Learning from Imperfections: Predicting Structure and Thermodynamics from Atomic Imaging of Fluctuations

Lukas Vlcek; Maxim Ziatdinov; Artem Maksov; Alexander Tselev; Arthur P. Baddorf; Sergei V. Kalinin; Rama K. Vasudevan

doi:10.1021/acsnano.8b07980

Learning from Imperfections: Predicting Structure and Thermodynamics from Atomic Imaging of Fluctuations

Lukas Vlcek, Maxim Ziatdinov, Artem Maksov, Alexander Tselev, Arthur P. Baddorf, Sergei V. Kalinin, Rama K. Vasudevan

Research output: Contribution to journal › Article › peer-review

24 Scopus citations

Abstract

In materials characterization, traditionally a single experimental sample is used to derive information about a single point in the composition space, while the imperfections, impurities, and stochastic details of material structure are deemed irrelevant or complicating factors in the analysis. Here we demonstrate that atomic-scale studies of a single nominal composition can provide information about microstructures and thermodynamic response over a finite area of chemical space. Using the principles of statistical inference, we develop a framework for incorporating structural fluctuations into statistical mechanical models and use it to solve the inverse problem of deriving effective interatomic interactions responsible for elemental segregation in a La _5/8 Ca _3/8 MnO ₃ thin film. The results are further analyzed by a variational autoencoder to detect anomalous behavior in the composition phase diagram. This study provides a framework for creating generative models from a combination of multiple experimental data and provides direct insight into the driving forces for cation segregation in manganites.

Original language	English
Pages (from-to)	718-727
Number of pages	10
Journal	ACS Nano
Volume	13
Issue number	1
DOIs	https://doi.org/10.1021/acsnano.8b07980
State	Published - Jan 22 2019

Funding

The work was supported by the U.S. Department of Energy, Office of Science, Materials Sciences and Engineering Division (R.K.V., S.V.K., L.V., M.Z., A.M.). Research was conducted at the Center for Nanophase Materials Sciences, which also provided support (A.P.B.) and is a US DOE Office of Science User Facility. A.T. acknowledges CICECO-Aveiro Institute of Materials, POCI-01-0145-FEDER-007679 (FCT ref. UID/ CTM/50011/2013), financed by national funds through the FCT/MEC and when appropriate cofinanced by FEDER under the PT2020 Partnership Agreement.

Funders	Funder number
CICECO-Aveiro Institute of Materials	POCI-01-0145-FEDER-007679
FCT/MEC
U.S. Department of Energy
Office of Science
Division of Materials Sciences and Engineering
Fundació Catalana de Trasplantament	UID/ CTM/50011/2013

Keywords

generative model
manganite
scanning tunneling microscopy
segregation
statistical inference
thin film

Access to Document

10.1021/acsnano.8b07980

Cite this

@article{34b55e2d20164ab3953005e13b82e0e0,

title = "Learning from Imperfections: Predicting Structure and Thermodynamics from Atomic Imaging of Fluctuations",

abstract = " In materials characterization, traditionally a single experimental sample is used to derive information about a single point in the composition space, while the imperfections, impurities, and stochastic details of material structure are deemed irrelevant or complicating factors in the analysis. Here we demonstrate that atomic-scale studies of a single nominal composition can provide information about microstructures and thermodynamic response over a finite area of chemical space. Using the principles of statistical inference, we develop a framework for incorporating structural fluctuations into statistical mechanical models and use it to solve the inverse problem of deriving effective interatomic interactions responsible for elemental segregation in a La 5/8 Ca 3/8 MnO 3 thin film. The results are further analyzed by a variational autoencoder to detect anomalous behavior in the composition phase diagram. This study provides a framework for creating generative models from a combination of multiple experimental data and provides direct insight into the driving forces for cation segregation in manganites.",

keywords = "generative model, manganite, scanning tunneling microscopy, segregation, statistical inference, thin film",

author = "Lukas Vlcek and Maxim Ziatdinov and Artem Maksov and Alexander Tselev and Baddorf, {Arthur P.} and Kalinin, {Sergei V.} and Vasudevan, {Rama K.}",

year = "2019",

month = jan,

day = "22",

doi = "10.1021/acsnano.8b07980",

language = "English",

volume = "13",

pages = "718--727",

journal = "ACS Nano",

issn = "1936-0851",

publisher = "American Chemical Society",

number = "1",

}

TY - JOUR

T1 - Learning from Imperfections

T2 - Predicting Structure and Thermodynamics from Atomic Imaging of Fluctuations

AU - Vlcek, Lukas

AU - Ziatdinov, Maxim

AU - Maksov, Artem

AU - Tselev, Alexander

AU - Baddorf, Arthur P.

AU - Kalinin, Sergei V.

AU - Vasudevan, Rama K.

PY - 2019/1/22

Y1 - 2019/1/22

N2 - In materials characterization, traditionally a single experimental sample is used to derive information about a single point in the composition space, while the imperfections, impurities, and stochastic details of material structure are deemed irrelevant or complicating factors in the analysis. Here we demonstrate that atomic-scale studies of a single nominal composition can provide information about microstructures and thermodynamic response over a finite area of chemical space. Using the principles of statistical inference, we develop a framework for incorporating structural fluctuations into statistical mechanical models and use it to solve the inverse problem of deriving effective interatomic interactions responsible for elemental segregation in a La 5/8 Ca 3/8 MnO 3 thin film. The results are further analyzed by a variational autoencoder to detect anomalous behavior in the composition phase diagram. This study provides a framework for creating generative models from a combination of multiple experimental data and provides direct insight into the driving forces for cation segregation in manganites.

AB - In materials characterization, traditionally a single experimental sample is used to derive information about a single point in the composition space, while the imperfections, impurities, and stochastic details of material structure are deemed irrelevant or complicating factors in the analysis. Here we demonstrate that atomic-scale studies of a single nominal composition can provide information about microstructures and thermodynamic response over a finite area of chemical space. Using the principles of statistical inference, we develop a framework for incorporating structural fluctuations into statistical mechanical models and use it to solve the inverse problem of deriving effective interatomic interactions responsible for elemental segregation in a La 5/8 Ca 3/8 MnO 3 thin film. The results are further analyzed by a variational autoencoder to detect anomalous behavior in the composition phase diagram. This study provides a framework for creating generative models from a combination of multiple experimental data and provides direct insight into the driving forces for cation segregation in manganites.

KW - generative model

KW - manganite

KW - scanning tunneling microscopy

KW - segregation

KW - statistical inference

KW - thin film

UR - http://www.scopus.com/inward/record.url?scp=85060020677&partnerID=8YFLogxK

U2 - 10.1021/acsnano.8b07980

DO - 10.1021/acsnano.8b07980

M3 - Article

C2 - 30609895

AN - SCOPUS:85060020677

SN - 1936-0851

VL - 13

SP - 718

EP - 727

JO - ACS Nano

JF - ACS Nano

IS - 1

ER -

Learning from Imperfections: Predicting Structure and Thermodynamics from Atomic Imaging of Fluctuations

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this