Fig. 1: Multi-task learning approach for predicting gas transport properties in polymers.

a MT learning pipeline. Our innovative multi-task learning approach employs the fusion of experimental and simulation data, harnessed through the power of polyGNN, a graph neural network architecture, to construct a state-of-the-art predictor for gas transport properties b Simulation protocol. The process begins with a polymer SMILES string³¹, from which the Polymer Structure Predictor (PSP) package³⁶ constructs a simulation box. This box undergoes a 21-step equilibration procedure³⁷. Subsequently, the equilibrated structures serve as the starting point for gas diffusivity and solubility calculations, accomplished through molecular dynamics and Monte Carlo simulations, respectively. Gas permeability is determined by the product of the simulated gas diffusivity and solubility. c Dataset overview. Curated experimental and simulation data used for training the multi-task ML models. d polyGNN²² architecture. A method based on graph neural networks is initiated with a polymer SMILES string. The encoder converts the repeat unit SMILES string into a periodic graph along with fingerprints, followed by the computation of initial atomic and bond fingerprint vectors. Subsequently, the message passing unit generates the learned polymer fingerprint. Introducing a selector vector to convey data fidelity (experimental or simulation) and specific properties (permeability, diffusivity, solubility) for six gases, the approach then combines this fingerprint and selector vector before passing it to the estimator, resulting in the prediction of the desired property.