Machine learning (ML) is rapidly emerging as a powerful tool to improve the safety, reliability, and long-term performance of marine structures exposed to harsh ocean environments. This study presents a comprehensive review of ML and deep learning algorithms applied to marine engineering, highlighting how they enhance structural design, construction efficiency, and real-time maintenance. The work introduces a novel modeling framework that integrates mechanical principles with data-driven algorithms, improving interpretability and prediction accuracy. It also outlines key challenges such as data scarcity, environmental uncertainty, and model transparency, offering guidance for future research. The review provides valuable insights for structural engineers seeking to adopt ML technologies for next-generation ocean infrastructure.

Researchers from Southeast University have developed a compact, dual-band, dual-polarized phased array for B5G/6G millimeter-wave communication. The array integrates four independent beamforming systems on a single printed circuit board, supporting concurrent operations at 28 GHz and 38 GHz. It features scalable architecture, broad bandwidth, and high spectral efficiency, making it ideal for future high-speed wireless applications.

A research team led by Dr. Jae-Woo Choi from the Water Resources Recycling Research Group and Dr. Jin Young Kim from the Center for Hydrogen and Fuel Cells at the Korea Institute of Science and Technology (KIST, President Sangrok Oh) has developed an eco-friendly palladium recovery technology based on titanium-based maxene material ('TiOx/Ti3C2Tx') nanosheets. Existing overseas technologies operated only in strongly acidic environments, limiting their applicability to weakly acidic wastewater commonly found in industrial settings.

Healthy aging induces parallel changes in brain functional activity and structural morphology, yet the interplay between these changes remains unclear. Prof. Yuhui Du’s team at the College of Computer and Information Technology, Shanxi University, in collaboration with Prof. Vince D. Calhoun (Georgia State University), analyzed multimodal neuroimaging data from 27,793 healthy subjects (aged 49-76 years) in the UK Biobank. They proposed a unified framework for single-modal and multimodal brain-age prediction and joint functional-structural aging analysis, systematically characterizing diverse synergistic vs. contradictory aging patterns between functional network connectivity (FNC) and gray matter volume (GMV). Importantly, these joint patterns were further linked to specific cognitive decline. The study, titled “Joint aging patterns in brain function and structure revealed using 27,793 samples” was published in Research (2025, 8:0887; DOI: 10.34133/research.0887).