Topic: Data-driven Science And Trustworthy Machine Learning For Dynamic Systems

Data-driven science and trustworthy machine learning techniques have become essential tools in advancing artificial intelligence (AI) for both scientific and engineering applications. One of the primary challenges in this field is extracting and understanding the physical properties and dynamic behaviors hidden within vast amounts of data from various engineering domains. Accurately identifying and modeling these dynamics is critical for effectively applying AI technologies. This Special Issue aims to bring together the latest theoretical advances in several key areas, including data-driven science for dynamic systems, interpretable and trustworthy machine learning techniques, and physics-informed learning approaches, as well as their engineering applications to the design and optimization of complex systems, advanced control strategies, condition monitoring, and system characterization, etc. We invite submissions across disciplines related to data-driven science and dynamic systems.

Trustworthy machine learning, data-driven science, interpretability, dynamics

30 Jun 2025