Virtual materials screening approaches have proliferated in the past decade,driven by rapid advances in first-principles computational techniques,and machine-learning algorithms.By comparison,computationally driven ma...Virtual materials screening approaches have proliferated in the past decade,driven by rapid advances in first-principles computational techniques,and machine-learning algorithms.By comparison,computationally driven materials synthesis screening is still in its infancy,and is mired by the challenges of data sparsity and data scarcity:Synthesis routes exist in a sparse,highdimensional parameter space that is difficult to optimize over directly,and,for some materials of interest,only scarce volumes of literature-reported syntheses are available.In this article,we present a framework for suggesting quantitative synthesis parameters and potential driving factors for synthesis outcomes.We use a variational autoencoder to compress sparse synthesis representations into a lower dimensional space,which is found to improve the performance of machine-learning tasks.To realize this screening framework even in cases where there are few literature data,we devise a novel data augmentation methodology that incorporates literature synthesis data from related materials systems.We apply this variational autoencoder framework to generate potential SrTiO_(3) synthesis parameter sets,propose driving factors for brookite TiO_(2) formation,and identify correlations between alkali-ion intercalation and MnO_(2) polymorph selection.展开更多
基金funding from the National Science Foundation Award#1534340DMREF that provided support to make this work possible+4 种基金support from the Office of Naval Research(ONR)under Contract No.N00014-16-1-2432the MIT Energy InitiativeNSF CAREER#1553284the Department of Energy’s Basic Energy Science Program through the Materials Project under Grant No.EDCBEEpartially supported by NSERC.
文摘Virtual materials screening approaches have proliferated in the past decade,driven by rapid advances in first-principles computational techniques,and machine-learning algorithms.By comparison,computationally driven materials synthesis screening is still in its infancy,and is mired by the challenges of data sparsity and data scarcity:Synthesis routes exist in a sparse,highdimensional parameter space that is difficult to optimize over directly,and,for some materials of interest,only scarce volumes of literature-reported syntheses are available.In this article,we present a framework for suggesting quantitative synthesis parameters and potential driving factors for synthesis outcomes.We use a variational autoencoder to compress sparse synthesis representations into a lower dimensional space,which is found to improve the performance of machine-learning tasks.To realize this screening framework even in cases where there are few literature data,we devise a novel data augmentation methodology that incorporates literature synthesis data from related materials systems.We apply this variational autoencoder framework to generate potential SrTiO_(3) synthesis parameter sets,propose driving factors for brookite TiO_(2) formation,and identify correlations between alkali-ion intercalation and MnO_(2) polymorph selection.
