@Article{D3CP00506B,
author ="Chen, Xu and Li, Pinyuan and Hruska, Eugen and Liu, Fang",
title  ="Δ-Machine Learning for Quantum Chemistry Prediction of Solution-phase Molecular Properties at the Ground and Excited States",
journal  ="Phys. Chem. Chem. Phys.",
year  ="2023",
pages  ="-",
publisher  ="The Royal Society of Chemistry",
doi  ="10.1039/D3CP00506B",
url  ="http://dx.doi.org/10.1039/D3CP00506B",
abstract  ="Due to the limitation of solvent models{,} quantum chemistry calculated solution-phase molecular properties often deviates from experimental measurements. Recently{,} Δ-machine learning (Δ-ML) was shown to be a promising approach to correcting errors in the quantum chemistry calculation of solvated molecules. However{,} this approach{'}s applicability to different molecular properties and its performance in various use cases are still unknown. In this work{,} we tested the performance of Δ-ML in correcting redox potential and absorption energy calculations using four types of input descriptors and various ML methods. We sought to understand the dependence of Δ-ML performance on the property to predict{,} the quantum chemistry method{,} the data set distribution/size{,} the type of input features{,} and the feature selection techniques. We found that Δ-ML can effectively correct the errors in redox potentials calculated by density functional theory (DFT) and absorption energies calculated by time-dependent DFT. For both properties{,} the Δ-ML corrected results showed less sensitivity to the DFT functional choice than the raw results. The optimal input descriptor depends on the property{,} regardless of the specific ML method used. The solvent-solute descriptor (SS) is the best for redox potential{,} whereas the combined molecular fingerprint (cFP) is the best for absorption energy. A detailed analysis of the feature space and the physical foundation of different descriptors well explained these observations. Feature selection did not further improve the Δ-ML performance. Finally{,} we analyzed the limitation of our Δ-ML solvent effects approach in data sets with molecules of varying degrees of electronic structure errors."}