Data and Code for "Machine Learning for Bridging the Gap between Density Functional Theory and Coupled Cluster Energies"

dc.contributorGerbig, Dennis
dc.contributorSchreiner, Peter Richard
dc.contributor.authorRuth, Marcel
dc.contributor.otherInstitute of Organic Chemistryde_DE
dc.date.accessioned2023-03-03T08:35:02Z
dc.date.available2023-03-03T08:35:02Z
dc.date.issued2023-02-02
dc.description.abstractThe datasets, models, and scripts were created to achieve an accurate prediction of the increment of single-point energies between density functional theory (DFT) and wavefunction-based methods, which led to our submitted article: 'A Machine Learning Approach for Bridging the Gap between Density Functional Theory and Coupled Cluster Energies'. We used the ORCA quantum chemical package to compute the geometries of each species at the B3LYP-D3(BJ)/cc-pVTZ level of theory. The optimized structure was subsequently employed for single-point (SP) computations at the DLPNO-CCSD(T)/cc-pVTZ and CCSD(T)/cc-pVTZ levels of theory. All data were extracted from the calculations and compiled in the provided .csv files. With the datasets and prediction scripts, it is possible to forecast the differences in single-point (SP) energies between the B3LYP-D3(BJ)/cc-pVTZ and DLPNO-CCSD(T)/cc-pVTZ (for monomers and dimers) levels of theory, as well as to the CCSD(T)/cc-pVTZ level of theory for monomers. The datasets can be opened and read with any text editor. The Pytorch models can be loaded and manipulated as usual (https://pytorch.org/tutorials/beginner/saving_loading_models.html). The prediction can be made by installing a suitable Python environment and setting the code line: test_database = f'TestDatabase_{mode}.csv' to the desired dataset for prediction. The format and column names of the file should match the uploaded dataset files. Once the line is modified, a prediction can be generated using the following command, for example, “python gen_predictions_CCSDt.py”.de_DE
dc.identifier.urihttps://jlupub.ub.uni-giessen.de//handle/jlupub/10034
dc.identifier.urihttp://dx.doi.org/10.22029/jlupub-9418
dc.language.isoende_DE
dc.relationhttps://doi.org/10.1021/acs.jctc.3c00274
dc.relationhttp://dx.doi.org/10.22029/jlupub-18463
dc.rightsCC0 1.0 Universal*
dc.rights.urihttp://creativecommons.org/publicdomain/zero/1.0/*
dc.subject.ddcddc:540de_DE
dc.titleData and Code for "Machine Learning for Bridging the Gap between Density Functional Theory and Coupled Cluster Energies"de_DE
dc.typeDatasetde_DE
local.affiliationFB 08 - Biologie und Chemiede_DE
local.projectSPP 2363, Schr 597/41-1de_DE

Dateien

Originalbündel
Gerade angezeigt 1 - 5 von 49
Vorschaubild nicht verfügbar
Name:
DLPNO_Monomers_SI.csv
Größe:
2.04 MB
Format:
Unknown data format
Beschreibung:
Input features and target value for the DLPNO-CCSD(T)/cc-pVTZ model (monomers).
Vorschaubild nicht verfügbar
Name:
DLPNO_Dimers_SI.csv
Größe:
2.48 MB
Format:
Unknown data format
Beschreibung:
Input features and target value for the DLPNO-CCSD(T)/cc-pVTZ model (dimers).
Vorschaubild nicht verfügbar
Name:
CCSDt_SI.csv
Größe:
804.23 KB
Format:
Unknown data format
Beschreibung:
Input features and target value for the CCSD(T)/cc-pVTZ model (monomers).
Vorschaubild nicht verfügbar
Name:
DFT_CCSDt_01.pt
Größe:
91.05 MB
Format:
Unknown data format
Beschreibung:
The 1. model for prediction of the B3LYP-D3(BJ)/cc-pVTZ to CCSD(T)/cc-pVTZ levels of theory SP energies.
Vorschaubild nicht verfügbar
Name:
DFT_CCSDt_02.pt
Größe:
91.05 MB
Format:
Unknown data format
Beschreibung:
The 2. model for prediction of B3LYP-D3(BJ)/cc-pVTZ to CCSD(T)/cc-pVTZ levels of theory SP energies.
Lizenzbündel
Gerade angezeigt 1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
license.txt
Größe:
7.58 KB
Format:
Item-specific license agreed upon to submission
Beschreibung:

Sammlungen