Deep Learning of Binary Solution Phase Behavior of Polystyrene

Ethier, Jeffrey G.; Casukhela, Rohan K.; Latimer, Joshua J.; Jacobsen, Matthew; Shantz, Allen B.; Vaia, Richard A.

doi:10.1021/acsmacrolett.1c00117

Cited by 24 publications

(18 citation statements)

References 37 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…UV–vis spectroscopy and small-angle X-ray scattering (SAXS) enable quantification of miscibility across the extreme range of solution concentration (>6 orders of magnitude) spanned by the coexistence curves, verify thermal reversibility, and establish a structure within the PGN-rich phase. Both methods are compatible with current liquid handling robots, automated data collection and analysis tools, and AI decision algorithms, enabling future autonomous data generation. − The solubility trends observed for the finite range of PGN architectures examined herein are consistent with established macromolecular-solution theory. The UCST behavior for a range of solvents of decreasing quality is comparable to linear chains in the same solvent.…”

Section: Discussionsupporting

confidence: 67%

Coexistence and Phase Behavior of Solvent–Polystyrene-Grafted Gold Nanoparticle Systems

et al. 2021

Self Cite

View full text Add to dashboard Cite

Polymer-grafted nanoparticles (PGNs) are widely used as additives or as single-component assemblies in numerous technologies, spanning from composites and coatings to membranes, optical elements, and printable electronics. How the design modularity of PGNs relates to their dispersibility and morphology in thermal or poor solvents, however, is not well established. Herein, we provide experimental volume fraction (ϕ)−temperature (T) coexistence curves (ϕ CE and T CE ) for polystyrene-grafted gold nanoparticles (PS-AuNPs) in solvents of various qualities (cyclohexane, cyclopentane, and ethyl acetate) using a combination of UV−vis spectroscopy and small-angle X-ray scattering. These systems exhibit upper critical solution temperatures, with coexistence curves that are broader and shifted to lower temperatures relative to their polymer analogs, consistent with prior reports of the impact of macromolecular branching. The coexistence curves span over 6 orders of magnitude in concentration, exhibit solvent-rich and solvent-poor arms that are ϕ PGN -dependent, display a reduction in critical temperature (T C *) as graft molecular weight decreases, exhibit an overall narrowing of the solvent-poor arm at higher graft molecular weights, and reveal a minimal influence of core nanoparticle volume (900−4200 nm 3 ). Additionally, the structure within the solvent swollen PS-AuNPs aggregates is disordered or face-centered cubic and depends on the aggregation temperature relative to T C * than on solvent characteristics. Such quantification of PGN phase behavior in thermal or poor solvents is used to demonstrate thermal fraction for purification and will inform future synthesis methods, self and directed assembly techniques, film and fiber processing, and formulation of inks, adhesives, thermosets, and coatings.

show abstract

Section: Discussionsupporting

confidence: 67%

Coexistence and Phase Behavior of Solvent–Polystyrene-Grafted Gold Nanoparticle Systems

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The cloud point refers to the temperature where a polymer is no longer miscible in a solution, which is essential for the synthesis, processing, purification, and self-assembly of polymer materials. Ethier et al [97] collected 3263 cloud point data of polystyrene in 19 different solvents, while the descriptors include singlephase orientation, Hansen solubility parameters (HSPs), topological fingerprints, polymer molecular weight, polymer volume fraction, polymer polydispersity index, and pressure. The prediction models based on HSPs solvent characteristics and fingerprint characteristics were constructed by DNN to predict the upper critical solubility and lower critical solubility.…”

Section: Recent Progress Of Machine Learning In Polymersmentioning

confidence: 99%

New Opportunity: Machine Learning for Polymer Materials Design and Discovery

Chen

et al. 2022

Advcd Theory and Sims

View full text Add to dashboard Cite

Under the guidance of the material genome initiative (MGI), the use of data‐driven methods to discover new materials has become an innovation of materials science. The polymer materials have been one of the most important parts in materials science for the excellent physical and chemical properties as well as corresponding complex structures. Machine learning, as the core of data‐driven methods, has taken an important place in polymer materials design and discovery. In this review, the authors have introduced the applications of machine learning in the design and discovery of polymer materials. The development tendency of published papers about machine learning in polymer materials, the commonly used algorithms, the polymer descriptors, the workflow of machine learning in polymer materials, and recent progresses of machine learning in materials are summarized. Then, the detail of how to use machine learning to assist design and discovery of polymer materials is fully discussed combined with two cases. Finally, the opportunities and challenges on the future development prospects of machine learning in the field of polymer materials are proposed.

show abstract

“…The state descriptors include concentration (polymer volume fraction), pressure, and temperature (our target or “label” feature). The experimental descriptor is required to distinguish the different cloud points and miscibility regions in T –ϕ space, which was first introduced in our previous work with polystyrene . Hence, the temperature region of complete miscibility for a particular cloud point is encoded into this descriptor.…”

Section: Computational Detailsmentioning

confidence: 99%

Predicting Phase Behavior of Linear Polymers in Solution Using Machine Learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

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 a large composition range is challenging. Qualitative agreement is provided by many current theoretical models, but only a portion of the phase space is quantitatively predicted. Here, we utilize a curated database for binary polymer solutions comprised of 21 linear polymers, 61 solvents, and 97 unique polymer–solvent combinations (6524 cloud point temperatures) to construct phase diagrams from machine learning predictions. A generalizable feature vector is developed that includes component descriptors concatenated with state variables and an experimental data descriptor (phase direction). The impact of several types of descriptors (Morgan fingerprints, molecular descriptors, and Hansen solubility parameters) to encode polymer–solvent interactions is assessed. Hansen solubility parameters are also introduced as a means to understand the general breadth of the linear polymer–solvent space as well as the density and distribution of curated data. Two common regression algorithms (XGBoost and neural networks) establish the generality of the descriptors; provide a root mean squared error (RMSE) within 3 °C for predicted cloud points in the test set; and offer 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 a single phase boundary, RMSE error of predictions are within 5 °C. This implies that the current model captures aspects of the underlying physics and can readily exploit correlations to reduce required data for additional polymer–solvent pairs. Finally, the model and data are accessible via the Polymer Property Predictor and Database (3PDb).

show abstract

Deep Learning of Binary Solution Phase Behavior of Polystyrene

Cited by 24 publications

References 37 publications

Coexistence and Phase Behavior of Solvent–Polystyrene-Grafted Gold Nanoparticle Systems

Coexistence and Phase Behavior of Solvent–Polystyrene-Grafted Gold Nanoparticle Systems

New Opportunity: Machine Learning for Polymer Materials Design and Discovery

Predicting Phase Behavior of Linear Polymers in Solution Using Machine Learning

Contact Info

Product

Resources

About