Computational cost limits the applicability of post-Hartree-Fock methods such as coupled-cluster on larger molecular systems. The data-driven coupled-cluster (DDCC) method applies machine learning to predict the coupled-cluster two-electron amplitudes () using data from second-order perturbation theory (MP2). One major limitation of the DDCC models is the size of training sets that increases exponentially with the system size. Effective sampling of the amplitude space can resolve this issue. Five different amplitude selection techniques that reduce the amount of data used for training were evaluated, an approach that also prevents model overfitting and increases the portability of data-driven coupled-cluster singles and doubles to more complex molecules or larger basis sets. In combination with a localized orbital formalism to predict the CCSD amplitudes, we have achieved a 10-fold error reduction for energy calculations.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1021/acs.jpca.3c06600 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Exploration of the Two-Electron Excitation Space with Data-Driven Coupled Cluster.
J Phys Chem A
March 2024
Department of Chemistry, University of Tennessee, Knoxville, Tennessee 37996-1600, United States.
Computational cost limits the applicability of post-Hartree-Fock methods such as coupled-cluster on larger molecular systems. The data-driven coupled-cluster (DDCC) method applies machine learning to predict the coupled-cluster two-electron amplitudes () using data from second-order perturbation theory (MP2). One major limitation of the DDCC models is the size of training sets that increases exponentially with the system size.
View Article and Find Full Text PDFData-driven approach for benchmarking DFTB-approximate excited state methods.
Phys Chem Chem Phys
February 2023
Instituto Interdisciplinario de Ciencias Básicas (ICB-CONICET), Universidad Nacional de Cuyo, Padre Jorge Contreras 1300, Mendoza 5502, Argentina.
In this work we propose a chemically-informed data-driven approach to benchmark the approximate density-functional tight-binding (DFTB) excited state (ES) methods that are currently available within the DFTB+ suite. By taking advantage of the large volume of low-detail ES-data in the machine learning (ML) dataset, QM8, we were able to extract valuable insights regarding the limitations of the benchmarked methods in terms of the approximations made to the parent formalism, density-functional theory (DFT), while providing recommendations on how to overcome them. For this benchmark, we compared the first singlet-singlet vertical excitation energies () predicted by the DFTB-approximate methods with predictions of less approximate methods from the reference ML-dataset.
View Article and Find Full Text PDFA transferrable range-separated force field for water: Combining the power of both physically-motivated models and machine learning techniques.
J Chem Phys
December 2022
Institute of Materials Research, Tsinghua-Berkeley Shenzhen Institute (TBSI), Tsinghua Shenzhen International Graduate School (TSIGS), University Town of Shenzhen, Nanshan District, Shenzhen 518055, People's Republic of China.
An accurate, transferrable, and computationally efficient potential energy surface is of paramount importance for all molecular mechanics simulations. In this work, by using water as an example, we demonstrate how one can construct a reliable force field by combining the advantages of both physically motivated and data-driven machine learning methods. Different from the existing water models based on molecular many-body expansion, we adopt a separation scheme that is completely based on distances, which is more convenient for generic molecular systems.
View Article and Find Full Text PDFAccurate Modeling of Bromide and Iodide Hydration with Data-Driven Many-Body Potentials.
J Phys Chem B
October 2022
Department of Chemistry and Biochemistry, University of California San Diego, La Jolla, California92093, United States.
Ion-water interactions play a central role in determining the properties of aqueous systems in a wide range of environments. However, a quantitative understanding of how the hydration properties of ions evolve from small aqueous clusters to bulk solutions and interfaces remains elusive. Here, we introduce the second generation of data-driven many-body energy (MB-nrg) potential energy functions (PEFs) representing bromide-water and iodide-water interactions.
View Article and Find Full Text PDFNeural network interaction potentials for para-hydrogen with flexible molecules.
J Chem Phys
August 2022
Lehrstuhl für Theoretische Chemie, Ruhr-Universität Bochum, 44780 Bochum, Germany.
The study of molecular impurities in para-hydrogen (pH) clusters is key to push forward our understanding of intra- and intermolecular interactions, including their impact on the superfluid response of this bosonic quantum solvent. This includes tagging with only one or very few pH, the microsolvation regime for intermediate particle numbers, and matrix isolation with many solvent molecules. However, the fundamental coupling between the bosonic pH environment and the (ro-)vibrational motion of molecular impurities remains poorly understood.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!