Copernicus Knowledge Base

Artificial Intelligence (AI) is not just a futuristic concept; it's a critical tool shaping the present, especially in the field of Earth Observation (EO). This is particularly evident in Copernicus, the Earth Observation component of the EU Space Programme, where, more and more, AI algorithms are employed to process the extensive data streams from Copernicus satellites. This marriage of machine intelligence and big satellite data is enabling a wide range of applications across various domains. From rapidly identifying environmental changes like deforestation or urban expansion to monitoring air quality and ocean temperatures for climate research, the use of Copernicus data with AI is transforming our understanding of the Earth’s surface in unprecedented ways. 

Quicker processing of data 

Copernicus generates around 25 terabytes of data every day. Sifting and sorting this data, let alone performing meaningful analytics from it would be near-impossible by hand. AI can be used to mine and manipulate data far more efficiently.

Software can be used to transform Copernicus data from raw- into application-ready form, while AI algorithms can identify patterns, anomalies, and changes in the environment. This brings added value to the end-user, who may at that point use the AI-derived insights for decision-making and better monitoring.

Improving crop monitoring

Earth Observation holds great promise for agriculture, and AI adds an exciting boost to these prospects. AI-powered EO helps farmers track crop health and optimise irrigation and fertiliser use. This results in increased crop yields and more sustainable agriculture practices.

One player in the field of using AI for agricultural information is CORAmaps, a German startup company. Their focus lies in harnessing AI-based interpretation of satellite radar data to provide insights on land conditions. Their specialisation extends to detailed and rapid assessment of agricultural areas, providing critical information such as crop types, quantities, and quality. Take this delineation of potato crops near the town of Lehrte, Germany, as an example:

Moreover, by leveraging radar data from Copernicus Sentinel-1 and combining it with extra data streams, CORAmaps can produce large-scale crop maps — a great resource to monitor food supply.

Detecting land cover change

Seeing how land changes from space can be tricky. Satellite images often show significant variations between different acquisitions. Many factors can cause these variations, such as seasonal shifts in vegetation and alterations caused by meteorological conditions. These fluctuations pose a challenge when we want to look for genuine land cover changes (like deforestation) with single-pixel time series data.

To address this, VITO Remote Sensing developed a detection algorithm using deep neural networks. These are a class of artificial networks with multiple layers, designed to model and solve complex large scale problems by simulating human neurons. 

VITO’s algorithm extracts compressed image features to identify areas with changing land cover. To build it, the team adapted an existing algorithm called Tile2Vec to ensure the separation of seasonal (change of foliage colour and other natural-occurring changes) from structural information (deforestation caused by fires, for example). This enables better land cover change detection. The team trained the algorithm on a set of 500 000 image patches from the Copernicus Sentinel-2 mission as well as Planet Fusion imagery making it so that it is not affected by seasonal effects. The resulting algorithm is capable of detecting land cover changes while ignoring naturally occurring ones.

Managing and dealing with natural disasters

You already know that Copernicus helps with emergency response with its Copernicus Emergency Management Service (CEMS), but AI can boost these efforts. Currently, with each emergency activation, CEMS teams provide maps of the disaster sites in a semi-automated process — they analyse Earth Observation datasets manually but also with the help of some AI algorithms. This can become a demanding process, especially when we consider that, in the future, the increasing frequency of natural disasters due to climate change will create even larger datasets. Automated data processing at scale can assist these teams, allowing them to harness Earth Observation data to its maximum potential.

But AI's assistance doesn't end here; this technology also plays a crucial role in quantifying the aftermath of natural disasters.

DSE (Data Science Experts), a company from France, developed AIperion, a system that evaluates agricultural damage caused by natural disasters. Leveraging AI and Earth Observation data, AIperion identifies flooded and burned areas, quantifies drought impact, and assesses damage to agricultural fields. The system integrates meteorological data from the Meteosat Second Generation (MSG) mission and relies on data from the Copernicus Sentinel-1 and Sentinel-2 missions to calculate vegetation indices. This approach not only provides valuable insights into crop health and the causes of damage but also supports insurance companies in determining premiums for crop losses attributable to natural disasters.

Filling in the marine gaps

AI has proven itself very useful to the Copernicus Marine Service (CMEMS) too. The service has implemented machine learning in a recent project known as 3DA. Ocean observations obtained primarily from satellites often have gaps in them. 3DA helps fill in these gaps.

Within the project, a machine learning programme was trained on sets of historical data, reinforcing the expected structure of Copernicus’ information. Its learnings were then applied to patch data in the ‘gappy’, as well as to predict its evolution through time; a feature not available using previous technologies. CMEMS uses AI in other ways and you can check other strategies the service is implementing here.

The AI4Copernicus project

Another project already in place is the AI4Copernicus. At its core, the initiative uses the AI4EU AI-on-demand platform to establish a digital environment for Copernicus data users, including researchers and innovators. 

The project has three main goals: firstly, integrating the vast resources and extensive Earth Observation data from existing providers, alongside training materials and expertise, enriching the AI4EU resources catalogue. Secondly, it strives to stimulate diverse communities within AI4EU and Copernicus, encouraging them to collaboratively tackle real-world challenges through a series of open calls. Lastly, AI4Copernicus aims to propel the advancement, adoption, and profound impact of the platforms involved, particularly AI4EU and the Copernicus Data Access platforms.

What lies ahead

In this article, we've only scratched the surface of how AI can supercharge Copernicus. But what's on the horizon is nothing short of thrilling. As we venture deeper into the uncharted territory of AI, the possibilities for harnessing massive amounts of satellite data are boundless. 

Entities like the European Space Agency (ESA), the European Centre for Medium-Range Weather Forecasts (ECMWF), and the European Organisation for the Exploitation of Meteorological Satellites (EUMETSAT), armed with Copernicus data, are embarking on the European Commission's Destination Earth initiative (DestinE). This visionary endeavour will craft a digital twin of our planet, a complete virtual model of Earth's dynamic systems — the atmosphere, oceans, and land. With this digital twin at our fingertips, we can meticulously monitor and better comprehend climate change, biodiversity loss, and the myriad impacts of human activity, all grounded in real-world data.  It's a bold leap into Earth's future, made possible by blending modern AI with Copernicus' full, free, and open data.

Useful Links

Destination Earth on YouTube

As the saying goes, a picture is worth a thousand words, but in the world of Earth Observation (EO), it can be worth so much more. With the boom in EO satellite missions over the past few decades, and the open data deluge resulting from the full-scale deployment of the Copernicus Sentinel satellites and thematic services; the truth is that we now have far more data to study our planet than ever before. But how do we make sense of it all and tell meaningful stories that engage audiences? In today's Observer, we'll look at a new EO Data Visualisation Good Practice guide, a new tool assembled by the European Organisation for the Exploitation of Meteorological Satellites (EUMETSAT), meant to help users craft and tell impactful stories.

Origins of the guide

While satellite imagery has been available since the 1980s, there have been significant recent additions to the list of available sources of Earth Observation data. Copernicus has ushered in a new era of freely available EO imagery and data. In addition to the Copernicus Sentinel and EUMETSAT satellites (Meteosat and Metop), which provide a bird's-eye view of our planet, there are dedicated Copernicus services that combine remote sensing with in situ data. These services meet users' needs for marine, atmospheric, climate, emergency-related and land data. 

Thus, now that we have new and comprehensive data on our planet, we can tell better stories about it. This why EUMETSAT brought together Copernicus data visualisers and communication professionals last year in a series of workshops which then resulted in the creation of a good practice guide.  

The series covered the effective strategies for visualising Copernicus data and storytelling tips. It brought together the perspectives of journalists, scientists, data visualisation experts, and remote sensing practitioners from operational agencies and industry. The series introduced attendees to the world of Earth Observation data visualisation and featured testimonials from world-class journalists who use EO imagery to tell powerful stories in their publications.

“For me as a journalist and for a very quick turnaround, satellite imagery provides a really valuable opportunity to show the public something they can remember because it’s so visual,” said Kasha Patel, who covers weather, climate change and the environment for the Washington Post, during the workshops.

The workshops also showed participants how to use EO data to communicate to the public about air quality, with a particular focus on using data from the Copernicus Atmosphere Monitoring (CAMS), Marine (CMEMS), Climate (C3S) and Emergency Management (CEMS) Services. Participants also gained a deeper understanding of how to use Copernicus data to tell stories about the oceans, sea ice and climate extremes.

More than 1,500 people attended the sessions and users from all over the world have since viewed the recordings. Representatives from news outlets such as the BBC, The New York Times, Le Monde, Agence France-Presse (AFP) and the Financial Times talked about their use of Copernicus imagery and data, while actors from various institutions such as the European Commission’s Directorate-general Joint Research Centre (JRC) and the USA’s National Oceanic and Atmospheric Administration (NOAA) shared their insights during the workshops.

A living resource for EO storytellers

The ideas, tips and tricks gathered in the workshops have been summarised in a EO Data Visualisation Good Practice guide. The document summarises the key points made in this series of webinars and provides examples of an effective use of storytelling with satellite data in a variety of contexts.

The guide starts with an overview of what makes a good environmental story for modern news media, with insights from those who work in traditional newspapers as well as those who tell stories through social media, and plenty of examples to inspire users who wish to tell more stories online.

The guide then explores what data users can look at to build good visualisations - how should users balance robust information with aesthetics? How do users choose the right colours? And how can they make it so engaging that someone will stop scrolling to check the visualisation out? The guide covers all these questions and even includes a 10-point checklist users can check when creating a visualisation.

A handful of examples

To help users understand what a good EO story looks like, the guide collects a wealth of examples of visualisations that users have used to tell stories on a range of environmental topics, from air quality to wildfires to sea ice visualisations.

By scrolling through the "Climate extremes: heatwaves, changes in ice and drought visualisations" collection of examples, users can see how scientists and EO enthusiasts have used different satellite products to raise awareness of climate change issues among online audiences. Examples include data visualisation strategies to tell stories about temperature anomalies, ocean heatwaves, sediment discharge from heavy flooding and more.

More inspiring examples can be found on the “Air quality and wildfires visualisations” page. One that particularly gained traction in recent years was the satellite visualisation of the lava flow and ash plume from the Cumbre Vieja volcano, back in 2021. Images from space not only amplified the spread of news on the event by providing powerful imagery to accompany the story, but equally helped local authorities manage the consequences of the eruption. In this way, EO-based stories can not only inform and inspire audiences, but also help us take better care of our communities.

At the end of the guide, users are invited to re-watch the webinars, which are published on EUMETSAT's YouTube channel and review the slides of the presentations made during the workshops, which are all organised by topic and easily accessible. And while the guide is already quite detailed, users should feel free to contribute if they have opinions to share, examples to add, or constructive criticism to offer. 

Telling powerful environmental and climate-related stories is critical in an era of misinformation and disinformation on subjects such as climate change, pollution and environmental health. The new EO Data Visualisation Good Practice guide serves not only as a practical resource for users, but also a concreate example of the importance of accurate and engaging communication in addressing global environmental challenges.

With the objective of supporting space entrepreneurship for a digitally sustainable Europe, the European Commission launched the Competitive Space Start-ups for Innovation Initiative (CASSINI) Hackathons in 2021.

These are competitions for students, graduates, researchers and early-stage teams/start-ups across Europe. Participants can unleash their creativity and build digital applications using EU space technology - including satellite imagery and positioning services - to respond to specific challenges. Taking place across ten European cities simultaneously, these hackathons provide the perfect environment to form dynamic teams, learn about space data access, understand customer needs and kick-start the development of innovative digital solutions.

Since the launch of the initiative, six editions of the hackathon have been held, each of them focusing on a different theme. In this week’s Observer, we'll take a trip down memory lane and look at those six editions and some of the ideas they generated.

1st edition: All about green spaces

Back in June 2021, participants were challenged to hack the future of our green spaces using European space technologies. As part of this challenge, teams could address one of three themes: “discover your city”, “stay fit and healthy”, and “protect rural areas”. One of the winning teams, TreeCount&Care, focused on using space data to empower citizens to take care of trees in their communities, tracking individual trees and their water needs to protect them from drought.

The team's model had several layers. First, the model detected trees using the DeepForest algorithm. Second, it assessed the current condition and life cycle of each tree using environmental data such as soil moisture and metrics such as the Normalised Difference Vegetation Index (NDVI), which helps to assess vegetation health. Finally, the collected data was integrated into the 'water me' platform, which informs communities about the water status of individual trees.

The team made most of their project available under open-source licences and sought to offer the service to communities on a pay-per-use basis. The project was implemented on the team's platform.

2nd edition: Icy solutions for an icy landscape

In November 2021, during the second edition, participants focused on the challenge of connecting the Arctic with European satellite technologies. The main challenges focused on safe passage at sea, life on land and wildlife management strategies.

The winning team focused on soil erosion in Iceland. The team took up the challenge to help protect the top soil layer in Iceland, which stores up to 80% of carbon. Due to climate change, this top layer is being eroded away and carbon can be released into the atmosphere. There are ways to prevent this erosion, but first we need to know where it is most likely to happen. So, the team developed a tool to map erosion risk remotely using satellite data. They combined satellite imagery with local weather and land data such as vegetation cover and average rainfall to calculate various vegetation and soil indices. By combining these indices with statistical analysis, the team was able to assess the risk of soil erosion in specific areas and help land owners better manage the erosion risk.

3rd edition: Time to hit the road - a focus on tourism

The third CASSINI Hackathon in May 2022 focused on preserving destinations across Europe and how we access them. Participants were challenged to work on ideas that support sustainable travel, improve experiences in local cities and cultures and promote thoughtful exploration of nature in Europe.

The winning project Mind the Path, built an application that would let users find and share unmapped hiking trails in rural areas. The team employed a combination of artificial intelligence (AI) and data from Copernicus satellites. The AI's neural network architecture, originally developed for medical applications, played a pivotal role in the mapping process. It could segment individual images in a specific way, identifying structures such as hidden paths and tracks. The algorithm was trained on a small amount of Copernicus data and was then able to find hidden pathways in a much larger dataset. These AI generated maps were then verified by hikers using smartphones. The resulting application identifies uncharted hiking trails, providing key information about climate conditions and the user's location. 

4th edition: Space for the financial world

The fourth CASSINI Hackathon took place in November of 2022 and challenged participants to imagine the future of finance, insurance and investments with the help of European space technologies. They were presented with the challenges of enabling green and sustainable investments, innovating financial tools and technologies or advancing global financial intelligence.

One of the winning teams, Cropernicus (and no, that’s not a typo) presented an innovative solution that uses satellite data to forecast crop production, providing stakeholders independent and real-time predictions of future yields in a user-friendly format. This application aimed at assisting farmers and the broader agricultural industry in making informed decisions related to finance, strategy, risk management, sustainable investments, and social impact.

5th edition: An eye on defence and security 

The fifth edition took place in early 2023, in March, and challenged participants to help secure and strengthen Europe's defence by developing viable solutions which improve the EU's defence and security capabilities.

The teams were presented with three challenges: enabling off-road mobility, making the seas safer and protecting the EU's critical infrastructure.

The first place winner was Hiris Guider, a team which demonstrated how Copernicus data can be used by defence forces, emergency response teams and humanitarian organisations. The team combined Copernicus data on multiple assets like land cover, vegetation, humidity, and forests with data on population density to create a platform for evaluating evacuation plans and scenarios, allowing users to locate high-risk areas and take mitigation measures in advance.

6th edition: International development and humanitarian aid

Last but not least, the 6th edition of the CASSINI Hackathons took place in early November 2023. The theme of this edition was "Space for International Development and Humanitarian Aid". Participants had to develop solutions to three overarching challenges: how space technologies could help support sustainable infrastructure development, improve food security and access to clean water, and understand and predict forced migration.

The winning team, Upstream, focused on improving aquaculture. In a warming world, parasites can thrive in aquaculture farms, threatening production. One way to combat this is through biosecurity planning, which is required by both the EU and local authorities. This is often done through marine spatial planning but can be challenging due to conflicting interests and the dynamic nature of the sea. Upstream used several data sets from Copernicus, such as ocean currents, ocean salinity and temperatures, to develop a tool to help with biosecurity planning for aquaculture sites. The solution can simulate the spread of harmful particles in aquaculture sites and identify parasite hotspots, helping aquaculture farmers to better understand where sites should and shouldn't be placed to avoid contamination.

Looking to the future, the winning team would like to offer this service through the NextOcean Store, an EU-funded project that aims to provide Earth Observation services for fisheries and aquaculture.

Over the last six editions, more than 1200 participants have participated in the CASSINI hackathons. By providing a competitive environment which allows for support from experts and ample opportunities for cross-pollination of ideas, the hackathon series showcases and enables innovative projects and fosters creativity. Furthermore, by supporting the overall winning projects to accelerate and become profitable, the CASSINI hackathons contribute to building an environment around European space services and making them accessible to everyone.