Gas permeability, diffusivity, and solubility in polymers: Simulation-experiment data fusion and multi-task machine learning

TL;DR

This paper introduces a multi-task deep learning framework that fuses experimental and simulation data to accurately predict gas permeability, diffusivity, and solubility in polymers, improving generalization across diverse chemical spaces.

Contribution

It presents a novel multi-tiered multi-task learning approach combining physics-informed features and data fusion, enhancing property prediction accuracy with limited experimental data.

Findings

Multi-task models outperform single-task models in accuracy.

Data fusion improves generalization to new chemical spaces.

Simultaneous prediction of multiple properties is feasible and effective.

Abstract

Machine learning (ML) models for predicting gas permeability through polymers have traditionally relied on experimental data. While these models exhibit robustness within familiar chemical domains, reliability wanes when applied to new spaces. To address this challenge, we present a multi-tiered multi-task learning framework empowered with advanced machine-crafted polymer fingerprinting algorithms and data fusion techniques. This framework combines scarce "high-fidelity" experimental data with abundant diverse "low-fidelity" simulation or synthetic data, resulting in predictive models that display a high level of generalizability across novel chemical spaces. Additionally, this multi-task scheme capitalizes on known physics and interrelated properties, such as gas diffusivity and solubility, both of which are closely tied to permeability. By amalgamating high-throughput generated simulation data with available experimental data for gas permeability, diffusivity, and solubility for various gases, we construct multi-task deep learning models. These models can simultaneously predict all three properties for all gases under consideration. With markedly enhanced predictive accuracy, particularly compared to traditional models reliant solely on experimental data for a singular property. This strategy underscores the potential of coupling high-throughput classical simulations with data fusion methodologies to yield state-of-the-art property predictors, especially when experimental data for targeted properties is scarce.