Deep learning-based estimation of Flory–Huggins parameter of A–B block copolymers from cross-sectional images of phase-separated structures

Abstract

In this study, deep learning (DL)-based estimation of the Flory–Huggins χ parameter of A-B diblock copolymers from two-dimensional cross-sectional images of three-dimensional (3D) phase-separated structures were investigated. 3D structures with random networks of phase-separated domains were generated from real-space self-consistent field simulations in the 25–40 χN range for chain lengths (N) of 20 and 40. To confirm that the prepared data can be discriminated using DL, image classification was performed using the VGG-16 network. We comprehensively investigated the performances of the learned networks in the regression problem. The generalization ability was evaluated from independent images with the unlearned χN. We found that, except for large χN values, the standard deviation values were approximately 0.1 and 0.5 for A-component fractions of 0.2 and 0.35, respectively. The images for larger χN values were more difficult to distinguish. In addition, the learning performances for the 4-class problem were comparable to those for the 8-class problem, except when the χN values were large. This information is useful for the analysis of real experimental image data, where the variation of samples is limited.

Renewable and Degradable Triblock Copolymers Produced via Metal-Free Polymerizations: From Low Sticky Pressure-Sensitive Adhesive to Soft Superelastomer

“…The degree of phase-separated behavior between two immiscible blocks can be defined as N χ AB , where N and χ AB are the total number of segments, and the Flory–Huggins interaction parameter is related to the interaction between the A and B components . Since the two PGM–PHL–PGM triblock copolymers in this study have the same χ AB value, the phase separation characteristic could be merely affected by the degree of polymerization ( N ).…”

Control of the Cell Structure of UV-Induced Chemically Blown Nanocellular Foams by Self-Assembled Block Copolymer Morphology

“…For PMMA-b-PtBA, the estimated value of χN is ∼18 at M n = 25500 g/mol (see the Supporting Information for the detailed calculations), which is larger than the theoretical limit. It is speculated that such a discrepancy may be caused by an overestimation of Flory−Huggins parameter for solvent annealing 61,62 and by no consideration of thermal fluctuation effects on phase separation. 63,64 At M n > 25500 g/mol, the size of lamellae becomes larger with increasing M n (Figure 5b−d).…”

Well-Defined Nanostructures by Block Copolymers and Mass Transport Applications in Energy Conversion

“…Three significant parameters are responsible for the microphase separation between the blocks: (1) the relative volume fraction f of each block, which is used to characterize the microscopic composition of BCP; (2) the Flory–Huggins parameter χ , which is used to characterize the interaction between the blocks [ 34 , 35 ] and is inversely proportional to the temperature change; (3) the total degree of polymerization N of the polymer. Among them, χN , which represents the phase separation strength, plays a decisive function in the separation state of BCP [ 36 ]. Increasing the temperature or decreasing χN gradually decreased the incompatibility between the blocks.…”