.png){kind=icon}
.png){kind=icon}
Return
Predicting Phase Behavior of Linear Polymers in Solution Using Machine Learning
.png){kind=icon}
PRE
AI
DOI：10.1021/acs.macromol.2c00245.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The phase behavior of polymers in solution is crucial to many applications in polymer processing, synthesis, self-assembly, and purification. Quantitative prediction of polymer solubility space for an arbitrary polymer-solvent pair and across alarge composition range is challenging. Qualitative agreement is provided by many current theoretical models, but only a portion ofthe phase space is quantitatively predicted. Here, we utilize a curated database for binary polymer solutions comprised of 21 linearpolymers, 61 solvents, and 97 unique polymer-solvent combinations (6524 cloud point temperatures) to construct phase diagramsfrom machine learning predictions. A generalizable feature vector is developed that includes component descriptors concatenatedwith state variables and an experimental data descriptor (phase direction). The impact of several types of descriptors (Morganfingerprints, molecular descriptors, and Hansen solubility parameters) to encode polymer-solvent interactions is assessed. Hansensolubility parameters are also introduced as a means to understand the general breadth of the linear polymer-solvent space as well asthe density and distribution of curated data. Two common regression algorithms (XGBoost and neural networks) establish thegenerality of the descriptors; provide a root mean squared error (RMSE) within 3 degrees C for predicted cloud points in the test set; andoffer excellent agreement with upper and lower critical solubility curves, isopleths, and closed-loop phase behavior by a single model.The ability to extrapolate to polymers that are very dissimilar from the curated data is poor, but with as little as 20 cloud points or asingle phase boundary, RMSE error of predictions are within 5 degrees C. This implies that the current model captures aspects of theunderlying physics and can readily exploit correlations to reduce required data for additional polymer-solvent pairs. Finally, themodel and data are accessible via the Polymer Property Predictor and Database (3PDb).
Keywords:
LIQUID-LIQUID EQUILIBRIA
CLOUD-POINT CURVES
FLORY-HUGGINS
PRESSURE-DEPENDENCE
POLYSTYRENE
THERMODYNAMICS
OPPORTUNITIES
ISOTOPE