Article Highlights
Updates every hour. Last Updated: 20-May-2026 11:16 ET (20-May-2026 15:16 GMT/UTC)
Innovative electro-filtration process achieves efficient wastewater treatment
Higher Education PressDiscover a groundbreaking wastewater treatment method that uses electro-filtration to remove harmful pollutants with remarkable efficiency. Learn how scientists have developed a novel membrane technology that simultaneously tackles nitrogen and carbon contaminants, offering a sustainable solution for cleaner water.
- Journal
- Engineering
Vision-language models revolutionize mobile robot navigation in smart manufacturing
Higher Education PressDiscover how cutting-edge vision-language models are transforming mobile robot navigation in smart manufacturing. Learn about a new system that enables robots to understand natural human language and navigate complex, unstructured environments with unprecedented accuracy and adaptability.
- Journal
- Engineering
Smart grid innovations: Increasing resilience, security, and sustainability in the era of energy transition
Higher Education PressAgainst the backdrop of global energy transition, smart grids have become pivotal yet face challenges in resilience, security, stability, and market operation. This special issue of Engineering features five cutting-edge studies, covering climate-resilient cyber–physical systems, carbon-coupled P2P trading mechanisms, power electronics-dominated grid stability, stealthy cyberattacks, and AI-enabled transient stability assessment, offering holistic solutions for sustainable smart grid development.
- Journal
- Engineering
AI-driven lab tackles “grand challenge” of inverse design
University of ChicagoIn new research from the University of Chicago Pritzker School of Molecular Engineering, Argonne National Laboratory and Purdue University, the AI-driven robotic lab Polybot designed and built new polymers that hit precise, targeted shades of orange and green – a task that takes researchers decades of experience to learn – in just 72 hours.
- Journal
- Journal of the American Chemical Society
Nitrogen-rich porous aromatic framework cathode for wide-temperature sodium-organic batteries
Science China PressResearchers have designed a nitrogen-rich porous aromatic framework material and investigated its electrochemical performance as the cathode material for sodium organic batteries. The aromatic framework material synthesized by introducing the redox-active hexaazatrinaphthylene (HATN) motif has a high redox potential and multi-ion storage capacity, and can still maintain a high capacity and excellent stability within the temperature range of -20 °C to 50 °C.
- Journal
- Science China Chemistry
ETRI achieves 100-meter underground wireless communication...Applied to underground disaster response
National Research Council of Science & TechnologyKorean researchers confirmed that underground wireless communication is possible, moving beyond the terrestrial wireless communication they have primarily focused on until now. This opened up a new wireless channel for confirming the survival of buried people in the event of a collapse of an underground facility such as a mine, conducting underground rescue operations, or conducting underground military operations.
- Journal
- IEEE Internet of Things Journal
- Funder
- Ministry of Science and ICT
Self-supervised learning opens a new path for neuroimaging analysis in brain disorders: a review highlights key opportunities from data scarcity to clinical translation
Health Data ScienceNeuroimaging analysis in brain disorders faces a persistent challenge: brain signals are complex and high-dimensional, while high-quality labeled datasets remain limited. This review article systematically examines how self-supervised learning can help address that gap by learning meaningful representations directly from unlabeled neuroimaging data. It covers major methodological families, including contrastive, generative, and hybrid generative-contrastive approaches, and discusses their applications in functional MRI, EEG, and multimodal brain network analysis.
The review argues that self-supervised learning offers more than annotation efficiency. It may enable more transferable and clinically useful representations for disease screening, diagnosis, and prognosis across heterogeneous datasets and disorders. At the same time, interpretability, data heterogeneity, missing modalities, and clinical validation remain major barriers. Future work will likely focus on stronger multimodal fusion, better cross-site generalization, and more clinically adaptable model design.
- Journal
- Health Data Science