Novel Edge-AI system for accurate and near real-time
plastic detection and monitoring
in marine environment
HLS4ML Tutorial at FastML conference 2026
On FML conference Georgios Flengas (CERN) with Marius Köppel (ETH Zurich) gave a tutorial on HLS4ML use, the framework that is used also in Edge-SpAIce for AI deployment on FPGA fabric.
Participation in EuroGEO workshop
The EuroGEO Marine & Coastal Action Group workshop in Geneva on 6-7th of July 2026 was a great coming together of researchers and project managers for those working on marine and coast ecosystem protection.
HLS4ML Tutorial at FDF 2026
The project’s consortium parter CERN presented HLS4ML use in Edge-SpAIce during the FPGA Developer Forum (FDF) on 29th May 2026 at CERN.
The project
Satellites are crucial for Earth observation, attracting significant investment from both the private and public sector and potentially reshaping global economics.
However, current data management infrastructure cannot sufficiently maximise the value of the increasing amount of data captured.
To address this, the EU-funded Edge SpAIce project plans to develop an efficient approach to deploy deep neural networks (DNNs) at the edge for : more effective data management, targeting continuous data flow between capture and processing.
Despite challenges such as high computational power requirements and complex DNN architectures, Edge SpAIce will optimise AI execution, enabling its compatibility with various on-board satellite hardware.
The ultimate goal is to demonstrate the potential of edge-AI technology by deploying a DNN for remote monitoring of marine plastic litter on a satellite.
Our solution
Towards this end, Edge SpAIce will develop a highly accurate use case demonstrator DNN for efficient marine plastic litter detection in hyperspectral satellite images based on publicly available database.
Then Edge SpAIce will improve the capabilities of AGS’s proprietary DNN distillation tool (ODiToo), allowing at least 50x size reduction of DNN with minimal accuracy loss for deployments on SoC FPGAs used on satellites.
Edge SpAIce then will extend HLS4ML tool capabilities to support developed DNN deployment to European FPGA (NanoXplore) and a target satellite FPGA (Xilinx).
Thus Edge SpAIce will eventually demonstrate forefront and highly competitive performance on the system deployed for in-orbit remote monitoring of plastic litter in marine environment, demonstrating clear technological advancements beyond the state of the art and achieve TRL 6 for European-based edge-AI FPGA application.
Successful DNN architecture downsizing and accurate detection capabilities demonstration will represent a challenge throughout the whole implementation and realisation of the project. At the same time they will constitute an ambitious goal for Edge SpAIce to demonstrate a highly effective pipeline for Edge-AI system deployments.
the Edge SpAIce project
Enabling complex DNN architecture resizing with minimal accuracy lost
Edge deployment of AI in representative SoC-FPGAs for on-board use on satellites
Accurate and continuous marine plastic litter detection and monitoring from space
