A simple denoising approach to exploit multi-fidelity data for machine learning materials properties  

作　　者：Xiaotong Liu Pierre-Paul De Breuck Linghui Wang Gian-Marco Rignanese 

机构地区：[1]Beijing Advanced Innovation Center for Materials Genome Engineering,Beijing Information Science and Technology University,No.35 Beisihuan Middle Road,Beijing,100101,Beijing,P.R.China [2]School of Computer,Beijing Information Science and Technology University,No.35 Beisihuan Middle Road,Beijing,100101,Beijing,P.R.China [3]Institute of Condensed Matter and Nanosciences,UCLouvain,Chemin desÉtoiles 8,Louvain-la-Neuve,1348,Belgium [4]School of Materials Science and Engineering,Northwestern Polytechnical University,No.127 Youyi West Road,Xi’an,710072,Shaanxi,P.R.China

出　　处：《npj Computational Materials》2022年第1期2226-2238,共13页计算材料学（英文）

基　　金：X.T.L.is grateful for the funding support from National Natural Science Foundation of China(No.22002008,22203008);P.-P.D.B.and G.-M.R.are grateful to the F.R.S.-FNRS for financial support.

摘　　要：Machine-learning models have recently encountered enormous success for predicting the properties of materials.These are often trained based on data that present various levels of accuracy,with typically much less high-than low-fidelity data.In order to extract as much information as possible from all available data,we here introduce an approach which aims to improve the quality of the data through denoising.We investigate the possibilities that it offers in the case of the prediction of the band gap using both limited experimental data and density-functional theory relying on different exchange-correlation functionals.After analyzing the raw data thoroughly,we explore different ways to combine the data into training sequences and analyze the effect of the chosen denoiser.We also study the effect of applying the denoising procedure several times until convergence.Finally,we compare our approach with various existing methods to exploit multi-fidelity data and show that it provides an interesting improvement.

关 键 词：APPROACH learning EXPLOIT 

分 类 号：TB30[一般工业技术—材料科学与工程] TP181[自动化与计算机技术—控制理论与控制工程]