From global open multi-source data to network-wide traffic flow: A large-scale case study across multiple cities
Peer-Reviewed Publication
Updates every hour. Last Updated: 11-Jun-2026 03:15 ET (11-Jun-2026 07:15 GMT/UTC)
To address the trade-off between accuracy and cross-city generalization in traffic flow estimation, a research team from The Hong Kong Polytechnic University and New York University proposes a novel framework based on global open multi-source (GOMS) data, including urban structures and population density. By developing an advanced graph neural network model that effectively fuses these static urban features with dynamic traffic data, the study achieves stable and accurate network-wide traffic estimation, as validated across 15 diverse cities in Europe and North America.
Researchers at National University of Singapore used multiple interpretable machine learning methods to predict traffic congestion in in Alameda County in the San Francisco Bay Area, USA, during the pre-lockdown, lockdown, and post-lockdown periods.
The Universitat Jaume I in Castelló will develop six research and innovation projects in areas such as environmental sustainability and risk detection to improve disaster response through funding obtained in the competitive call for proposals from the Valencian Innovation Agency (AVI) (IVACE+e innovación) 2025, which seeks to promote innovation, R&D transfer and collaboration between universities, technology centres and companies.
The UJI has obtained funding in three lines of the call financed by the European Union within the framework of the European Regional Development Fund (ERDF) Programme for the Valencian Community 2021-2027 – IVACE+ for an amount of nearly one million euros, with which it will promote six projects with direct technological and social impact to respond to real challenges.
The various initiatives led by UJI research staff will provide innovative solutions in the field of environmental sustainability through advanced technologies to improve water quality and management, strengthen the circular carbon economy, promote cleaner and safer production systems aligned with green technology, and strengthen the innovation ecosystem through materials with a lower environmental impact. They also seek to anticipate responses to situations of risk due to natural disasters resulting from climate change.
Colloidal quantum dot (QD) light-emitting diodes have great potential in display applications. However, their commercialization remains a challenge due to the difficulty in achieving high-resolution patterning of QDs without degrading their optical properties. To address this, researchers have developed a nondestructive method for ultrahigh-resolution QD patterning. By blending QDs with a photocrosslinkable polymer, the approach preserves their optical properties and boosts efficiency and lifetime, paving the way for development of next-generation display technologies.
Electropulsing treatment rapidly heats metallic materials using high-density electrical pulses. Scientists at Pusan National University have now isolated its thermal and athermal effects in magnesium alloys using a novel T-type specimen. Their findings show that athermal effects significantly accelerate strain-induced boundary migration and grain growth—revealing how electropulsing can act as a fast, energy-efficient next-generation processing technology for lightweight metals.
In a study published in Nature Communications, researchers from the University of York synthesised over 700 complex metal compounds in just one week. This rapid screening process identified a promising new iridium-based antibiotic candidate that kills bacteria while remaining non-toxic to human cells.
Researchers have developed a new way to decipher the language of the brain by listening to and recording the fastest and faintest communications signals of neurons. This allows scientists to watch neurons talk to each other in real time. Until now, detecting these incoming signals in living brain tissue was nearly impossible; but now, researchers can hear the entire conversation rather than fragments of it.