An accurate full-dimensional interaction potential energy surface of CO2+N2 incorporating ∆-machine learning approach via permutation invariant polynomial-neural network
The interaction between CO2 and N2, both as essential components of the Earth’s atmosphere, plays a crucial role in investigating the greenhouse effect. In this work, we sampled 40,930 data points within the full-dimensional configuration space of CO2 and N2 and performed calculations at the level o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | Artificial Intelligence Chemistry |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2949747723000192 |
| _version_ | 1797237819910914048 |
|---|---|
| author | Jia Li Jun Li |
| author_facet | Jia Li Jun Li |
| author_sort | Jia Li |
| collection | DOAJ |
| description | The interaction between CO2 and N2, both as essential components of the Earth’s atmosphere, plays a crucial role in investigating the greenhouse effect. In this work, we sampled 40,930 data points within the full-dimensional configuration space of CO2 and N2 and performed calculations at the level of explicitly correlated coupled cluster single, double, and perturbative triple level with the augmented correlation corrected valence triple-ζ basis set (CCSD(T)-F12a/AVTZ). To ensure computational accuracy while reducing computational costs, we employed the recently proposed Δ-machine learning (Δ-ML) method based on Permutation Invariant Polynomial-Neural Network (PIP-NN) for basis set superposition error (BSSE) correction. By leveraging the limited extrapolation capability of NN, efficient sampling was performed within the existing dataset, enabling the construction of the potential energy surface (PES) incorporating BSSE correction with only a small number of data points for BSSE calculations. A total of approximately 1100 data points were selected from the initial dataset to construct a BSSE correction PES. Utilizing this correction PES, BSSE predictions were carried out for all remaining data points, resulting in the successful development of a high-precision full-dimensional PES with BSSE correction for the CO2 + N2 system. The PIP-NN based Δ-ML method significantly reduced the required BSSE calculations by approximately 97.2%, resulting in a final PES with a fitting error of merely 0.026 kcal/mol. |
| first_indexed | 2024-04-24T17:25:49Z |
| format | Article |
| id | doaj.art-5dfde7887b6044d4844170a3ef891a33 |
| institution | Directory Open Access Journal |
| issn | 2949-7477 |
| language | English |
| last_indexed | 2024-04-24T17:25:49Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Artificial Intelligence Chemistry |
| spelling | doaj.art-5dfde7887b6044d4844170a3ef891a332024-03-28T06:40:16ZengElsevierArtificial Intelligence Chemistry2949-74772023-12-0112100019An accurate full-dimensional interaction potential energy surface of CO2+N2 incorporating ∆-machine learning approach via permutation invariant polynomial-neural networkJia Li0Jun Li1School of Chemistry and Chemical Engineering & Chongqing Key Laboratory of Theoretical and Computational Chemistry, Chongqing University, Chongqing 401331, ChinaCorresponding author.; School of Chemistry and Chemical Engineering & Chongqing Key Laboratory of Theoretical and Computational Chemistry, Chongqing University, Chongqing 401331, ChinaThe interaction between CO2 and N2, both as essential components of the Earth’s atmosphere, plays a crucial role in investigating the greenhouse effect. In this work, we sampled 40,930 data points within the full-dimensional configuration space of CO2 and N2 and performed calculations at the level of explicitly correlated coupled cluster single, double, and perturbative triple level with the augmented correlation corrected valence triple-ζ basis set (CCSD(T)-F12a/AVTZ). To ensure computational accuracy while reducing computational costs, we employed the recently proposed Δ-machine learning (Δ-ML) method based on Permutation Invariant Polynomial-Neural Network (PIP-NN) for basis set superposition error (BSSE) correction. By leveraging the limited extrapolation capability of NN, efficient sampling was performed within the existing dataset, enabling the construction of the potential energy surface (PES) incorporating BSSE correction with only a small number of data points for BSSE calculations. A total of approximately 1100 data points were selected from the initial dataset to construct a BSSE correction PES. Utilizing this correction PES, BSSE predictions were carried out for all remaining data points, resulting in the successful development of a high-precision full-dimensional PES with BSSE correction for the CO2 + N2 system. The PIP-NN based Δ-ML method significantly reduced the required BSSE calculations by approximately 97.2%, resulting in a final PES with a fitting error of merely 0.026 kcal/mol.http://www.sciencedirect.com/science/article/pii/S2949747723000192Potential energy surfaceΔ-machine learningPermutation invariant polynomial-neural networkBasis set superposition error |
| spellingShingle | Jia Li Jun Li An accurate full-dimensional interaction potential energy surface of CO2+N2 incorporating ∆-machine learning approach via permutation invariant polynomial-neural network Artificial Intelligence Chemistry Potential energy surface Δ-machine learning Permutation invariant polynomial-neural network Basis set superposition error |
| title | An accurate full-dimensional interaction potential energy surface of CO2+N2 incorporating ∆-machine learning approach via permutation invariant polynomial-neural network |
| title_full | An accurate full-dimensional interaction potential energy surface of CO2+N2 incorporating ∆-machine learning approach via permutation invariant polynomial-neural network |
| title_fullStr | An accurate full-dimensional interaction potential energy surface of CO2+N2 incorporating ∆-machine learning approach via permutation invariant polynomial-neural network |
| title_full_unstemmed | An accurate full-dimensional interaction potential energy surface of CO2+N2 incorporating ∆-machine learning approach via permutation invariant polynomial-neural network |
| title_short | An accurate full-dimensional interaction potential energy surface of CO2+N2 incorporating ∆-machine learning approach via permutation invariant polynomial-neural network |
| title_sort | accurate full dimensional interaction potential energy surface of co2 n2 incorporating ∆ machine learning approach via permutation invariant polynomial neural network |
| topic | Potential energy surface Δ-machine learning Permutation invariant polynomial-neural network Basis set superposition error |
| url | http://www.sciencedirect.com/science/article/pii/S2949747723000192 |
| work_keys_str_mv | AT jiali anaccuratefulldimensionalinteractionpotentialenergysurfaceofco2n2incorporatingmachinelearningapproachviapermutationinvariantpolynomialneuralnetwork AT junli anaccuratefulldimensionalinteractionpotentialenergysurfaceofco2n2incorporatingmachinelearningapproachviapermutationinvariantpolynomialneuralnetwork AT jiali accuratefulldimensionalinteractionpotentialenergysurfaceofco2n2incorporatingmachinelearningapproachviapermutationinvariantpolynomialneuralnetwork AT junli accuratefulldimensionalinteractionpotentialenergysurfaceofco2n2incorporatingmachinelearningapproachviapermutationinvariantpolynomialneuralnetwork |