Artificial intelligence for performance prediction of organic solvent nanofiltration membranes

Abstract There is an urgent need to develop predictive methodologies that will fast-track the industrial implementation of organic solvent nanofiltration (OSN). However, the performance prediction of OSN membranes has been a daunting and challenging task, due to the high number of possible solvents and the complex relationship between solvent-membrane, solute-solvent, and solute-membrane interactions. Therefore, instead of developing fundamental mathematical equations, we have broken away from conventions by compiling a large dataset and building artificial intelligence (AI) based predictive models for both rejection and permeance, based on a collected dataset containing 38,430 datapoints with more than 18 dimensions (parameters). To elucidate the important parameters that affect membrane performance, we have carried out a thorough principal component analysis (PCA), which revealed that the factors affecting both permeance and rejection are surprisingly similar. We have trained three different AI models (artificial neural network, support vector machine, random forest) that predicted the membrane performance with unprecedented accuracy, as high as 98% (permeance) and 91% (rejection). Our findings pave the way towards appropriate data standardization, not only for performance prediction, but also for better membrane design and development.

[1]  Andrew G. Livingston,et al.  OSN Designer, a tool for predicting organic solvent nanofiltration technology performance using Aspen One, MATLAB and CAPE OPEN , 2013 .

[2]  Yong Sun,et al.  A simple coupled ANNs‐RSM approach in modeling product distribution of Fischer‐Tropsch synthesis using a microchannel reactor with Ru‐promoted Co/Al2O3 catalyst , 2019, International Journal of Energy Research.

[3]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[4]  Andrew G. Livingston,et al.  Sustainability assessment of organic solvent nanofiltration: from fabrication to application , 2014 .

[5]  Cormac Toher,et al.  Predicting superhard materials via a machine learning informed evolutionary structure search , 2019, npj Computational Materials.

[6]  Weida Tong,et al.  Comparing SVM and ANN based Machine Learning Methods for Species Identification of Food Contaminating Beetles , 2018, Scientific Reports.

[7]  Pieter Vandezande,et al.  Compositional optimization of polyimide-based SEPPI membranes using a genetic algorithm and high-throughput techniques. , 2009, Journal of combinatorial chemistry.

[8]  K. K. Sahu,et al.  Normalization: A Preprocessing Stage , 2015, ArXiv.

[9]  Andrew G. Livingston,et al.  An improved phenomenological model for prediction of solvent permeation through ceramic NF and UF membranes , 2012 .

[10]  Gyorgy Szekely,et al.  Bio-Inspired Robust Membranes Nanoengineered from Interpenetrating Polymer Networks of Polybenzimidazole/Polydopamine. , 2019, ACS nano.

[11]  Yang Wang,et al.  Prediction of higher-selectivity catalysts by computer-driven workflow and machine learning , 2019, Science.

[12]  Mirko Skiborowski,et al.  Machine-based learning of predictive models in organic solvent nanofiltration: Pure and mixed solvent flux , 2020, Separation and Purification Technology.

[13]  Levente Cseri,et al.  Membrane-assisted catalysis in organic media , 2017 .

[14]  Alexander Mitsos,et al.  Simultaneous rational design of ion separation membranes and processes , 2020, Journal of Membrane Science.

[15]  Andrew G. Livingston,et al.  Predictive membrane transport models for Organic Solvent Nanofiltration: How complex do we need to be? , 2015 .

[16]  Metin Bulut,et al.  Directed development of high-performance membranes via high-throughput and combinatorial strategies. , 2006, Journal of combinatorial chemistry.

[17]  Paul Geladi,et al.  Principal Component Analysis , 1987, Comprehensive Chemometrics.

[18]  Giorgos Borboudakis,et al.  Chemically intuited, large-scale screening of MOFs by machine learning techniques , 2017, npj Computational Materials.

[19]  A. Livingston,et al.  The Selectivity Challenge in Organic Solvent Nanofiltration: Membrane and Process Solutions. , 2017, Annual review of chemical and biomolecular engineering.

[20]  Philip Lutze,et al.  Characterisation of Organic Solvent Nanofiltration membranes in multi-component mixtures: Process design workflow for utilising targeted solvent modifications , 2014 .

[21]  Kristen A. Severson,et al.  Data-driven prediction of battery cycle life before capacity degradation , 2019, Nature Energy.

[22]  J. H. Zar,et al.  Significance Testing of the Spearman Rank Correlation Coefficient , 1972 .

[23]  Haiping Lu,et al.  MPCA: Multilinear Principal Component Analysis of Tensor Objects , 2008, IEEE Transactions on Neural Networks.

[24]  Jianzhong Wu,et al.  Toward the inverse design of MOF membranes for efficient D2/H2 separation by combination of physics-based and data-driven modeling , 2020 .

[25]  M. Buonomenna,et al.  Organic Solvent Nanofiltration in Pharmaceutical Industry , 2015 .

[26]  Gyorgy Szekely,et al.  Molecular separation with organic solvent nanofiltration: a critical review. , 2014, Chemical reviews.

[27]  Andrew G. Livingston,et al.  Sub–10 nm polyamide nanofilms with ultrafast solvent transport for molecular separation , 2015, Science.

[28]  Andrew G. Livingston,et al.  Polymer nanofilms with enhanced microporosity by interfacial polymerization. , 2016, Nature materials.