Topological defects are key to determining the behavior of many advanced materials, but predicting their formation has typically relied on slow, computationally intensive simulations. However, researchers at Chungnam National University have developed a deep learning approach that can identify stable defect configurations in nematic liquid crystals within milliseconds rather than hours. By dramatically reducing computation time while maintaining accuracy, this method could accelerate the design of advanced materials that currently depend on lengthy trial-and-error experimentation.

In the physical world, many intricate structures are formed through symmetry breaking. When a system with inherent symmetry transitions into an ordered state, it can form stable imperfections known as topological defects. These defects are found everywhere, from the large-scale structure of the universe to everyday materials, making them a powerful way to study the ways in which order emerges in complex systems.

Nematic liquid crystals can be used to study these defects. In these materials, molecules can rotate freely while remaining roughly aligned, providing a clear and controllable platform for observing the ways in which defects form, move, and reorganize. These defect structures are usually described using the Landau–de Gennes theory, which mathematically captures how molecular order breaks down in defect cores where orientation becomes undefined.

Researchers led by Professor Jun-Hee Na from Chungnam National University in Korea have developed a faster way to predict stable defect configurations using deep learning.

Their method, published in the journal Small last fall, replaces time-consuming conventional numerical simulations, generating results in milliseconds rather than hours. “Our approach complements slow simulations with rapid, reliable predictions, facilitating the systematic exploration of defect-rich regimes,” Prof. Na said.

The model employs a 3D U-Net architecture, a convolutional neural network widely used in scientific and medical image analysis, to capture both global orientational order and local defect structures. The framework works by directly linking prescribed boundary conditions to the final equilibrium structure. Boundary information is fed into the neural network, which then predicts the complete molecular alignment field, including defect locations and shapes. The model was trained on data generated using conventional simulations covering a wide range of alignment patterns. Once trained, it can accurately predict new configurations it has never seen, with results that agree closely with both simulations and experiments.

The model learns the underlying physical behavior directly from data rather than relying on explicit equations. This allows it to handle highly complex situations, such as higher-order topological defects, where defects can merge, split, or rearrange. Experimental tests confirmed that the network correctly reproduced these behaviors, demonstrating its robustness across various conditions.

By allowing researchers to rapidly explore large design spaces, this approach also opens new possibilities for rapidly designing materials with specific defect architectures for sophisticated optical devices and metamaterials.

“By drastically shortening the material development process, AI-driven design could accelerate the creation of smart materials for applications ranging from holographic and VR or AR displays to adaptive optical systems and smart windows that respond to their environment,” Prof. Na stated.

Located in Daejeon, South Korea, Chungnam National University (CNU) was established in 1952 and offers diverse programs in engineering, medicine, sciences, and the arts, fostering innovation and global collaboration. Situated near Daedeok Innopolis, a major R&D hub, it excels in biotechnology, materials science, and information technology. With a vibrant international community and cutting-edge facilities, CNU continues to drive academic and technological advancements.

Title of original paper: “Spontaneous Wrinkle Collapse in Anisotropic Condensed Matter Predicted by Deep Learning.”