An official website of the United States government
A computational framework that leverages data from self-consistent field theory simulations with deep learning to accelerate the exploration of parameter space for block copolymers is presented. This is a substantial two-dimensional extension of the framework introduced in the work of Xuan et al. [J. Comput. Phys. 443, 110519 (2021)]. Several innovations and improvements are proposed. (1) A Sobolev space-trained, convolutional neural network is employed to handle the exponential dimension increase of the discretized, local average monomer density fields and to strongly enforce both spatial translation and rotation invariance of the predicted, field-theoretic intensive Hamiltonian. (2) A generative adversarial network (GAN) is introduced to efficiently and accurately predict saddle point, local average monomer density fields without resorting to gradient descent methods that employ the training set. This GAN approach yields important savings of both memory and computational cost. (3) The proposed machine learning framework is successfully applied to 2D cell size optimization as a clear illustration of its broad potential to accelerate the exploration of parameter space for discovering polymer nanostructures. Extensions to three-dimensional phase discovery appear to be feasible.
more »
« less
Gaming self-consistent field theory: Generative block polymer phase discovery
Block polymers are an attractive platform for uncovering the factors that give rise to self-assembly in soft matter owing to their relatively simple thermodynamic description, as captured in self-consistent field theory (SCFT). SCFT historically has found great success explaining experimental data, allowing one to construct phase diagrams from a set of candidate phases, and there is now strong interest in deploying SCFT as a screening tool to guide experimental design. However, using SCFT for phase discovery leads to a conundrum: How does one discover a new morphology if the set of candidate phases needs to be specified in advance? This long-standing challenge was surmounted by training a deep convolutional generative adversarial network (GAN) with trajectories from converged SCFT solutions, and then deploying the GAN to generate input fields for subsequent SCFT calculations. The power of this approach is demonstrated for network phase formation in neat diblock copolymer melts via SCFT. A training set of only five networks produced 349 candidate phases spanning known and previously unexplored morphologies, including a chiral network. This computational pipeline, constructed here entirely from open-source codes, should find widespread application in block polymer phase discovery and other forms of soft matter.
more »
« less
- Award ID(s):
- 2011401
- PAR ID:
- 10506670
- Publisher / Repository:
- Proceedings of the National Academy of Sciences
- Date Published:
- Journal Name:
- Proceedings of the National Academy of Sciences
- Volume:
- 120
- Issue:
- 45
- ISSN:
- 0027-8424
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Compositionally asymmetric diblock copolymers provide an attractive platform for understanding the emergence of tetragonally close-packed, Frank–Kasper phases in soft matter. Block-polymer phase behavior is governed by a straightforward competition between chain stretching and interfacial tension under the constraint of filling space at uniform density. Experiments have revealed that diblock copolymers with insufficient conformational asymmetry to form Frank–Kasper phases in the neat-melt state undergo an interconversion from body-centered cubic (bcc) close-packed micelles to a succession of Frank–Kasper phases (σ to C14 to C15) upon the addition of minority-block homopolymer in the dry-brush regime, accompanied by the expected transition from bcc to hexagonally packed cylinders in the wet-brush regime. Self-consistent field theory data presented here qualitatively reproduce the salient features of the experimental phase behavior. A particle-by-particle analysis of homopolymer partitioning furnishes a basis for understanding the symmetry breaking from the high-symmetry bcc phase to the lower-symmetry Frank–Kasper phases, wherein the reconfiguration of the system into polyhedra of increasing volume asymmetry delays the onset of macroscopic phase separation.more » « less
-
A twin boundary (TB) is a common low energy planar defect in crystals including those with the atomic diamond structure (C, Si, Ge, etc.). We study twins in a self-assembled soft matter block copolymer (BCP) supramolecular crystal having the double diamond (DD) structure, consisting of two translationally shifted, interpenetrating diamond networks of the minority polydimethyl siloxane block embedded in a polystyrene block matrix. The coherent, low energy, mirror-symmetric double tubular network twin has one minority block network with its nodes offset from the (222) TB plane, while nodes of the second network lie in the plane of the boundary. The offset network, although at a scale about a factor of 10 3 larger, has precisely the same geometry and symmetry as a (111) twin in atomic single diamond where the tetrahedral units spanning the TB retain nearly the same strut (bond) lengths and strut (bond) angles as in the normal unit cell. In DD, the second network undergoes a dramatic restructuring—the tetrahedral nodes transform into two new types of mirror-symmetric nodes (pentahedral and trihedral) which alternate and link to form a hexagonal mesh in the plane of the TB. The collective reorganization of the supramolecular packing highlights the hierarchical structure of ordered BCP phases and emphasizes the remarkable malleability of soft matter.more » « less
-
Cationic glycylalanylglycine (GAG) self-assembles into a gel in a 55 mol% ethanol/45 mol% water mixture. The gel exhibits a network of crystalline fibrils grown to lengths on a 10 −4 –10 −5 m scale (Farrel et al. , Soft Matter , 2016, 12 , 6096–6110). Rheological data are indicative of a rather strong gel with storage moduli in the 10 kPa regime. Spectroscopic data revealed the existence of two gel phases; one forms below T = 15 °C (phase I) while the other one forms in a temperature range between 15 °C and the melting temperature of ca. 35 °C (phase II). We explored the reformation of the cationic GAG gel in 55 mol% ethanol/45 mol% water after thermal annealing by spectroscopic and rheological means. Our data reveal that even a short residence time of 5 minutes in the sol phase at 50 °C produced a delay of the gelation process and a gel of lesser strength. These observations suggest that the residence time at the annealing temperature can be used to adjust the strength of both gel phases. Our spectroscopic data show that the annealing process does not change the chirality of peptide fibrils in the two gel phases and that the initial aggregation state of the reformation process is by far more ordered for phase I than it is for phase II. In the gel phases of GAG/ethanol/water mixtures, ethanol seems to function as a sort of catalyst that enables the self-assembly of the peptide in spite of its low intrinsic propensity for aggregation.more » « less
-
null (Ed.)Generative Adversarial Networks (GANs) have shown impressive results for image generation. However, GANs face challenges in generating contents with certain types of constraints, such as game levels. Specifically, it is difficult to generate levels that have aesthetic appeal and are playable at the same time. Additionally, because training data usually is limited, it is challenging to generate unique levels with current GANs. In this paper, we propose a new GAN architecture named Conditional Embedding Self-Attention Generative Adversarial Net- work (CESAGAN) and a new bootstrapping training procedure. The CESAGAN is a modification of the self-attention GAN that incorporates an embedding feature vector input to condition the training of the discriminator and generator. This allows the network to model non-local dependency between game objects, and to count objects. Additionally, to reduce the number of levels necessary to train the GAN, we propose a bootstrapping mechanism in which playable generated levels are added to the training set. The results demonstrate that the new approach does not only generate a larger number of levels that are playable but also generates fewer duplicate levels compared to a standard GAN.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1073/pnas.2308698120
