AdaBoost Ensemble Correction Models for TDDFT Calculated Absorption Energies
Molecular excited states are important for molecular optical properties, which can be feasibly explored by quantum chemical calculations. However, the computation is highly demanding due to their complicated characteristic features. Therefore, high accuracy and unambiguous descriptions are strongly...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8668753/ |
id |
doaj-68c3eb3bd4704913bd4fe7e17c95413e |
---|---|
record_format |
Article |
spelling |
doaj-68c3eb3bd4704913bd4fe7e17c95413e2021-04-05T17:01:05ZengIEEEIEEE Access2169-35362019-01-017383973840610.1109/ACCESS.2019.29059288668753AdaBoost Ensemble Correction Models for TDDFT Calculated Absorption EnergiesJingxia Cui0Wenze Li1Chao Fang2Shunting Su3Jiaoyang Luan4Ting Gao5Lihong Hu6https://orcid.org/0000-0003-3792-2917Yinghua Lu7Guanhua Chen8Faculty of Chemistry, Institute of Functional Material Chemistry, Northeast Normal University, Changchun, ChinaSchool of Information Science and Technology, Northeast Normal University, Changchun, ChinaSchool of Information Science and Technology, Northeast Normal University, Changchun, ChinaSchool of Information Science and Technology, Northeast Normal University, Changchun, ChinaSchool of Information Science and Technology, Northeast Normal University, Changchun, ChinaSchool of Information Science and Technology, Northeast Normal University, Changchun, ChinaSchool of Information Science and Technology, Northeast Normal University, Changchun, ChinaFaculty of Chemistry, Institute of Functional Material Chemistry, Northeast Normal University, Changchun, ChinaDepartment of Chemistry, The University of Hong Kong, Hong KongMolecular excited states are important for molecular optical properties, which can be feasibly explored by quantum chemical calculations. However, the computation is highly demanding due to their complicated characteristic features. Therefore, high accuracy and unambiguous descriptions are strongly desired for excited state investigations. This paper proposes accurate, robust, and efficient ensemble correction models for absorption calculations with the most used quantum chemical method, time-dependent density functional theory (TDDFT). Models are built by AdaBoost framework with both weak machine learning: support vector machine (SVM), general regression neural network (GRNN), and an ensemble learning: the random forest (RF) regression method. With the models, the low accuracy calculations, TDDFT calculated absorption energies (λ<sub>max</sub>) for 433 organic molecules with the minimum basis set STO-3G, are significantly improved. The mean absolute error (MAE) and the root mean square error (RMSE) of the calculated λmax are reduced from 0.62 and 0.79 eV to 0.11 and 0.14 eV, respectively. The validation parameters of the proposed correction model can reach up to R<sup>2</sup>(0.97), Q<sup>2</sup>(0.98), and Q<sub>cv</sub><sup>2</sup> (0.99), which suggests the great goodness-of-fit and predictability. This investigation illustrates that the proposed ensemble correction models by sophisticated algorithms are highly efficient and accurate. Therefore, it may serve as an alternative tool to establish good correction models for TDDFT absorption calculations, which could significantly improve the accuracy of TDDFT calculations and extend machine learning algorithms on other feature calculations of excited states.https://ieeexplore.ieee.org/document/8668753/Ensemble learningAdaBoostregressionTDDFTabsorption energies |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jingxia Cui Wenze Li Chao Fang Shunting Su Jiaoyang Luan Ting Gao Lihong Hu Yinghua Lu Guanhua Chen |
spellingShingle |
Jingxia Cui Wenze Li Chao Fang Shunting Su Jiaoyang Luan Ting Gao Lihong Hu Yinghua Lu Guanhua Chen AdaBoost Ensemble Correction Models for TDDFT Calculated Absorption Energies IEEE Access Ensemble learning AdaBoost regression TDDFT absorption energies |
author_facet |
Jingxia Cui Wenze Li Chao Fang Shunting Su Jiaoyang Luan Ting Gao Lihong Hu Yinghua Lu Guanhua Chen |
author_sort |
Jingxia Cui |
title |
AdaBoost Ensemble Correction Models for TDDFT Calculated Absorption Energies |
title_short |
AdaBoost Ensemble Correction Models for TDDFT Calculated Absorption Energies |
title_full |
AdaBoost Ensemble Correction Models for TDDFT Calculated Absorption Energies |
title_fullStr |
AdaBoost Ensemble Correction Models for TDDFT Calculated Absorption Energies |
title_full_unstemmed |
AdaBoost Ensemble Correction Models for TDDFT Calculated Absorption Energies |
title_sort |
adaboost ensemble correction models for tddft calculated absorption energies |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
Molecular excited states are important for molecular optical properties, which can be feasibly explored by quantum chemical calculations. However, the computation is highly demanding due to their complicated characteristic features. Therefore, high accuracy and unambiguous descriptions are strongly desired for excited state investigations. This paper proposes accurate, robust, and efficient ensemble correction models for absorption calculations with the most used quantum chemical method, time-dependent density functional theory (TDDFT). Models are built by AdaBoost framework with both weak machine learning: support vector machine (SVM), general regression neural network (GRNN), and an ensemble learning: the random forest (RF) regression method. With the models, the low accuracy calculations, TDDFT calculated absorption energies (λ<sub>max</sub>) for 433 organic molecules with the minimum basis set STO-3G, are significantly improved. The mean absolute error (MAE) and the root mean square error (RMSE) of the calculated λmax are reduced from 0.62 and 0.79 eV to 0.11 and 0.14 eV, respectively. The validation parameters of the proposed correction model can reach up to R<sup>2</sup>(0.97), Q<sup>2</sup>(0.98), and Q<sub>cv</sub><sup>2</sup> (0.99), which suggests the great goodness-of-fit and predictability. This investigation illustrates that the proposed ensemble correction models by sophisticated algorithms are highly efficient and accurate. Therefore, it may serve as an alternative tool to establish good correction models for TDDFT absorption calculations, which could significantly improve the accuracy of TDDFT calculations and extend machine learning algorithms on other feature calculations of excited states. |
topic |
Ensemble learning AdaBoost regression TDDFT absorption energies |
url |
https://ieeexplore.ieee.org/document/8668753/ |
work_keys_str_mv |
AT jingxiacui adaboostensemblecorrectionmodelsfortddftcalculatedabsorptionenergies AT wenzeli adaboostensemblecorrectionmodelsfortddftcalculatedabsorptionenergies AT chaofang adaboostensemblecorrectionmodelsfortddftcalculatedabsorptionenergies AT shuntingsu adaboostensemblecorrectionmodelsfortddftcalculatedabsorptionenergies AT jiaoyangluan adaboostensemblecorrectionmodelsfortddftcalculatedabsorptionenergies AT tinggao adaboostensemblecorrectionmodelsfortddftcalculatedabsorptionenergies AT lihonghu adaboostensemblecorrectionmodelsfortddftcalculatedabsorptionenergies AT yinghualu adaboostensemblecorrectionmodelsfortddftcalculatedabsorptionenergies AT guanhuachen adaboostensemblecorrectionmodelsfortddftcalculatedabsorptionenergies |
_version_ |
1721540478498766848 |