Koopmans’ Theorem-Compliant Long-range Corrected (KTLC) Density Functional Mediated by Black-box Optimization and Data-Driven Prediction for Organic Molecules

08 June 2023, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

Density functional theory (DFT) is a significant computational tool that has sub- stantially influenced chemistry, physics, and materials science. DFT necessitates pa- rameterized approximation for determining an expected value. Hence, to predict the properties of a given molecule using DFT, appropriate parameters of the functional should be set for each molecule. Herein, we optimize the parameters of range-separated functionals (LC-BLYP and CAM-B3LYP) via Bayesian optimization (BO) to satisfy Koopmans’ theorem. Our results demonstrate the effectiveness of BO in optimizing functional parameters. Particularly, Koopmans’ theorem-compliant LC-BLYP (KTLC- BLYP) shows results comparable to the experimental UV-absorption values. Further- more, we prepared an optimized parameter dataset of KTLC-BLYP for over 3,000 molecules through BO for satisfying Koopmans’ theorem. We have developed a ma- chine learning model on this dataset to predict the parameters of LC-BLYP functional for a given molecule. The prediction model automatically predicts appropriate param- eters for a given molecule and calculates the corresponding values. The fashion in this paper would be useful to develop new functionals and update the previously developed functionals.

Keywords

density functional theory
Black-box optimization

Supplementary materials

Title
Description
Actions
Title
Supplementary Materials for Koopmans' Theorem-Compliant Long-range Corrected (KTLC) Density Functional Mediated by Black-box Optimization and Data-Driven Prediction for Organic Molecules
Description
Initial values of Bayesian optimization (BO) and random sampling (RS) Distributions of α and β in CAM-B3LYP Averaged conversion process of KTLC-BLYP for 3,000 molecules Details of performance evaluation for predicting μ using RF and LightGBM Molecules used for the validation for KTLC-BLYP (PM) Details and characterization of materials with 1H NMR
Actions
Title
Dataset of over 3,000 molecules
Description
Dataset of over 3,000 molecules for building prediction model of parameter of LC
Actions

Supplementary weblinks

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.