The main goal of the project is the development of a reliable and transparent system for the continuous assessment of the environmental impact of deep-sea exploration. With €16M funding - with close to €12M provided by the EC's Horizon Europe programme -, the project brings together 26 institutions from 10 countries, five of them Portuguese, including the Institute for Systems and Computer Engineering, Technology and Science (INESC TEC) - also acting as the project's leader.

Over the next three years, the project ENERSHARE - European commoN EneRgy dataSpace framework enabling data sHaring-driven Across- and beyond- eneRgy sErvices-, with INESC TEC as partner, will develop a reference architecture that facilitates data sharing in the energy sector.

INESC TEC strengthened its relationship with Asia by signing a Memorandum of Understanding (MoU) with RIKEN (Japan), through the Center for Computational Science (R-CCS). The collaboration aims to promote activities focusing on energy efficiency of the advanced computing operational centres that host the Fugaku and Deucalion supercomputers, contributing to position the two organisations at the forefront of green supercomputing.

José Manuel Mendonça led us in a journey through his memories and some of the most remarkable moments of his life: from his “kindergarten” days, with his paternal grandmother in Esmoriz, through the path – and passion – for martial arts, experiences abroad (in countries like Switzerland, Denmark or the United Kingdom), and the beginning of his academic career, in favour of the country’s Scientific and Technological System and public policies. In the end, he also reflected on the role played by the Universities and Science in addressing the challenges posed to the country and society. This was the Last Lecture of José Manuel Mendonça, Full Professor at the Faculty of Engineering of the University of Porto (FEUP) and Chairman of the Board of Directors at INESC TEC. 

A team of researchers from INESC TEC and the University of Munich tested a solution to classify seizures, the main symptom of epilepsy, using infrared radar and 3D videos. The study presents an innovative approach, which is the first to consider near-real time classification from two second samples, showing the feasibility of a system to support diagnosis and monitoring process (based on action recognition) that uses deep learning; it allows distinguishing between frontal and temporal lobes seizures (the two most common classes of epilepsy), or non-epileptic events. The results of this research were recently published by Nature Scientific Reports.