ESA title

About We Explore

Our goal is to enable a connected network of talent that unites expertise and ideas from researchers, industry executives, ICT players, innovators and start-ups to foster learning and to exploit EO products with new technologies for human prosperity on planet Earth

Supported by a core team of staff overseeing its innovation strategy, Φ-lab operates as an open space, collaborative platform. We operate as a kind of “think tank” for exploring transformative innovation and as an ESA hub and catalyst within the network of EO academic and industrial researchers across Europe and globally.

As an open innovation lab, we host a diverse team of researchers, i.e. comprising ESA research fellows, Young Graduate Trainees, Visiting Researchers and Professors from both academia and industry, all collaborating to investigate new ideas together.

Our people

The ESA Φ-lab Explore Office explores innovative technologies to revolutionise and accelerate the future of EO.

Activities are organised within three technological axes to use untapped potential for EO technologies and applied to all elements of the Earth observation sector:

AXIS I

Artificial Intelligence and Machine Learning

AXIS II

Quantum and Edge Computing

AXIS III

The Internet of Things, Web 3, Blockchain and Cognitive Cloud Computing in Space

Flight HW
Flight SW applications
Downstream applications
End to end systems
Innovative business models

Φ-lab, in developing its own competences, is mainly active within three technology axes, and applies them to all elements of the Earth observation sector.

Artificial Intelligence and Machine Learning currently form the core of our research activities and a significant part of the InCubed programme, testifying to the fact that Artificial Intelligence is also a transformative technology in space.

We develop algorithms, contribute to the growth of the AI4EO community, and host Visiting Researchers from industry to generate their next disruptive product or service with us.

R&I ACTIVITIES, FOCUS AND STRATEGY

Discover the Φ-lab Explore Office

Focus on AI4EO

Quantum computing for EO

Destination EARTH

Φ-sat programme

The Φ-lab challenges

Our people

Research Use Cases

Optic

Automating methods of data assimilation

Automating methods of data assimilation
Optic

Volcanic eruptions detection through Convolutional Neural Networks

Volcanic eruptions detection through Convolutional Neural Networks
Radar (SAR)

Use of AI for onboard SAR image classification

Use of AI for onboard SAR image classification
Radar (SAR)

Spatiotemporal crop type classification with Deep Learning applied to SAR time series

Spatiotemporal crop type classification with Deep Learning applied to SAR time series
Optic

Supporting EO with hyperspectral images

Supporting EO with hyperspectral images
Optic

An unsupervised solution for detecting urban changes using optical images

An unsupervised solution for detecting urban changes using optical images
Optic

Crop mapping with multi temporal and multi-sensor images

Crop mapping with multi temporal and multi-sensor images
Optic

Sensor-independence for cloud masking

Sensor-independence for cloud masking
Optic

Machine Learning analysis of swarm data

Machine Learning analysis of swarm data
Optic

Seeing through clouds challenge

Seeing through clouds challenge
Radar (SAR)

Burned area reporting from Copernicus Sentinel-1 analysis-ready data

Burned area reporting from Copernicus Sentinel-1 analysis-ready data
Radar (SAR)

Advancing data-driven land applications with Copernicus Sentinel-1

Advancing data-driven land applications with Copernicus Sentinel-1
Optic

Bringing Convolutional Neural Networks to the edge

Bringing Convolutional Neural Networks to the edge
Radar (SAR)

Infrastructure monitoring in desert regions

Infrastructure monitoring in desert regions
Optic

Crop types mapping using drones, Copernicus Sentinel-2 and daily life images

Crop types mapping using drones, Copernicus Sentinel-2 and daily life images
Optic

Physics-Based machine learning for Copernicus Sentinel-5P methane retrieval

Physics-Based machine learning for Copernicus Sentinel-5P methane retrieval

Building Capacity

The Rise of AI for EO and the Φ-lab Explore Office

Imperative MOOCs – Earth Observation, Disruptive Technology and New Space

Immersive Experience (IE)

Gaming Approaches for Crowdsourcing Urban Information

Crowdsourcing Platform

Machine Learning Toolbox for Hyperspectral Data

Dynamic U-Net for tracking a rapidly changing planet

Spatio-temporal Deep Learning for land cover classification

EO-Learn Open-Source Toolkit

Speckle filtering through Convolutional Neural Networks

The Open SAR Toolkit for Sentinel-1 Analysis-Ready Data

Subscribe to our newsletter

Share