Neural Network Based ∆-Machine learning approach efficiently brings the DFT potential energy surface to the CCSD(T) quality: a case for the OH + CH3OH reaction

Song, Kai-Sheng; Li, Jun

doi:10.26434/chemrxiv-2022-0lnsj-v2

Cited by 2 publications

(3 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…35,36 This approach has proven its efficacy in the construction of PESs for a wide range of systems, both reactive and non-reactive. 12, 26,32,37,38 Owing to its faster convergence with respect to the size of the basis set, as compared to the conventional CCSD(T) method, the CCSD(T)-F12 method offers significant numerical advantages. Furthermore, the accuracy of CCSD(T)-F12a/AVTZ is comparable to the calculations performed at the CCSD(T)/AV5Z level.…”

Section: D Potential Energy Surface Of Hf Trimer 21 Ab Initio Calcula...mentioning

confidence: 99%

“…This methodology has been efficaciously implemented in developing the PESs of the multi-channel reaction systems HO 2 + HO 2 and CH 3 OH + OH. 31,32 Notably, only 14% and 5% of the low-level DFT datasets, comprising 75,300*14% and 140,192*5% data points, respectively, were required to improve their PESs from the DFT level to the UCCSD(T)-F12a/AVTZ level. Inspired by this methodology, we extended its application to the interaction system CO 2 + N 2 , where the difference PES corresponds to the BSSE correction PES.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HF trimer: A new full-dimensional potential energy surface and rigorous 12D quantum calculations of vibrational states

Li,

Vindel Zandbergen,

et al. 2024

Preprint

View full text Add to dashboard Cite

HF trimer, as the lightest cyclic hydrogen-bonded (HB) trimer, has long been a favorite prototype system for spectroscopic and theoretical investigations of the structure, energetics, and dynamics of hydrogen-bond networks, and the role that nonadditive, three-body interactions play in shaping these properties. Recently, rigorous quantum 12D calculations of the coupled intra- and intermolecular vibrations of this fundamental HB trimer [P.M. Felker and Z. Bačić, J. Chem. Phys. 2023, 158, 234109] were performed, employing an older ab initio-based many-body potential energy surface (PES). While the theoretical results were found to be in reasonably good agreement with the available spectroscopic data, it was also evident that it is highly desirable to develop a more accurate 12D PES of HF trimer. Motivated by this, here we report a new 12D PES of this paradigmatic system. Approximately 42,540 geometries were sampled and calculated at the level of CCSD(T)-F12a/AVTZ. The permutationally invariant polynomial-neural network based Δ-machine learning approach [Y. Liu and J. Li, J. Phys. Chem. Lett. 2022, 13, 4729] was employed to perform cost-efficient calculations of the basis-set-superposition error (BSSE) correction. By strategically selecting data points, this approach facilitated the construction of a high-precision PES with BSSE correction, while requiring only a minimal number of BSSE value computations. The fitting error of the final PES is only 0.035 kcal/mol. To assess its performance, the 12D fully coupled quantum calculations of excited intra- and intermolecular vibrational states of HF trimer are carried out using the rigorous methodology developed by us earlier. The results are found to be in a significantly better agreement with the available spectroscopic data than those obtained with the previously existing 12D PES.

show abstract

Section: D Potential Energy Surface Of Hf Trimer 21 Ab Initio Calcula...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

HF trimer: A new full-dimensional potential energy surface and rigorous 12D quantum calculations of vibrational states

Li,

Vindel Zandbergen,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…∆-Machine learning [66][67][68] is a general method to bring a property, such a PES, trained on an efficient lower-level method close to the accuracy of a higher-level method. Here, we correct an MP2-level PES to the gold standard CCSD(T) level, for which ∆-ML approach was already employed and tested extensively also by some of us.…”

Section: ∆-Machine Learning For Pes Constructionmentioning

confidence: 99%

Combining state-of-the-art quantum chemistry and machine learning make gold standard potential energy surfaces accessible for medium-sized molecules

Nandi,

Nagy

2023

Preprint

View full text Add to dashboard Cite

Developing full-dimensional machine-learned potentials with the current gold-standard coupled-cluster (CC) level is a challenging already for medium-sized molecules due to the high computational cost. Consequently, researchers are often bound to use lower-level electronic structure methods such as density functional theory or second-order Moller-Plesset perturbation theory (MP2). Here, we demonstrate on a representative example that gold-standard potentials can now be effectively constructed for molecules of 15 atoms using off-the-shelf hardware. This is achieved by accelerating the CCSD(T) computations via the accurate and cost-effective frozen natural orbital (FNO) approach. The Delta-machine learning (Delta-ML) approach is employed with the use of permutationally invariant polynomials to fit a full-dimensional PES of the acetylacetone molecule, but any other effective descriptor and ML approach can similarly benefit from the accelerated data generation proposed here. Our benchmarks for the global minima, H-transfer TS, and many high-lying configurations show the excellent agreement of FNO-CCSD(T) results with conventional CCSD(T) while achieving a significant time advantage of about a factor of 30-40. The obtained Delta-ML PES shows high fidelity from multiple perspectives including energetic, structural, and vibrational properties. We obtain the symmetric double well H-transfer barrier of 3.15 kcal/mol in excellent agreement with the direct FNO-CCSD(T) barrier of 3.11 kcal/mol as well as with the benchmark CCSD(F12*)(T+)/CBS value of 3.21 kcal/mol. Furthermore, the tunneling splitting due to H-atom transfer is calculated using a 1D double-well potential, providing improved estimates over previous ones obtained using an MP2-based PES. The methodology introduced here represents a significant advancement in the efficient and precise construction of potentials at the CCSD(T) level for molecules above the current limit of 15 atoms.

show abstract

Neural Network Based ∆-Machine learning approach efficiently brings the DFT potential energy surface to the CCSD(T) quality: a case for the OH + CH3OH reaction

Cited by 2 publications

References 59 publications

HF trimer: A new full-dimensional potential energy surface and rigorous 12D quantum calculations of vibrational states

HF trimer: A new full-dimensional potential energy surface and rigorous 12D quantum calculations of vibrational states

Combining state-of-the-art quantum chemistry and machine learning make gold standard potential energy surfaces accessible for medium-sized molecules

Contact Info

Product

Resources

About