Roberto Del Prete

Information

Bio

Roberto is Ph.D. specializing in TinyML and edge computing. He focuses on enhancing time-critical decision-making through cutting-edge AI solutions for both space missions and Earth monitoring. His work focuses on developing innovative systems such as vision-based navigation and onboard AI solutions for analyzing Synthetic Aperture Radar (SAR) raw data.

Del Prete's professional journey includes roles as a Visiting Researcher at both the ESA Φ-lab and SmartSat CRC in Australia. Recognized for his contributions, he received the 2022 NATO STO Early Career Scientist Award and participated in the 2021 NASA-ESA Trans-Atlantic Training. Notably, he won the best presentation award at the AI4Space@CVPR workshop in 2024, and he has been a key contributor to high-impact projects like the Kanyini Mission. With more than 30 scientific publications, Del Prete's dedication to leveraging AI and remote sensing technologies aims to address global challenges in Earth Observation and space exploration.

Current Role

Currently, I serve as Internal Research Fellow at ESA, where I deploy tiny models in space. At ESA, I am dedicated to expanding the uptake of onboard machine learning.

Areas of Expertise

My expertise lies in several key areas of Remote Sensing, including Synthetic Aperture Radar (SAR), Multispectral and Hyperspectral imaging, and the processing of raw satellite data. I also specialise in Onboard AI, TinyML, and Embedded Systems, enabling efficient, edge-deployable models for spaceborne and aerial platforms. These specialisations empower me to develop advanced, low-latency analytics pipelines for critical applications such as Maritime Domain Awareness, Disaster Response, Wildfire Monitoring, and Vessel Detection. My integrated knowledge of spaceborne AI and remote sensing contributes directly to ESA Φ-lab CIN’s goals by supporting intelligent edge computing, onboard inference, and the rapid prototyping of transformative Earth

Vision for the Future

Driven by a vision of a future where Earth Observation systems operate autonomously at the edge—processing, interpreting, and reacting to data in real time onboard spacecraft, I am committed to advancing onboard AI, TinyML, and embedded analytics to enable self-aware satellites and smart EO constellations. My long-term goal is to bridge the gap between raw sensor data and actionable intelligence directly in space, thereby reducing latency, optimizing bandwidth, and empowering rapid decision-making in domains such as disaster response, maritime surveillance, and environmental monitoring. This work has the potential to transform how we use satellite data—moving from passive observation to proactive, onboard situational awareness, aligned with ESA Φ-lab mission to push the boundaries of Earth Observation innovation.

Project as CIN Researcher