Φ-lab Challenges is dedicated to organising cutting-edge innovative challenges in partnership with esteemed partners and sponsors. These challenges not only promote the growth and engagement of the Φ-lab community, but also provide a platform for researchers and talented innovators to showcase their work and make a tangible impact in solving some of society’s most pressing challenges.

By leveraging transformative technologies like AI, ML, Quantum Computing, and others, and utilising Earth observation, we aim to exctract valuable insights and information to drive positive change for human prosperity.

Φ-lab Challenges is an initiative of ESA Φ-lab implemented by a consortium of private companies and startups composed of Novaspace, Planetek Italia, Sinergise, GMATICS and EarthPulse.

New Challenge now available

Join now

The Reaching new heights with GeoFM Challenge is now officially open! The ESA Φ-lab is proud to join the International Telecommunication Union and AI for Good to co-host a new instance in their ongoing GeoAI series 🚀

Join this global initiative to explore how geospatial foundation model embeddings can power multi-task learning for building and vegetation segmentation and height estimation using open satellite data.

Don’t miss your chance to contribute to next-generation global mapping and make an impact aligned with the UN Sustainable Development Goals 🌍

Ready for the final sprint?

The ESA Φ-lab, together with KP Labs, Bias Variance Labs, Telespazio, and the Silesian University of Technology, invite AI researchers, developers and EO enthusiasts from around the world to a new exciting Challenge.

The ClearSAR-Track 1 Challenge will have you work on AI-based methods to detect and mitigate radio frequency interference in Copernicus Sentinel-1 SAR data. We are on the final sprint: You have until 13 May to work on your submission and code your way up onto the podium!

ClearSAR Track-1 Challenge

Join now

Open challenges

AI for Earthquake Response

When disaster strikes, time is critical. With this challenge, the ESA Φ-lab and the International Charter ‘Space and Major Disasters’ invite you to develop AI models that can rapidly detect earthquake damage using satellite imagery – helping emergency teams assess destruction faster and act where it matters most. Bring space, AI, and impact together to support real-world crisis response. […]

Read More… from AI for Earthquake Response

EASi Workshop // HYPERVIEW2

The new HYPERVIEW2 Challenge is implemented as part of the Explainable AI in Space (EASi) workshop, that KP Labs, ESA, and the Φ-Lab Challenges team are organising as part of the European Conference on Artificial Intelligence (ECAI), which is hosted in Bologna, Italy from 25th–30th October 2025. […]

Read More… from EASi Workshop // HYPERVIEW2

PANGAEA

PANGAEA is a new evaluation and benchmarking protocol that covers a diverse set of datasets, tasks, resolutions, sensor modalities, and temporalities. This challenge is open-ended, giving participants the flexibility to explore, experiment, and iterate on their models over time. Alongside the open challenge, we’ll be launching regular Data Sprints – short, high-impact tasks that run for about two months each and focus on specific use cases within the PANGAEA dataset. These sprints will come with their own goals, deadlines, and prizes. […]

Read More… from PANGAEA

Encouraging Interaction

ESA Φ-lab challenges

ESA Φ-lab Challenges, an initiative from Φ-lab of ESA’s Directorate of Earth Observation Programmes, strives to bring the worlds of AI and EO closer to encourage interaction and collaboration.

Artificial Intelligence

When large amounts of data is captured by remote sensing devices on EO satellites, our computers and AI algorithms can be used to help us solve problems. They can learn to recognise patterns and find correlations that humans would otherwise miss.

Earth observation

EO data allows us to gather global information about our planet Earth’s physical, chemical and biological systems via satellites carrying remote sensing devices.

Funded and initiated by

Implemented by