Machine Learning Accelerated Genetic Algorithms for Computational Materials Search
Steen Lysgaard
Paul C. Jennings
Jens Strabo HummelshÃ¸j
Thomas Bligaard
Tejs Vegge
10.26434/chemrxiv.7411172.v1
https://chemrxiv.org/articles/Machine_Learning_Accelerated_Genetic_Algorithms_for_Computational_Materials_Search/7411172
A machine learning model is used as a surrogate fitness evaluator in a genetic algorithm (GA) optimization of the atomic distribution of Pt-Au nanoparticles. The machine learning accelerated genetic algorithm (MLaGA) yields a 50-fold reduction of required energy calculations compared to a traditional GA.
2018-12-03 17:20:54
Genetic algorithms
Nanoparticle Catalysts
Machine Learning
Gaussian process regression model
PtAu
Icosahedral Pt Au nanoparticles
Density Functional Theory
GPAW
Effective Medium Theory