Topic: AI-Driven Inverse Design and Automated Platforms for Metamaterials

The design of engineered metamaterials is undergoing a paradigm shift, transitioning from heuristic trial-and-error to data-driven, algorithmically guided synthesis. While traditional pipelines rely heavily on physics-based simulations, the integration of deep generative models and inverse design frameworks now enables the direct mapping from target properties to optimal microstructures, processing pathways, and manufacturing strategies. Beyond algorithmic advances, the field is witnessing the rise of AI-driven automated design platforms that unify computational discovery with physical realization.

This Special Issue focuses on the full lifecycle of metamaterial innovation: from AI-powered topology generation, microstructure characterization and reconstruction, and multi-objective optimization, to digital twin-assisted manufacturing, autonomous experimentation, and intelligent fabrication. Particular attention will be given to emerging paradigms such as agentic AI, self-driving laboratories, and closed-loop experimental workflows that continuously connect design, synthesis, characterization, and validation.

Such integrated systems are pivotal for translating theoretical designs into robust engineering applications in mechanics, acoustics, and thermal management, and multifunctional materials. We invite cutting-edge contributions that leverage generative deep learning, inverse design methodologies, intelligent optimization, and automated experimentation within these workflows. We particularly welcome studies demonstrating the seamless integration of design, fabrication, characterization, where real-world experimental data is utilized to improve algorithmic performance and accelerate the lab-to-fab transition for complex engineered systems.

Metamaterials, Inverse design, Generative deep learning, Autonomous metamaterials discovery, Closed-loop optimization, AI-driven design automation, Surrogate modeling, Design-to-fabrication integration