The application of machine learning models to predict material properties is determined by the availability of high-quality data.We present an expert-curated dataset of lithium ion conductors and associated lithium io...The application of machine learning models to predict material properties is determined by the availability of high-quality data.We present an expert-curated dataset of lithium ion conductors and associated lithium ion conductivities measured by a.c.impedance spectroscopy.This dataset has 820 entries collected from 214 sources;entries contain a chemical composition,an expert-assigned structural label,and ionic conductivity at a specific temperature(from 5 to 873°C).There are 403 unique chemical compositions with an associated ionic conductivity near room temperature(15–35°C).The materials contained in this dataset are placed in the context of compounds reported in the Inorganic Crystal Structure Database with unsupervised machine learning and the Element Movers Distance.This dataset is used to train a CrabNet-based classifier to estimate whether a chemical composition has high or low ionic conductivity.This classifier is a practical tool to aid experimentalists in prioritizing candidates for further investigation as lithium ion conductors.展开更多
基金This work was supported by the University of Liverpool(studentship to C.J.H.),by the Faraday Institution(SOLBAT,grant number FIRG007)by EPSRC under EP/V026887 and EP/R018472/1+1 种基金The authors thank the Leverhulme Trust for funding this research via the Leverhulme Research Centre for Functional Materials Design(RC-2015-036)This work was undertaken on Barkla,part of the High-Performance Computing facilities at the University of Liverpool,UK.K.T.,B.-E.P.,C.A.C.,J.G.,G.H.,B.T.L.,A.J.P.,A.R.,O.R.,P.M.S.,W.J.T.,A.V.,and L.W.thank the UK Engineering and Physical Sciences Research Council(EPSRC)for funding under EP/N004884.We acknowledge the ICSF Faraday Challenge projects“SOLBAT-The Solid-State(Li or Na)Metal-Anode Battery”[grant number FIRG007]and“All-Solid State Lithium Anode Battery 2”[grant number FIRG026]for funding Y.D.,A.M.,C.M.C.and E.S.,including partial support of a studentship to B.B.D.,who is also supported by the University of Liverpool.V.A.K.thanks the Royal Academy of Engineering for their fellowship support[ref IF2122\186].We acknowledge the ICSF Faraday Institution projects“CATMAT-Next Generation Li-Ion Cathode Materials”[grant number FIRG016]for funding M.S.
文摘The application of machine learning models to predict material properties is determined by the availability of high-quality data.We present an expert-curated dataset of lithium ion conductors and associated lithium ion conductivities measured by a.c.impedance spectroscopy.This dataset has 820 entries collected from 214 sources;entries contain a chemical composition,an expert-assigned structural label,and ionic conductivity at a specific temperature(from 5 to 873°C).There are 403 unique chemical compositions with an associated ionic conductivity near room temperature(15–35°C).The materials contained in this dataset are placed in the context of compounds reported in the Inorganic Crystal Structure Database with unsupervised machine learning and the Element Movers Distance.This dataset is used to train a CrabNet-based classifier to estimate whether a chemical composition has high or low ionic conductivity.This classifier is a practical tool to aid experimentalists in prioritizing candidates for further investigation as lithium ion conductors.
