Understanding the effects of solvents on organic solvent nanofiltration currently depends on results obtained from small datasets, which slows down the industrial implementation of this technology. We present an in-depth study to identify and unify the effects of solvent parameters on solute rejection. For this purpose, we measured the rejection of 407 solutes in 11 common and green solvents using a polyimide membrane in a medium-throughput cross-flow nanofiltration system. Based on the large dataset, we experimentally verify that permeance and electronic effects of the solvent structure (Hildebrand parameters, electrotopological descriptors, and LogP) have strong impact on the average solute rejection. We furthermore identify the most important solvent parameters affecting solute rejection. Our dataset was used to build and test a graph neural network to predict the rejection of solutes. The results were rigorously tested against both internal and literature data, and demonstrated good generalization and robustness. Our model showed 0.124 (86.4% R2) and 0.123 (71.4 R2) root mean squared error for the internal and literature test sets, respectively. Explainable artificial intelligence helps understand and visualize the underlying effects of atoms and functional groups altering the rejection.
Bibliographical noteFunding Information:
The research reported in this publication was supported by funding from the AI Initiative at King Abdullah University of Science and Technology (KAUST) . The authors thank Aron K. Beke and Mujtaba Alsulaiman for their generous help with some of the rejection measurements. The graphical abstract was produced by Heno Hwang, scientific illustrator at KAUST.
© 2023 The Authors
- Big data
- Explainable AI
- Organic solvent
- Solute rejection
ASJC Scopus subject areas
- Chemical Engineering (miscellaneous)
- Filtration and Separation
- Process Chemistry and Technology
- Materials Science (miscellaneous)