the ambient properties of the phases involved.
