Machine Learning Approaches toward Orbital-free Density Functional Theory: Simultaneous Training on the Kinetic Energy Density Functional and Its Functional Derivative

Meyer, Ralf; Weichselbaum, Manuel; Hauser, Andreas

doi:10.1021/acs.jctc.0c00580

Cited by 73 publications

(66 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We expect that similar progress can be made for transition metal containing systems. Newer approaches, such as the use of machine learning methods to create better functional forms for the DFT functional, [139][140][141][142][143][144] may also prove to be useful in the optimization process.…”

Section: Reduction Potentials In Solutionmentioning

confidence: 99%

Calculation of Metallocene Ionization Potentials via Auxiliary Field Quantum Monte Carlo: Towards Benchmark Quantum Chemistry for Transition Metals

Rudshteyn

Weber

Coskun

et al. 2022

Preprint

View full text Add to dashboard Cite

The accurate ab initio prediction of ionization energies is essential to understanding the electrochemistry of transition metal complexes in both materials science and biological applications. However, such predictions have been complicated by the scarcity of gas-phase experimental data, the relatively large size of the relevant molecules, and the presence of strong electron correlation effects. In this work, we apply all-electron phaseless auxiliary-field quantum Monte Carlo (ph-AFQMC) utilizing multi-determinant trial wavefunctions to six metallocene complexes to compare the computed adiabatic and vertical ionization energies to experimental results. We find that ph-AFQMC yields mean averaged errors (MAE) of 1.69±1.02 kcal/mol for the adiabatic energies and 2.85±1.13 kcal/mol for the vertical energies. We also carry out density functional theory (DFT) calculations using a variety of functionals, which yields MAE’s of 3.62 to 6.98 and 3.31 to 9.88 kcal/mol, as well as a localized coupled cluster approach (DLPNO-CCSD(T0)), which has MAEs of 4.96 and 6.08 kcal/mol, respectively. We also test the reliability of DLPNO-CCSD(T0) and DFT on acetylacetonate (acac) complexes for adiabatic energies measured in the same manner experimentally, and find much higher MAE’s, ranging from 4.56 kcal/mol to 10.99 kcal/mol (with a different ordering) for DFT and 6.97 kcal/mol for DLPNO-CCSD(T0). Finally, by utilizing experimental solvation energies, we show that accurate reduction potentials in solution for the metallocene series can be obtained from the AFQMC gas phase results.

show abstract

Section: Reduction Potentials In Solutionmentioning

confidence: 99%

Calculation of Metallocene Ionization Potentials via Auxiliary Field Quantum Monte Carlo: Towards Benchmark Quantum Chemistry for Transition Metals

Rudshteyn

Weber

Coskun

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The second future prospect is the creation of embedding approaches linking our wave-function-based description with orbital free He-DFT (Dalfovo et al, 1995;Ancilotto et al, 2017), following previous efforts . In this sense, the highly accurate method presented in our latest work (de Lara-Castells and Mitrushchenkov, 2021) is expected to provide benchmark results guiding new, machine-learning driven, parameterizations in He-DFT, as already illustrated in electronic structure theory (Meyer et al, 2020).…”

Section: Concluding Remarks and Future Directionsmentioning

confidence: 87%

Mini Review: Quantum Confinement of Atomic and Molecular Clusters in Carbon Nanotubes

Lara‐Castells

Mitrushchenkov

2021

Front. Chem.

View full text Add to dashboard Cite

We overview our recent developments on a computational approach addressing quantum confinement of light atomic and molecular clusters (made of atomic helium and molecular hydrogen) in carbon nanotubes. We outline a multi-scale first-principles approach, based on density functional theory (DFT)-based symmetry-adapted perturbation theory, allowing an accurate characterization of the dispersion-dominated particle–nanotube interaction. Next, we describe a wave-function-based method, allowing rigorous fully coupled quantum calculations of the pseudo-nuclear bound states. The approach is illustrated by showing the transition from molecular aggregation to quasi-one-dimensional condensed matter systems of molecular deuterium and hydrogen as well as atomic 4He, as case studies. Finally, we present a perspective on future-oriented mixed approaches combining, e.g., orbital-free helium density functional theory (He-DFT), machine-learning parameterizations, with wave-function-based descriptions.

show abstract

“…As can be seen in Fig. 3, existing atomistic ML packages such as AMP, 155 sGDML 156 or SchNet-Pack 45,121 could be interfaced with electronic structure packages that heavily expose internal routines (e.g., FHIaims, 157 PSI4, 158 or PySCF 159 ) and be used alongside dynamics packages such as i-Pi 160 and SHARC, 161,162 as well as algebra and electronic structure libraries such as ELSI 2 and ESL. 1 The structure generation, workflow and parser tool Atomic Simulation Environment (ASE) 163 is for example already interfaced with the above examples of AMP and SchNetPack.…”

Section: Please Cite This Article As Doi:101063/50047760mentioning

confidence: 99%

Perspective on integrating machine learning into computational chemistry and materials science

Westermayr

Gastegger

Schütt³

et al. 2021

The Journal of Chemical Physics

146

View full text Add to dashboard Cite

Machine learning (ML) methods are being used in almost every conceivable area of electronic structure theory and molecular simulation. In particular, ML has become firmly established in the construction of highdimensional interatomic potentials. Not a day goes by without another proof of principle being published on how ML methods can represent and predict quantum mechanical properties -be they observable, such as molecular polarizabilities, or not, such as atomic charges. As ML is becoming pervasive in electronic structure theory and molecular simulation, we provide an overview of how atomistic computational modeling is being transformed by the incorporation of ML approaches. From the perspective of the practitioner in the field, we assess how common workflows to predict structure, dynamics, and spectroscopy are affected by ML. Finally, we discuss how a tighter and lasting integration of ML methods with computational chemistry and materials science can be achieved and what it will mean for research practice, software development, and postgraduate training.

show abstract

Machine Learning Approaches toward Orbital-free Density Functional Theory: Simultaneous Training on the Kinetic Energy Density Functional and Its Functional Derivative

Cited by 73 publications

References 64 publications

Calculation of Metallocene Ionization Potentials via Auxiliary Field Quantum Monte Carlo: Towards Benchmark Quantum Chemistry for Transition Metals

Calculation of Metallocene Ionization Potentials via Auxiliary Field Quantum Monte Carlo: Towards Benchmark Quantum Chemistry for Transition Metals

Mini Review: Quantum Confinement of Atomic and Molecular Clusters in Carbon Nanotubes

Perspective on integrating machine learning into computational chemistry and materials science

Contact Info

Product

Resources

About