Abstract

The fast and accurate description of the solvent environment is crucial for quantum chemical (QC) discovery in the solution phase. We combine high-performance computing hardware and machine learning (ML) techniques to improve the efficiency and accuracy of QC discovery of solvated molecules.

To improve the efficiency, we developed strategies to accelerate both the implicit and explicit solvent models. For the implicit solvent models such as the conductor-like polarization model (C-PCM), we exploited graphical processing units (GPUs) to accelerate the calculation and achieved hundreds of speedups for ground- and excited- state calculations. For the explicit solvent model, we developed AutoSolvate, an open-source toolkit to streamline the QC calculation workflow of explicitly solvated molecules. To improve the accuracy, we develop ML models to reduce the discrepancy between experimental measurements and computationally predicted molecular properties in both implicit and explicit solvent models. For ground-state redox potential calculations, our ML models can reduce both the systematic bias and the number of outliers, and the ML corrected results demonstrate less sensitivity to density functional theory (DFT) functional choice. This ML correction technique is transferrable to predicting other molecular properties in the solution phase, including the excited state redox potential and absorption/fluorescence wavelength.