Evolutionary approach to constructing a deep feedforward neural network for prediction of electronic coupling elements in molecular materials

Onur Çaylak (Corresponding author), Anil Yaman (Corresponding author), Björn Baumeier (Corresponding author)

Research output: Contribution to journalArticleAcademicpeer-review

1 Citation (Scopus)
28 Downloads (Pure)

Abstract

We present a general framework for the construction of a deep feedforward neural network (FFNN) to predict distance and orientation dependent electronic coupling elements in disordered molecular materials. An evolutionary algorithm automatizes the selection of an optimal architecture of the artificial neural network within a predefined search space. Systematic guidance, beyond minimizing the model error with stochastic gradient descent based backpropagation, is provided by simultaneous maximization of a model fitness that takes into account additional physical properties, such as the field-dependent carrier mobility. As a prototypical system, we consider hole transport in amorphous tris(8-hydroxyquinolinato)aluminum. Reference data for training and validation is obtained from multiscale ab initio simulations, in which coupling elements are evaluated using density-functional theory, for a system containing 4096 molecules. The Coulomb matrix representation is chosen to encode the explicit molecular pair coordinates into a rotation and translation invariant feature set for the FFNN. The final optimized deep feedforward neural network is tested for transport models without and with energetic disorder. It predicts electronic coupling elements and mobilities in excellent agreement with the reference data. Such a FFNN is readily applicable to much larger systems at negligible computational cost, providing a powerful surrogate model to overcome the size limitations of the ab initio approach.

Original languageEnglish
Pages (from-to)1777-1784
Number of pages8
JournalJournal of Chemical Theory and Computation
Volume15
Issue number3
DOIs
Publication statusPublished - 12 Mar 2019

Fingerprint

Feedforward neural networks
predictions
electronics
Carrier mobility
Aluminum
Backpropagation
Evolutionary algorithms
fitness
Density functional theory
descent
carrier mobility
Physical properties
Neural networks
education
physical properties
Molecules
disorders
density functional theory
costs
aluminum

Cite this

@article{7423b880c0384e69a14f885c8808caf8,
title = "Evolutionary approach to constructing a deep feedforward neural network for prediction of electronic coupling elements in molecular materials",
abstract = "We present a general framework for the construction of a deep feedforward neural network (FFNN) to predict distance and orientation dependent electronic coupling elements in disordered molecular materials. An evolutionary algorithm automatizes the selection of an optimal architecture of the artificial neural network within a predefined search space. Systematic guidance, beyond minimizing the model error with stochastic gradient descent based backpropagation, is provided by simultaneous maximization of a model fitness that takes into account additional physical properties, such as the field-dependent carrier mobility. As a prototypical system, we consider hole transport in amorphous tris(8-hydroxyquinolinato)aluminum. Reference data for training and validation is obtained from multiscale ab initio simulations, in which coupling elements are evaluated using density-functional theory, for a system containing 4096 molecules. The Coulomb matrix representation is chosen to encode the explicit molecular pair coordinates into a rotation and translation invariant feature set for the FFNN. The final optimized deep feedforward neural network is tested for transport models without and with energetic disorder. It predicts electronic coupling elements and mobilities in excellent agreement with the reference data. Such a FFNN is readily applicable to much larger systems at negligible computational cost, providing a powerful surrogate model to overcome the size limitations of the ab initio approach.",
author = "Onur {\cC}aylak and Anil Yaman and Bj{\"o}rn Baumeier",
year = "2019",
month = "3",
day = "12",
doi = "10.1021/acs.jctc.8b01285",
language = "English",
volume = "15",
pages = "1777--1784",
journal = "Journal of Chemical Theory and Computation",
issn = "1549-9618",
publisher = "American Chemical Society",
number = "3",

}

TY - JOUR

T1 - Evolutionary approach to constructing a deep feedforward neural network for prediction of electronic coupling elements in molecular materials

AU - Çaylak, Onur

AU - Yaman, Anil

AU - Baumeier, Björn

PY - 2019/3/12

Y1 - 2019/3/12

N2 - We present a general framework for the construction of a deep feedforward neural network (FFNN) to predict distance and orientation dependent electronic coupling elements in disordered molecular materials. An evolutionary algorithm automatizes the selection of an optimal architecture of the artificial neural network within a predefined search space. Systematic guidance, beyond minimizing the model error with stochastic gradient descent based backpropagation, is provided by simultaneous maximization of a model fitness that takes into account additional physical properties, such as the field-dependent carrier mobility. As a prototypical system, we consider hole transport in amorphous tris(8-hydroxyquinolinato)aluminum. Reference data for training and validation is obtained from multiscale ab initio simulations, in which coupling elements are evaluated using density-functional theory, for a system containing 4096 molecules. The Coulomb matrix representation is chosen to encode the explicit molecular pair coordinates into a rotation and translation invariant feature set for the FFNN. The final optimized deep feedforward neural network is tested for transport models without and with energetic disorder. It predicts electronic coupling elements and mobilities in excellent agreement with the reference data. Such a FFNN is readily applicable to much larger systems at negligible computational cost, providing a powerful surrogate model to overcome the size limitations of the ab initio approach.

AB - We present a general framework for the construction of a deep feedforward neural network (FFNN) to predict distance and orientation dependent electronic coupling elements in disordered molecular materials. An evolutionary algorithm automatizes the selection of an optimal architecture of the artificial neural network within a predefined search space. Systematic guidance, beyond minimizing the model error with stochastic gradient descent based backpropagation, is provided by simultaneous maximization of a model fitness that takes into account additional physical properties, such as the field-dependent carrier mobility. As a prototypical system, we consider hole transport in amorphous tris(8-hydroxyquinolinato)aluminum. Reference data for training and validation is obtained from multiscale ab initio simulations, in which coupling elements are evaluated using density-functional theory, for a system containing 4096 molecules. The Coulomb matrix representation is chosen to encode the explicit molecular pair coordinates into a rotation and translation invariant feature set for the FFNN. The final optimized deep feedforward neural network is tested for transport models without and with energetic disorder. It predicts electronic coupling elements and mobilities in excellent agreement with the reference data. Such a FFNN is readily applicable to much larger systems at negligible computational cost, providing a powerful surrogate model to overcome the size limitations of the ab initio approach.

UR - http://www.scopus.com/inward/record.url?scp=85062339572&partnerID=8YFLogxK

U2 - 10.1021/acs.jctc.8b01285

DO - 10.1021/acs.jctc.8b01285

M3 - Article

C2 - 30753071

AN - SCOPUS:85062339572

VL - 15

SP - 1777

EP - 1784

JO - Journal of Chemical Theory and Computation

JF - Journal of Chemical Theory and Computation

SN - 1549-9618

IS - 3

ER -