Preserving the earth
As far as public knowledge reaches, human life along with the Earth ecosystems supporting it is absolutely unique in the whole cosmos. We the humans need to protect it, with all our might. Eating micro-plastics in our foods supply system doesn’t help it [ref]. Neither a rise of microplastic contamination in water help climate to cool down [ref].
Macroplastics is a precursor to microplastics. The 1st one can still be excavated from waters and recycled. However, when left too long, it turns in microplastics and ends up in tummies of sea-life and thereafter humans. Therefore detecting and tracking macro-plastics globally is of critical need to human and the planet health.
Some critical milestones on AI models addressing marine littering:
- 2025.06 – NTUA developed DNN for marine plastic detection on data that are sourced from Sentinel-2 and Planet and transferred to resemble BLK-1.
- 2026.06 – NTUA achieved DNN that can segment marine plastics in 3.7m resolution RGB images.
European FPGA in space for AI
Globally there are only a few FPGA manufacturers (major being Xilinx, Microchip, Intel), none of which is European. It is not by choice, but rather related to the high cost of silicone wafer production that makes it a rational choice to have only a few manufacturers of FPGAs globally. However, critical dependency on USA components for the whole space industry makes EU’s geopolitical relationships very strained.
In today’s digital age, particularly the wave of AI, having sovereign EU solution for AI processing is critical. For edge-AI ground applications the Dutch company Axelera-AI is gaining momentum, however, there is no VPU/GPU solution for space. Meanwhile, NanoXplore (NX), a French company, is focusing on building space-grade FPGAs, that can efficiently be used as AI accelerators. While NX company is focusing on making FPGAs, Edge-SpAIce consortium has been focusing on making SW that enables executing AI on it.
HLS4ML was developed by CERN, is an open source project that brings AI-acceleration to FPGAs. During Edge-SpAIce this framework was matured, with following major achievements:
- 2026.05 – 4.2k DNN executed on NX NG-Ultra
global marine litter monitoring Service
It would be great to have a tack of all big plumps of macroplastics globally. Not just track their spread and movements, but also the source and facilitate activities to avoid pollution in 1st place.
During Edge-SpAIce project, we as consortium got convinced it is feasible to achieve such goal, fully with European technologies. It would be based on 10 satellite constellation, with 9 multi-spectral and 1 hyper-spectral imagers. Estimated manufacturing cost would be appox. 90M€ over 2 year period. The constellation is seeking for financing interesee.