Coarse-Grained Density Functional Theory Predictions via Deep Kernel Learning

2022 ◽  
Author(s):  
Ganesh Sivaraman ◽  
Nicholas E. Jackson
Keyword(s):  
Density Functional Theory ◽  
Density Functional ◽  
Coarse Grained ◽  
Kernel Learning ◽  
Functional Theory

scholarly journals Coarse-Grained Density Functional Theory Predictions via Deep Kernel Learning

2021 ◽  
Author(s):  
Nicholas Jackson ◽  
Ganesh Sivaraman
Keyword(s):  
Density Functional Theory ◽  
Active Learning ◽  
Density Functional ◽  
Predictive Accuracy ◽  
Coarse Graining ◽  
Soft Materials ◽  
Coarse Grained ◽  
Kernel Learning ◽  
Data Sets ◽  
Functional Theory

Scalable electronic predictions are critical for soft materials design. Recently, the Electronic Coarse-Graining (ECG) method was introduced to renormalize all-atom quantum chemical (QC) predictions to coarse-grained (CG) molecular representations using deep neural networks (DNN). While DNN can learn complex representations that prove challenging for traditional kernel-based methods, they are susceptible to overfitting and the overconfidence of uncertainty estimations. Here, we develop ECG within the GPU-accelerated Deep Kernel Learning (DKL) framework to enable CG QC predictions of a conjugated oligomer using range-separated hybrid density functional theory. DKL-ECG provides accurate reproduction of QC electronic properties in conjunction with prediction uncertainties that facilitate efficient training over multiple temperature data sets via active learning. We show that while active learning algorithms enable efficient sampling of a more diverse configurational space relative to random sampling, the predictive accuracy of DKL-ECG models is effectively identical across all active learning methodologies employed. We attribute this result to the low conformational barriers of our test molecule and the redundant sampling of configurations induced by Boltzmann sampling, even for distinct temperature ensembles.

scholarly journals Classical density functional theory & simulations on a coarse-grained model of aromatic ionic liquids

Soft Matter ◽  
2014 ◽  
Vol 10 (18) ◽  
pp. 3229 ◽  
Author(s):  
Martin Turesson ◽  
Ryan Szparaga ◽  
Ke Ma ◽  
Clifford E. Woodward ◽  
Jan Forsman
Keyword(s):  
Density Functional Theory ◽  
Ionic Liquids ◽  
Density Functional ◽  
Coarse Grained ◽  
Functional Theory ◽  
Coarse Grained Model

Toward Quantitative Coarse-Grained Models of Lipids with Fluids Density Functional Theory

2012 ◽  
Vol 8 (4) ◽  
pp. 1393-1408 ◽  
Author(s):  
Laura J. Douglas Frink ◽  
Amalie L. Frischknecht ◽  
Michael A. Heroux ◽  
Michael L. Parks ◽  
Andrew G. Salinger
Keyword(s):  
Density Functional Theory ◽  
Density Functional ◽  
Coarse Grained ◽  
Functional Theory

scholarly journals Structural transitions at electrodes, immersed in simple ionic liquid models

Soft Matter ◽  
2021 ◽  
Vol 17 (14) ◽  
pp. 3876-3885
Author(s):  
Hongduo Lu ◽  
Samuel Stenberg ◽  
Clifford E. Woodward ◽  
Jan Forsman
Keyword(s):  
Density Functional Theory ◽  
Ionic Liquid ◽  
Phase Transitions ◽  
Density Functional ◽  
Dft Method ◽  
Coarse Grained ◽  
Fluid Models ◽  
Structural Transitions ◽  
Functional Theory

We used a recently developed classical Density Functional Theory (DFT) method to study the structures, phase transitions, and electrochemical behaviours of two coarse-grained ionic fluid models, in the presence of a perfectly conducting model electrode.

Sign in / Sign up

Export Citation Format

Share Document