Polymer genome–based prediction of gas permeabilities in polymers

Abstract Predicting gas permeabilities of polymers a priori is a long-standing challenge within the membrane research community that has important applications for membrane process design and ultimately widespread adoption of membrane technology. From early attempts based on free volume and cohesive energy to more recent group contribution methods, the ability to predict membrane permeability has improved in terms of accuracy. However, these models usually stay “within the paper”, i.e. limited model details are provided to the wider community such that adoption of these predictive platforms is limited. In this work, we combined an advanced polymer chemical structure fingerprinting method with a large experimental database of gas permeabilities to provide unprecedented prediction precision over a large range of polymer classes. No prior knowledge of the polymer is needed for the prediction other than the repeating unit chemical formula. In addition, we have incorporated this model into the existing Polymer Genome project to make it open to the membrane research community.

[1]  Arun Mannodi-Kanakkithodi,et al.  Critical assessment of regression-based machine learning methods for polymer dielectrics , 2016 .

[2]  Stephen J. Miller,et al.  Molecularly Designed Stabilized Asymmetric Hollow Fiber Membranes for Aggressive Natural Gas Separation. , 2016, Angewandte Chemie.

[3]  A. McCallum,et al.  Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning , 2017 .

[4]  Tai‐Shung Chung,et al.  High-performance composite hollow fiber membrane for flue gas and air separations , 2017 .

[5]  Arun Mannodi-Kanakkithodi,et al.  Rational Co‐Design of Polymer Dielectrics for Energy Storage , 2016, Advanced materials.

[6]  Ryan P. Lively,et al.  Seven chemical separations to change the world , 2016, Nature.

[7]  Geoff W. Stevens,et al.  Membrane-based carbon capture from flue gas: a review , 2015 .

[8]  Jiping Xu,et al.  A Simple Method for Prediction of Gas Permeability of Polymers from Their Molecular Structure , 1991 .

[9]  Anand Chandrasekaran,et al.  Impact of dataset uncertainties on machine learning model predictions: the example of polymer glass transition temperatures , 2019, Modelling and Simulation in Materials Science and Engineering.

[10]  L. Robeson,et al.  A group contribution approach to predict permeability and permselectivity of aromatic polymers , 1997 .

[11]  Ryan P. Lively,et al.  Defect-free PIM-1 hollow fiber membranes , 2017 .

[12]  Chiho Kim,et al.  From Organized High-Throughput Data to Phenomenological Theory using Machine Learning: The Example of Dielectric Breakdown , 2016 .

[13]  P. Labute.  A widely applicable set of descriptors. , 2000, Journal of molecular graphics & modelling.

[14]  Chiho Kim,et al.  Machine learning in materials informatics: recent applications and prospects , 2017, npj Computational Materials.

[15]  W. Koros,et al.  Physical aging of ester-cross-linked hollow fiber membranes for natural gas separations and mitigation thereof , 2018 .

[16]  Nikolai Gaponik,et al.  Highly emitting perovskite quantum dots are finally available in water , 2019, MRS Communications.

[17]  P. Selzer,et al.  Fast calculation of molecular polar surface area as a sum of fragment-based contributions and its application to the prediction of drug transport properties. , 2000, Journal of medicinal chemistry.

[18]  T. Merkel,et al.  50th Anniversary Perspective: Polymers and Mixed Matrix Membranes for Gas and Vapor Separation: A Review and Prospective Opportunities , 2017 .

[19]  Donald R Paul,et al.  Correlation and prediction of gas permeability in glassy polymer membrane materials via a modified free volume based group contribution method , 1997 .

[20]  Arun Mannodi-Kanakkithodi,et al.  Machine Learning Strategy for Accelerated Design of Polymer Dielectrics , 2016, Scientific Reports.

[21]  M. Szwarc,et al.  The permeability of polymer films to gases—a simple relationship , 1955 .

[22]  Mike Preuss,et al.  Planning chemical syntheses with deep neural networks and symbolic AI , 2017, Nature.

[23]  M. Salame.  Prediction of gas barrier properties of high polymers , 1986 .

[24]  A. Alentiev,et al.  A novel method for predictions of the gas permeation parameters of polymers on the basis of their chemical structure , 2015 .

[25]  Anand Chandrasekaran,et al.  Polymer Genome: A Data-Powered Polymer Informatics Platform for Property Predictions , 2018, The Journal of Physical Chemistry C.

[26]  A. Alentiev,et al.  Group contribution method for transport property predictions of glassy polymers: focus on polyimides and polynorbornenes , 1998 .

[27]  Onno E. de Noord,et al.  Machine Learning and Statistical Analysis for Materials Science: Stability and Transferability of Fingerprint Descriptors and Chemical Insights , 2017 .

[28]  W. M. Lee.  Selection of barrier materials from molecular structure , 1980 .

[29]  Arun Mannodi-Kanakkithodi,et al.  Scoping the polymer genome: A roadmap for rational polymer dielectrics design and beyond , 2017, Materials Today.

[30]  Arun Mannodi-Kanakkithodi,et al.  Mining materials design rules from data: The example of polymer dielectrics , 2017 .

[31]  L. Robeson,et al.  The upper bound revisited , 2008 .

[32]  Nidal Hilal,et al.  Membrane technology enhancement in oil–water separation. A review , 2015 .

[33]  L. Robeson,et al.  Correlation of separation factor versus permeability for polymeric membranes , 1991 .

[34]  Denis Roizard,et al.  Neural networks for the prediction of polymer permeability to gases , 2017 .