Materials discovery is increasingly being impelled by machine learning methods that rely on pre-existing datasets.Where datasets are lacking,unbiased data generation can be achieved with genetic algorithms.Here a mach...Materials discovery is increasingly being impelled by machine learning methods that rely on pre-existing datasets.Where datasets are lacking,unbiased data generation can be achieved with genetic algorithms.Here a machine learning model is trained on-the-fly as a computationally inexpensive energy predictor before analyzing how to augment convergence in genetic algorithm-based approaches by using the model as a surrogate.This leads to a machine learning accelerated genetic algorithm combining robust qualities of the genetic algorithm with rapid machine learning.The approach is used to search for stable,compositionally variant,geometrically similar nanoparticle alloys to illustrate its capability for accelerated materials discovery,e.g.,nanoalloy catalysts.The machine learning accelerated approach,in this case,yields a 50-fold reduction in the number of required energy calculations compared to a traditional“brute force”genetic algorithm.This makes searching through the space of all homotops and compositions of a binary alloy particle in a given structure feasible,using density functional theory calculations.展开更多
基金The authors acknowledge support of the European Commission under the FP7 Fuel Cells and Hydrogen Joint Technology Initiative grant agreement FP7-2012-JTI-FCH-325327(SMARTCat)V-Sustain:The VILLUM Centre for the Science of Sustainable Fuels and Chemicals(no.9455)from VILLUM FONDEN.
文摘Materials discovery is increasingly being impelled by machine learning methods that rely on pre-existing datasets.Where datasets are lacking,unbiased data generation can be achieved with genetic algorithms.Here a machine learning model is trained on-the-fly as a computationally inexpensive energy predictor before analyzing how to augment convergence in genetic algorithm-based approaches by using the model as a surrogate.This leads to a machine learning accelerated genetic algorithm combining robust qualities of the genetic algorithm with rapid machine learning.The approach is used to search for stable,compositionally variant,geometrically similar nanoparticle alloys to illustrate its capability for accelerated materials discovery,e.g.,nanoalloy catalysts.The machine learning accelerated approach,in this case,yields a 50-fold reduction in the number of required energy calculations compared to a traditional“brute force”genetic algorithm.This makes searching through the space of all homotops and compositions of a binary alloy particle in a given structure feasible,using density functional theory calculations.
