The QMspin data set: Several thousand carbene singlet and triplet state structures and vertical spin gaps computed at MRCISD+Q-F12/cc-pVDZ-F12 level of theory

Schwilk, Max; Tahchieva, Diana N.; Lilienfeld, O. Anatole von

doi:10.24435/materialscloud:2020.0051/v1

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…29,31,41,42 For the QMSpin dataset, the singlet and triplet optimized structures and to-tal MRCISD+Q-F12/cc-pVDZ-F12 energies are directly obtained from the QMSpin dataset. 58,59 The closed-shell features for singlet energies and the open-shell features for triplet energies are computed from RHF/cc-pVDZ and ROHF/cc-pVDZ using ENTOS QCORE, 70 respectively.…”

Section: Computational Details a Dataset Preparationmentioning

confidence: 99%

“…Since it is more challenging to get the dissociated region correct, we use the open-shell features generated by ROHF calculations and predict the energy differences between ROHF and true MRCI+Q energies with correct reference wave functions. We finally apply MOB-ML (KA-GPR) to learn the energies and spin gaps in QMSpin dataset, 58,59 which includes 5022 optimized singlet and 7958 optimized triplet carbene structures generated from QM9 dataset. All the structures are optimized with open-shell restricted B3LYP/def2-TZVP, and most of these structures have computed singlet and triplet energies at MRCISD+Q-F12/ cc-pVDZ-F12, resulting in around 26000 energy points in total.…”

Section: Mob-ml For Water Bond Dissociation Pesmentioning

confidence: 99%

“…radicals, QM9, 54,55 QM7b-T, GDB-13-T, 20,56,57 water bond dissociation, and QMSpin datasets. 58,59 II. THEORY AND METHOD A. MOB-ML formalism for general electronic structure theory at ground state MOB-ML is a ML approach that predicts correlation energies using MOB features generated from HF computations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Molecular-orbital-based Machine Learning for Open-shell and Multi-reference Systems with Kernel Addition Gaussian Process Regression

Cheng¹,

Sun²,

Deustua³

et al. 2022

Preprint

View full text Add to dashboard Cite

We introduce a novel machine learning strategy, kernel addition Gaussian process regression (KA-GPR), in molecularorbital-based machine learning (MOB-ML) to learn the total correlation energies of general electronic structure theories for closed-and open-shell systems by introducing a machine learning strategy. The learning efficiency of MOB-ML(KA-GPR) is the same as the original MOB-ML method for the smallest criegee molecule, which is a closed-shell molecule with multi-reference characters. In addition, the prediction accuracies of different small free radicals could reach the chemical accuracy of 1 kcal/mol by training on one example structure. Accurate potential energy surfaces for the H 10 chain (closed-shell) and water OH bond dissociation (open-shell) could also be generated by MOB-ML(KA-GPR). To explore the breadth of chemical systems that KA-GPR can describe, we further apply MOB-ML to accurately predict the large benchmark datasets for closed-(QM9, QM7b-T, GDB-13-T) and open-shell (QMSpin) molecules.

show abstract

Section: Computational Details a Dataset Preparationmentioning

confidence: 99%

Section: Mob-ml For Water Bond Dissociation Pesmentioning

confidence: 99%

See 1 more Smart Citation

Molecular-orbital-based Machine Learning for Open-shell and Multi-reference Systems with Kernel Addition Gaussian Process Regression

Cheng¹,

Sun²,

Deustua³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects

et al. 2021

View full text Add to dashboard Cite

Machine-learned force fields combine the accuracy of ab initio methods with the efficiency of conventional force fields. However, current machine-learned force fields typically ignore electronic degrees of freedom, such as the total charge or spin state, and assume chemical locality, which is problematic when molecules have inconsistent electronic states, or when nonlocal effects play a significant role. This work introduces SpookyNet, a deep neural network for constructing machine-learned force fields with explicit treatment of electronic degrees of freedom and nonlocality, modeled via self-attention in a transformer architecture. Chemically meaningful inductive biases and analytical corrections built into the network architecture allow it to properly model physical limits. SpookyNet improves upon the current state-of-the-art (or achieves similar performance) on popular quantum chemistry data sets. Notably, it is able to generalize across chemical and conformational space and can leverage the learned chemical insights, e.g. by predicting unknown spin states, thus helping to close a further important remaining gap for today’s machine learning models in quantum chemistry.

show abstract

The QMspin data set: Several thousand carbene singlet and triplet state structures and vertical spin gaps computed at MRCISD+Q-F12/cc-pVDZ-F12 level of theory

Cited by 2 publications

References 0 publications

Molecular-orbital-based Machine Learning for Open-shell and Multi-reference Systems with Kernel Addition Gaussian Process Regression

Molecular-orbital-based Machine Learning for Open-shell and Multi-reference Systems with Kernel Addition Gaussian Process Regression

SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects

Contact Info

Product

Resources

About