首页|Research Conducted at Leibniz Institute for Solid State and Materials Research (IFW Dresden) Has Updated Our Knowledge about Machine Learning (Machine Learning Facilitated By Microscopic Features for Discovery of Novel Magnetic Double ...)
Research Conducted at Leibniz Institute for Solid State and Materials Research (IFW Dresden) Has Updated Our Knowledge about Machine Learning (Machine Learning Facilitated By Microscopic Features for Discovery of Novel Magnetic Double ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in Machine Learning.According to news originating from Dresden,Germany,by NewsRx corres pondents,research stated,"Double perovskites are a growing class of compounds with prospects for realization of novel magnetic behaviors.The rich chemistry o f double perovskites calls for high-throughput computational screening that can be followed by or combined with machine-learning techniques." Financial supporters for this research include Collaborative Research Center,IF W Excellence Program,German Research Foundation (DFG).Our news journalists obtained a quote from the research from Leibniz Institute f or Solid State and Materials Research (IFW Dresden),"Yet,most approaches negle ct the bulk of microscopic information implicitly provided by first-principles c alculations,severely reducing the predictive power.In this work,we remedy thi s drawback by including onsite energies and transfer integrals between the d sta tes of magnetic atoms.These quantities were computed by Wannierization of the r elevant energy bands.By combining them with the experimental information on the magnetism of studied materials and applying machine learning,we constructed a model capable of predicting the magnetic properties of the remaining materials w hose magnetism has not been addressed experimentally.Our approach combines clas sification learning to distinguish between double perovskites with dominant ferr omagnetic or antiferromagnetic interactions and regression employed to estimate magnetic transition temperatures.In this way,we identified one antiferromagnet and three ferromagnets with a high transition temperature.Another 28 antiferro magnetic candidates were identified as magnetically frustrated compounds.Among them,cubic Ba2LaReO6 shows the highest frustration parameter,which is further validated by a direct first-principles calculation.Our methodology holds promis e for eliminating the need for resource-demanding calculations."
DresdenGermanyEuropeCyborgsEmerg ing TechnologiesMachine LearningLeibniz Institute for Solid State and Materi als Research (IFW Dresden)
NETL
NSTL
