Electron density learning of non-covalent systems

Fabrizio, Alberto; Grisafi, Andrea; Meyer, Benjamin; Ceriotti, Michele; Corminbœuf, Clémence

doi:10.1039/c9sc02696g

Cited by 131 publications

(147 citation statements)

References 98 publications

Supporting

Mentioning

142

Contrasting

Order By: Relevance

“…ò ρ (%) was found to be 1.26% for the entire test set. This is very close to the errors reported in other studies [2,39]. The accuracy of the prediction can be visually observed from figure 6 where that charge density in each class of structures contained in the test set are plotted.…”

supporting

confidence: 88%

“…An accurate estimate of ρ(r) can provide insights concerning charge redistribution, bond formation etc, in molecular and materials systems. ρ(r) is also the starting point for a variety of electronic structure simulations aimed at calculating higher level electronic properties like electrostatic moments associated with molecules such as dipole and quadrupole moments, electrostatic potentials (recently demonstrated by Fabrizio et al [2]), electrostatic interaction energies etc. It can also be used to directly compute IR intensities [3] and identify binding sites in host-guest compounds [4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A charge density prediction model for hydrocarbons using deep neural networks

Kamal

Chandrasekaran

Batra

et al. 2020

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

The electronic charge density distribution ρ(r) of a given material is among the most fundamental quantities in quantum simulations from which many large scale properties and observables can be calculated. Conventionally, ρ(r) is obtained using Kohn-Sham density functional theory (KS-DFT) based methods. But, the high computational cost of KS-DFT renders it intractable for systems involving thousands/millions of atoms. Thus, recently there has been efforts to bypass expensive KS equations, and directly predict ρ(r) using machine learning (ML) based methods. Here, we build upon one such scheme to create a robust and reliable ρ(r) prediction model for a diverse set of hydrocarbons, involving huge chemical and morphological complexity /(saturated, unsaturated molecules, cyclogroups and amorphous and semi-crystalline polymers). We utilize a grid-based fingerprint to capture the atomic neighborhood around an arbitrary point in space, and map it to the reference ρ(r) obtained from standard DFT calculations at that point. Owing to the grid-based learning, dataset sizes exceed billions of points, which is trained using deep neural networks in conjunction with a incremental learning based approach. The accuracy and transferability of the ML approach is demonstrated on not only a diverse test set, but also on a completely unseen system of polystyrene under different strains. Finally, we note that the general approach adopted here could be easily extended to other material systems, and can be used for quick and accurate determination of ρ(r) for DFT charge density initialization, computing dipole or quadrupole, and other observables for which reliable density functional are known.

show abstract

supporting

confidence: 88%

Section: Introductionmentioning

confidence: 99%

A charge density prediction model for hydrocarbons using deep neural networks

Kamal

Chandrasekaran

Batra

et al. 2020

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…While these latter functionals can already be considered members of the machine learning (ML) family, other modern ML approaches make use of algorithms such as artificial neural networks (ANN), kernel ridge regression (KRR) and gaussian process regression (GPR). Grifasi et al [12] have shown that the electron density for small hydrocarbons can be directly predicted from structural information and Fabrizio et al [13] have been able to extend this work to non-covalently bonded systems. Chandrasekaran et al [14] were able to achieve the same goal for solid-state systems by introducing a grid-based structure to electron density mapping using an ANN.…”

Section: Introductionmentioning

confidence: 96%

Machine Learning Accurate Exchange and Correlation Functionals of the Electronic Density

Dick

Fernández-Serra²

2020

Preprint

View full text Add to dashboard Cite

<div>Density Functional Theory (DFT) is the standard formalism to study the electronic structure</div><div>of matter at the atomic scale. In Kohn-Sham DFT simulations, the balance between accuracy</div><div>and computational cost depends on the choice of exchange and correlation functional, which only</div><div>exists in approximate form. Here we propose a framework to create density functionals using</div><div>supervised machine learning, termed NeuralXC. These machine-learned functionals are designed to</div><div>lift the accuracy of baseline functionals towards that are provided by more accurate methods while</div><div>maintaining their efficiency. We show that the functionals learn a meaningful representation of the</div><div>physical information contained in the training data, making them transferable across systems. A</div><div>NeuralXC functional optimized for water outperforms other methods characterizing bond breaking</div><div>and excels when comparing against experimental results. This work demonstrates that NeuralXC</div><div>is a first step towards the design of a universal, highly accurate functional valid for both molecules</div><div>and solids.</div>

show abstract

“…While these latter functionals can already be considered members of the machine learning (ML) family, other modern ML approaches make use of algorithms such as artificial neural networks (ANN), kernel ridge regression (KRR) and gaussian process regression (GPR). Grifasi et al [18] have shown that the electron density for small hydrocarbons can be directly predicted from structural information and Fabrizio et al [19] have been able to extend this work to non-covalently bonded systems. Chandrasekaran et al [20] were able to achieve the same goal for solid-state systems by introducing a grid-based structure to electron density mapping using an ANN.…”

mentioning

confidence: 96%

Machine Learning Accurate Exchange and Correlation Functionals of the Electronic Density

Dick

Fernández-Serra²

2019

Preprint

View full text Add to dashboard Cite

Density Functional Theory (DFT) is the standard formalism to study the electronic structure of matter<br>at the atomic scale. The balance between accuracy and computational cost that<br>DFT-based simulations provide allows researchers to understand the structural and dynamical properties of increasingly large and complex systems at the quantum mechanical level.<br>In Kohn-Sham DFT, this balance depends on the choice of exchange and correlation functional, which only exists<br>in approximate form. Increasing the non-locality of this functional and climbing the figurative Jacob's ladder of DFT, one can systematically reduce the amount of approximation involved and thus approach the exact functional. Doing this, however, comes at the price of increased computational cost, and so, for extensive systems, the predominant methods of choice can still be found within the lower-rung approximations. <br>Here we propose a framework to create highly accurate density functionals by using supervised machine learning, termed NeuralXC. These machine-learned functionals are designed to lift the accuracy of local and semilocal functionals to that provided by more accurate methods while maintaining their efficiency. We show that the functionals learn a meaningful representation of the physical information contained in the training data, making them transferable across systems. We further demonstrate how a functional optimized on water can reproduce experimental results when used in molecular dynamics simulations. Finally, we discuss the effects that our method has on self-consistent electron densities by comparing these densities to benchmark coupled-cluster results.

show abstract

Electron density learning of non-covalent systems

Abstract: Machine learning model of the electron densities for analyzing non-covalent interaction patterns in peptides.

Cited by 131 publications

References 98 publications

A charge density prediction model for hydrocarbons using deep neural networks

A charge density prediction model for hydrocarbons using deep neural networks

Machine Learning Accurate Exchange and Correlation Functionals of the Electronic Density

Machine Learning Accurate Exchange and Correlation Functionals of the Electronic Density

Contact Info

Product

Resources

About