In the framework of the AI-OBSERVER project, the capabilities of ERATOSTHENES Centre of Excellence (CoE) on Earth Observation (EO) based Disaster Risk Reduction are significantly enhanced through a series of capacity building activities on Artificial Intelligence (AI) that are provided by the project’s two advanced partners, the German Research Centre for Artificial Intelligence (DFKI) from Germany, and the University of Rome Tor Vergata (UNITOV) from Italy. These were designed, following a gap analysis of the existing staff and scientific capacity of the ERATOSTHENES CoE researchers, on the thematic research areas of: (i) Land movements (Earthquakes, Landslides and Soil erosion); (ii) Forest fires; (iii) Floods and extreme meteorological events; and (iv) Marine Pollution (oil spills, illegal waste damping, etc.). DFKI and UNITOV are transferring their scientific expertise through several workshops, webinars, short-term staff exchanges, summer schools and expert visits covering a combination of these AI-related topics, aiming to fill the identified gaps. All these will enable the ERATOSTHENES CoE researchers to build AI models for large scale image processing and Big EO data. Up to date, over thirty early stage and senior researchers have participated in these trainings. The knowledge transferred to ERATOSTHENES CoE will be utilised by its staff in a research exploratory project applying Artificial Intelligence on Earth Observation for multi-hazard monitoring and assessment in Cyprus, with the support of the advanced partners, leading to the development of the first ERATOSTHENES CoE product integrating EO and AI for Disaster Risk Reduction.
The Φsat-2 mission from the European Space Agency (ESA) is part of Φsat mission lineup aimed to address innovative mission concepts making use of advanced onboard processing including Artificial Intelligence. Φsat-2 is based on a 6U CubeSat with a medium-high resolution VIS/NIR multispectral payload (eight bands plus NIR) combined with a hardware accelerated unit capable of running several AI applications throughout the mission lifetime. As images are acquired, and after the application of dTDI processing, the raw data is transferred through SpaceWire to a payload pre-processor where level L1B will be produced. At this stage radiometric and geometric processing are carried out in conjunction with georeferencing. Once the data is pre-processed, it is fed to the AI processor through the primary computer and made available to the onboard applications; orchestration is done via a dedicated version of the NanoSat MO Framework. The following applications are currently baselined and additional two will be selected via dedicated AI Challenge by Q3 2023: SAT2MAP for autonomous detection of streets during emergency scenarios; Cloud Detection application and service for data reduction; the Autonomous Vessel Awareness to detect and classify vessel types and the deep compression application (CAE) that has the goal of reducing the amount of acquired data to improve the mission effectiveness.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.