Please use this identifier to cite or link to this item: http://hdl.handle.net/10995/111123
Title: Machine Learning Methods for Predicting the Lattice Characteristics of Materials
Authors: Filanovich, A. N.
Povzner, A. A.
Issue Date: 2020
Publisher: Institute of Electrical and Electronics Engineers Inc.
IEEE
Citation: Filanovich A. N. Machine Learning Methods for Predicting the Lattice Characteristics of Materials / A. N. Filanovich, A. A. Povzner // Proceedings - 2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2020. — 2020. — Vol. — P. 414-416. — 9117689.
Abstract: Data on 5244 crystalline compounds from the open AFLOWlib repository are used to build machine learning models, which enable to predict important features of phonon spectrum of a material (Debye temperature and Gruneisen parameter) required for simulation of its lattice properties. We build two types of descriptors: the first one contains data solely on the chemical composition of a compound and the second one incorporates information on the elemental properties of atoms that make up the compound and additionally contains several features regarding its crystal structure. The regression models are built using four popular approaches - gradient boosting (GB), random forests (RF), artificial neural networks (ANN) and support vector machines (SVM). Prior the regression a search for the best values of hyperparameters has been performed for each of the model supplemented with a 5-fold cross validation. We compare prediction accuracy of models based on different methods as well as trained on each of the descriptors. © 2020 IEEE.
Keywords: MACHINE LEARNING
REGRESSION
THERMAL PROPERTIES
BIOMEDICAL ENGINEERING
CRYSTAL ATOMIC STRUCTURE
DECISION TREES
FORECASTING
NANOCRYSTALLINE MATERIALS
PHONONS
PREDICTIVE ANALYTICS
SUPPORT VECTOR MACHINES
SUPPORT VECTOR REGRESSION
CHEMICAL COMPOSITIONS
CRYSTALLINE COMPOUNDS
GRADIENT BOOSTING
GRUNEISEN PARAMETERS
IMPORTANT FEATURES
MACHINE LEARNING METHODS
MACHINE LEARNING MODELS
PREDICTION ACCURACY
LEARNING SYSTEMS
URI: http://hdl.handle.net/10995/111123
Access: info:eu-repo/semantics/openAccess
Conference name: 2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2020
Conference date: 14 May 2020 through 15 May 2020
SCOPUS ID: 85089654270
PURE ID: 13681162
ISBN: 9781728131658
Appears in Collections:Научные публикации, проиндексированные в SCOPUS и WoS CC

Files in This Item:
File Description SizeFormat 
2-s2.0-85089654270.pdf207,71 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.