Predicting the Solubility of Gases, Vapors, and Supercritical Fluids in Amorphous Polymers from Electron Density using Convolutional Neural Networks

14 June 2023, Version 2
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

A twin convolutional neural network is proposed to predict the pressure and temperature-dependent sorption of gases, vapors, and supercritical fluids in amorphous polymers based solely on spatial electron density distribution. Quantum chemical data as 3D tensors (3D images) is derived from DFT calculations. A dataset of almost 15000 experimentally measured uptakes (0.01-50 wt%) of 79 gases in 102 different polymers under pressures from 1E-3 – 7E+2 bar range and temperatures from 233-508 K range is collected from over 250 literature sources. The dataset includes measurements on almost 500 solvent-polymer systems spanning from typical low-pressure sorption in membrane glassy polymers to high-pressure solubility of supercritical fluids in molten polymers. Irreducible mean absolute percentage error (MAPE) is approximately estimated to be ~20%. The sources of inherent data variability are briefly discussed. In 100 epochs, the model achieved 31% MAPE on a test set of 1600 experimental measurements concerning 22 polymers previously unseen by the model.

Keywords

deep learning
property prediction
electron density
molecular modeling
solubility
polymers

Supplementary materials

Title
Description
Actions
Title
collection of solubilities
Description
A collection of pressure and temperature dependent solubilities of gases, vapors and supercritical fluids in polymers
Actions
Title
list of polymers
Description
A list of polymers used in the dataset with their ID numbers
Actions
Title
list of solvents
Description
A list of solvents used in the dataset with their ID numbers
Actions
Title
optimized geometries
Description
Optimized geometries of polymer repeating units and solvent molecules
Actions
Title
smiles
Description
Polymers and solvents in SMILES format
Actions

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.