Data-Driven Design of Next-Generation Metal Materials

The development of next-generation metallic materials is entering a transformative era driven by data-driven methodologies. Traditional trial-and-error experimental and computational approaches, while invaluable, are often time-consuming and resource-intensive. Recent advances in machine learning, artificial intelligence, and high-throughput computation have enabled the rapid exploration of vast compositional and microstructural spaces, facilitating the discovery of alloys with unprecedented combinations of strength, ductility, corrosion resistance, and thermal stability. These emerging data-driven approaches, when integrated with physics-based modeling and experimental validation, provide powerful tools for accelerating materials discovery and optimization, paving the way toward intelligent materials design and predictive manufacturing of high-performance alloys.This Research Topic aims to show the transformative power of data-driven methodologies in overcoming the traditional barriers of metal materials design. We seek to explore how machine learning, artificial intelligence, and advanced data analytics can be combined to establish predictive models that link composition, processing parameters to microstructure and final performance. The goal is to move beyond mere prediction towards active design, enabling the inverse creation of new alloys tailored for specific applications such as additive manufacturing, extreme environments, or sustainable technologies. We welcome contributions that demonstrate recent advances in using data to discover novel compositions, optimize thermo-mechanical processing, predict mechanical performance, and unravel complex physical phenomena in metals, thereby paving the way for materials development.We invite the submission of high-quality Original Research, Review, and Perspective articles that address the challenges and opportunities in data-driven metal materials design. Specific themes of interest include, but are not limited to:(1) Machine learning for the prediction of mechanical properties (e.g., strength, ductility, fatigue).(2) AI-guided discovery and optimization of high-entropy alloys and complex concentrated alloys.(3) Data-driven models for process optimization in additive manufacturing and other advanced manufacturing techniques.(4) Microstructure quantification and linkage to properties using computer vision and deep learning.(5) The development and application of machine learning interatomic potentials for accelerated atomistic simulations.(6) Frameworks for active learning and Bayesian optimization in closed-loop materials development.(7) Case studies on the integration of computational (e.g., CALPHAD, DFT, MD) and experimental data within AI models. Topic editors: Ling Qiao, Gongzhuang Peng, Shakti Padhy Source: https://www.frontiersin.org/research-topics/77615/data-driven-design-of-next-generation-metal-materials