Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods

Abstract Modern ab initio methods have rapidly increased our understanding of solid state materials properties, chemical reactions, and the quantum interactions between atoms. However, poor scaling often renders direct ab initio calculations intractable for large or complex systems. There are two ob...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Brian Kolb, Levi C. Lentz, Alexie M. Kolpak
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/73f316d424fc41c6a69484affeee9b87
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:73f316d424fc41c6a69484affeee9b87
record_format	dspace
spelling	oai:doaj.org-article:73f316d424fc41c6a69484affeee9b872021-12-02T11:40:51ZDiscovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods10.1038/s41598-017-01251-z2045-2322https://doaj.org/article/73f316d424fc41c6a69484affeee9b872017-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-01251-zhttps://doaj.org/toc/2045-2322Abstract Modern ab initio methods have rapidly increased our understanding of solid state materials properties, chemical reactions, and the quantum interactions between atoms. However, poor scaling often renders direct ab initio calculations intractable for large or complex systems. There are two obvious avenues through which to remedy this problem: (i) develop new, less expensive methods to calculate system properties, or (ii) make existing methods faster. This paper describes an open source framework designed to pursue both of these avenues. PROPhet (short for PROPerty Prophet) utilizes machine learning techniques to find complex, non-linear mappings between sets of material or system properties. The result is a single code capable of learning analytical potentials, non-linear density functionals, and other structure-property or property-property relationships. These capabilities enable highly accurate mesoscopic simulations, facilitate computation of expensive properties, and enable the development of predictive models for systematic materials design and optimization. This work explores the coupling of machine learning to ab initio methods through means both familiar (e.g., the creation of various potentials and energy functionals) and less familiar (e.g., the creation of density functionals for arbitrary properties), serving both to demonstrate PROPhet’s ability to create exciting post-processing analysis tools and to open the door to improving ab initio methods themselves with these powerful machine learning techniques.Brian KolbLevi C. LentzAlexie M. KolpakNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-9 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Brian Kolb Levi C. Lentz Alexie M. Kolpak Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods
description	Abstract Modern ab initio methods have rapidly increased our understanding of solid state materials properties, chemical reactions, and the quantum interactions between atoms. However, poor scaling often renders direct ab initio calculations intractable for large or complex systems. There are two obvious avenues through which to remedy this problem: (i) develop new, less expensive methods to calculate system properties, or (ii) make existing methods faster. This paper describes an open source framework designed to pursue both of these avenues. PROPhet (short for PROPerty Prophet) utilizes machine learning techniques to find complex, non-linear mappings between sets of material or system properties. The result is a single code capable of learning analytical potentials, non-linear density functionals, and other structure-property or property-property relationships. These capabilities enable highly accurate mesoscopic simulations, facilitate computation of expensive properties, and enable the development of predictive models for systematic materials design and optimization. This work explores the coupling of machine learning to ab initio methods through means both familiar (e.g., the creation of various potentials and energy functionals) and less familiar (e.g., the creation of density functionals for arbitrary properties), serving both to demonstrate PROPhet’s ability to create exciting post-processing analysis tools and to open the door to improving ab initio methods themselves with these powerful machine learning techniques.
format	article
author	Brian Kolb Levi C. Lentz Alexie M. Kolpak
author_facet	Brian Kolb Levi C. Lentz Alexie M. Kolpak
author_sort	Brian Kolb
title	Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods
title_short	Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods
title_full	Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods
title_fullStr	Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods
title_full_unstemmed	Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods
title_sort	discovering charge density functionals and structure-property relationships with prophet: a general framework for coupling machine learning and first-principles methods
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/73f316d424fc41c6a69484affeee9b87
work_keys_str_mv	AT briankolb discoveringchargedensityfunctionalsandstructurepropertyrelationshipswithprophetageneralframeworkforcouplingmachinelearningandfirstprinciplesmethods AT leviclentz discoveringchargedensityfunctionalsandstructurepropertyrelationshipswithprophetageneralframeworkforcouplingmachinelearningandfirstprinciplesmethods AT alexiemkolpak discoveringchargedensityfunctionalsandstructurepropertyrelationshipswithprophetageneralframeworkforcouplingmachinelearningandfirstprinciplesmethods
_version_	1718395523109486592

Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods

Ejemplares similares