The Copernicus Data Space Ecosystem is pleased to announce its annual user community event. Mark your calendar for the CDSE User Summit 2026 taking place on Wednesday, 16 September 2026 during INTERGEO 2026 in Munich.
The CDSE User Summit is a hybrid event that brings together users, service providers, and Earth observation experts to explore the latest developments, discover innovative Earth observation data and services, exchange experiences with the community, and help shape the future of Earth observation.
Join us on-site in Munich or online for a day of inspiring presentations, user stories, live demonstrations, and networking. Participation is free for both in-person and online attendees. The preliminary programme and registration details will be published by mid-July. Visit https://dataspace.copernicus.eu/events/cdse-user-summit-intergeo-2026 for all latest updates.
What does mission-critical accuracy look like in practice?
Enabled Intelligence, an AI technology and services provider specialising in geospatial analysis, builds models for government and commercial clients across military intelligence, disaster recovery, transportation logistics and agricultural monitoring. Its quality bar is explicit: at least 95% accuracy on all training data, with certain ground truth datasets required to exceed 99%.
The technical constraints were as demanding as the accuracy targets. Datasets spanned synthetic aperture radar, electro-optical imagery, hyperspectral data and full motion video. Every project involved coordinate transitions: from geospatial coordinates for labeling, to pixel coordinates for model training, and back to geospatial coordinates at deployment.
After evaluating more than 35 labeling platforms and software packages, Enabled Intelligence selected Kili as the core of its annotation architecture. The team measures objects in real-world coordinates directly in the interface, stacks multiple image layers (synthetic aperture radar over electro-optical, for instance) and toggles between them during analysis, and runs quality control workflows tracking false positives, false negatives, misclassifications and label alignment.
The results: 95%+ accuracy across training data, 99%+ on ground truth datasets, and millions of labels produced across thousands of geospatial images for use cases ranging from aircraft detection to land use classification.
“We’ve assessed over 35 different platforms, labeling tools and software packages, and Kili has been by far the best platform that we have used for many of our types of data and certainly the best for geospatial,” says Peter Kant, CEO of Enabled Intelligence.
The lesson from programmes like this one is that geospatial data carries structure — spatial, geometric, radiometric — that generic image tooling ignores. Our recent releases follow that principle in four areas.
Geography as a way to organise the work, not just view it
A queue treats every asset the same way, in whatever order it happens to load. Geospatial datasets are not random: they have real spatial structure, and that structure is often exactly what should drive how work gets organised. Knowing that a cluster of assets sits over a flooded region, along a specific coastline, or across a city centre is the kind of context that should shape prioritisation and assignment, and it is precisely what a list view cannot surface.
Map View puts the dataset on an actual map. Teams see the geographic distribution at a glance and act on it directly, selecting, assigning or prioritising assets by where they are, with a built-in base map and reorderable layers underneath so the data reads correctly while they work.
Coordinates you can actually trust
Geospatial data is only useful if its coordinates hold up. Kili now preserves each image’s native coordinate reference system rather than forcing everything into a single projection, and teams can lock the CRS and resampling method at the project level so every asset is handled consistently. For imagery delivered with RPC metadata instead of full orthorectification, Kili supports an explicit affine transformation as a clearly flagged approximation, giving teams a usable path forward without quietly compromising on precision. The active coordinate system is always visible in the labeling interface.
Imagery rendered the way the data deserves
High bit-depth imagery (16-bit, Float32) carries far more dynamic range than standard 8-bit images. Kili now applies a percentile-based rescaling tuned for that range, so high bit-depth imagery renders with real contrast and detail, with no manual preprocessing required before import.
Confidence, visible right where labeling happens
Model predictions often come with a confidence score, but that signal is only useful if annotators can see it while they work. Kili now supports importing confidence scores and displaying them directly on geospatial objects in the labeling interface, giving teams a quick, built-in way to flag uncertain predictions for closer review.
Where this is heading
Across the EO ecosystem, the shift underway is from AI experiments to operational AI services, and it changes what dataset quality means. When a model informs a disaster response or a monitoring contract, training data becomes part of the supply chain: it needs provenance, consistent coordinate handling, and quality metrics that stand up to audit. The four capabilities above, like the workflows Enabled Intelligence built, exist to make that level of rigour the default rather than an achievement.
Kili Technology will keep developing along this line. EO organisations interested in the geospatial toolkit can find more detail on the geospatial annotation product page or get in touch with our team.
About Kili Technology
Kili Technology is the complete platform for building trustworthy, high-quality datasets for training, fine-tuning and evaluating AI/ML models, with dedicated support for geospatial imagery including SAR, electro-optical, hyperspectral and full motion video.
EUSI announced a major upgrade of its satellite ground segment and cloud infrastructure, further accelerating its industry-leading satellite tasking and intelligence delivery capabilities through the secure ATOM™ web and API platform. The platform, in combination with EUSI’s Rapid Satellite Intelligence (RSINT) program, enables satellite tasking up to 30 minutes before image acquisition and delivery of imagery within 15 minutes of collection. This reduces the end-to-end request-to-receive cycle from hours down to minutes, supporting time-critical operations including crisis response, border security, maritime awareness, and military intelligence across national and EU agencies.
The investment includes significant enhancements across EUSI’s German-based operations, covering mission software, cloud architecture, processing pipelines, delivery infrastructure, and ground segment capabilities. Located near Munich and operated in close partnership with the German Aerospace Center (DLR), EUSI’s infrastructure forms a critical component of Germany’s commercial Earth observation ecosystem and sovereign space capabilities.
EUSI operates the European uplink and downlink service for the Vantor satellite constellation, providing the continent a gateway for rapid satellite tasking and low-latency imagery delivery of 30 cm optical imagery. Together with high resolution SAR and RF satellite capabilities, they offer a multi-sensor approach to satellite-based intelligence through a secure, fully EU-operated environment that strengthens resilience and Space Act initiatives.
“The intelligence community increasingly requires data at the speed of operations and procurement that integrates directly into their workflows,” said Pascal Schichor, VP of Sales at European Space Imaging. “These upgrades to our ground infrastructure represent a significant investment in European operational capabilities and our direct support of German and broader EU security and space objectives.”
The operational value of EUSI’s ATOM platform and RSINT service level is already being demonstrated through its integration by GAF Geospatial GmbH (GAF) into the Copernicus Rapid Response Desk (RRD), supporting hundreds of tasking and data delivery activities for emergency management and security missions across Europe.
“The integration of EUSI's ATOM API into the Copernicus Rapid Response Desk enables comprehensive catalogue search, fast automated direct tasking ordering and order monitoring till data delivery in a single access point, significantly accelerating access to commercial Earth observation data for time-critical emergency response operations.”
-GAF
As European governments continue investing in resilient and sovereign space capabilities, EUSI's upgraded operational infrastructure provides a secure European gateway to commercial satellite intelligence. By combining direct satellite tasking, rapid data delivery, and multi-sensor integration through a single operational partner, EUSI continues to support the evolving requirements of defence, civil security, and emergency response organisations across Germany and Europe.
France – As climate change accelerates and pressure on natural ecosystems intensifies, governments face a growing challenge: how can they protect biodiversity when the natural world is changing faster than they can measure it?
A major biodiversity mapping programme in southern France is combining satellite technology, ecological expertise and frugal AI to help territories adapt to climate change and biodiversity loss. A dynamic map that could change our resilience on a global scale in the coming years.
A new biodiversity mapping programme in the Occitanie Region of southern France aims to demonstrate that an innovative approach is possible.
Over the next three years, the Region will combine satellite Earth Observation, ecological field expertise and a frugal artificial intelligence approach to create a unique dynamic map of its natural habitats and better understand how they are evolving under the combined effects of climate change, urbanisation and human activity.
Covering nearly 72,000 km², the equivalent of 10 million football pitches, the project will map forests, grasslands, wetlands, agricultural landscapes, coastal ecosystems and urban green spaces across one of Europe’s most ecologically diverse territories, at a resolution and exhaustivness that’s never been seen before. The resulting habitat map will provide decision-makers with an incomparable and regularly updated view of ecosystem change, helping guide biodiversity conservation, climate adaptation and land-use planning strategies.
The programme is being delivered by a consortium led by CLS, a subsidiary of the French Space Agency (CNES) and a global specialist in Earth Observation solutions, together with ecological engineering experts BIOTOPE, ECO-MED, ENVOLIS and NATURALIA.
From Satellite Data, through AI, to Nature Intelligence
Monitoring biodiversity on a regional scale has traditionally relied on field surveys that are essential but difficult to repeat regularly across large territories.
The French programme combines multiple sources of information to create a more comprehensive understanding of nature.
Satellite imagery from the European Space Agency’s (ESA) Sentinel satellite missions and very high-resolution Earth Observation systems will be combined with climate, topographic, geological and environmental datasets.
Artificial intelligence models will then analyse these data to identify and classify hundreds of different habitat types across the region.
Rather than replacing ecological expertise, the technology is designed to extend its reach.
Over a six-month period, nearly 30 botanists will conduct approximately 700 field days across the territory, collecting the ecological reference data required to train, validate and continuously improve the models.
The result is a new form of environmental intelligence that combines the scale of satellite observation with the precision of field ecology.
A Different Approach to AI
As concern grows over the environmental footprint of artificial intelligence, the project also reflects a growing movement towards more responsible and efficient AI systems.
Instead of relying on large, general-purpose models requiring extensive computational resources, CLS, a mission driven company (equivalent B-Corp company), has adopted a frugal AI approach specifically designed for environmental monitoring applications.
The objective is simple: use only the computing power necessary to generate robust scientific results.
By combining targeted machine learning techniques with satellite data and ecological expertise, the project aims to maximise environmental insight while minimising computational impact.
This approach is consistent with a broader principle underpinning the programme: technologies designed to support environmental sustainability should themselves be developed responsibly.
Scaling Ecological Expertise
For Karim Mehah, Head of Service & Delivery, Environment & Climate Unit at CLS, the project demonstrates how innovation can support environmental stewardship when applied thoughtfully.
Karim Mehah, Head of Service & Delivery, Environment & Climate, CLS:
“Artificial intelligence is often discussed in terms of its environmental footprint. We believe the conversation should also focus on how AI is designed and what purpose it serves. In this project, we are using a frugal AI approach to help understand and protect biodiversity on a regional scale. By combining satellite observation, ecological expertise and targeted machine learning, we can generate valuable environmental intelligence while remaining consistent with the sustainability objectives we are trying to support.”
Carole Delga, President of the Occitanie / Pyrénées-Méditerranée Region:
“Protecting biodiversity means investing in the future of our region and of future generations. With this unprecedented mapping initiative, the Region is equipping itself with a strategic tool to anticipate the impacts of climate change, better manage land artificialisation, and support more sustainable and responsible territorial development.
This is a strong commitment to preserving our natural heritage and improving the well-being of our communities. CLS embodies the excellence of the regional space industry, firmly rooted in Occitanie and recognized internationally. I am proud that the Occitanie Region can draw on their expertise to support this ambitious and transformative project for our territory.”
As biodiversity loss and climate change continue to reshape landscapes around the world, the ability to observe nature from space, validate it on the ground and transform it into actionable intelligence may become an increasingly important tool for governments and territories seeking to protect natural ecosystems.
The Occitanie programme offers a practical example of how technology, when combined with scientific expertise and designed responsibly, can help turn data into action for nature.
CLS is a global company, mission-driven, and pioneer provider of monitoring and surveillance solutions for the Earth, created in 1986. We are subsidiary of the French Space Agency1 (CNES) and CNP2, an investment firm. Our mission is to create innovative space-based solutions to understand and protect our planet and to manage its resources sustainably.
CLS employs, now, 1,200 people at our headquarters in Toulouse (France) and in 40 other sites around the world.
The company works in five strategic markets:
sustainable fisheries management,
environmental monitoring,
maritime surveillance,
mobility,
and energies & infrastructures.
CLS processes data from almost 200,000 beacons per month (such as drifting buoys, animal tags, VMS beacons, & LRIT tracking) and observes the oceans and inland waters (every day more than 20 instruments onboard satellites deliver information to CLS on the world’s seas and oceans). In addition, we monitor land and sea activities by satellite (nearly 20,000 radar and optical images and several hundred drone flights are processed each year).
Committed to a sustainable planet, every day the company works for Earth, from Space.
The French Space Agency (Centre National d’Études Spatiales) is the government agency responsible for shaping and implementing French space policy in Europe. It designs and puts satellites into orbit and invents the space systems of tomorrow; it promotes the emergence of new services useful in everyday life. Founded in 1961, CNES has developed major space projects, launchers, and satellites and is the industry’s natural partner for promoting innovation. The agency has nearly 2,500 employees passionate about space and its infinite, innovative fields of application. They work in five areas: the Ariane project, science, observation, telecommunications, and defense. CNES is a major player in technological innovation, economic development, and France’s industrial policy. It also forges scientific partnerships and is involved in many international cooperative endeavors. France, represented by CNES, is one of the main contributors to the European Space Agency (ESA). www.cnes.fr
²About CNP
CNP is a private investment company founded by Albert Frère and a preeminent player on the European investment market. Backed by a stable family shareholder base, CNP manages a net asset value of €3bn, focusing on long-term value creation by actively supporting the management teams of the companies in which it holds majority or leading stakes. From the start, CNP has sought to foster entrepreneurship: with permanent capital at its disposal, CNP comes in as a trusted partner to both founders and managers, and tailors its commitment with their ambition in mind. www.cnp.be
More about the Occitanie / Pyrénées-Méditerranée Region
The Occitanie / Pyrénées-Méditerranée Region is a regional authority committed to serving its residents and supporting local stakeholders. Through its responsibilities in regional planning, economic development, ecological transition, transportation, education, and vocational training, it designs and implements ambitious public policies tailored to today’s challenges.
Actively engaged in environmental transition and biodiversity conservation, the Region supports local initiatives, fosters innovation, and promotes scientific and institutional collaboration to advance sustainable and responsible development.
Biotope is an environmental consultancy specializing in ecology and biodiversity. For more than 33 years, in France and around the world, Biotope has supported businesses and public authorities through environmental impact assessments, nature conservation and management initiatives, and ecosystem restoration projects.
Biotope also advises companies on identifying biodiversity-related opportunities within their operations and integrating environmental considerations into their corporate strategies. In addition, the company provides professional training programs focused on environmental and biodiversity issues.
ECO-MED Ecologie & Médiation is an ecological consultancy founded in 2003 by its Managing Director, Julien Viglione. The company helps regional development stakeholders navigate regulatory frameworks designed to protect biodiversity and enhance natural environments.
While the company originated in Southern France, ECO-MED’s team of field ecologists now brings its expertise across the Mediterranean region, including Occitanie, Auvergne-Rhône-Alpes, and Bourgogne-Franche-Comté, as well as internationally.
ENVOLIS is a consultancy composed of scientists and environmental experts who provide environmental assessments and advisory services in the fields of water, soil, and biodiversity.
Working with a wide range of clients, whether driven by regulatory requirements or a genuine commitment to environmental stewardship, ENVOLIS supports projects throughout their entire lifecycle—from design and implementation to operation. The company currently operates across western and southern France through its regional offices.
Naturalia Environnement is an ecological consulting and engineering company. Founded in 1998, it has become a recognized leader in biodiversity expertise and environmental regulatory studies.
Its multidisciplinary team, composed primarily of ecologists and naturalists, develops practical solutions to protect, restore, and sustainably manage ecosystems.
color33 is an automated, cloud-based, online processing service that converts multispectral Earth observation images into actionable categories without requiring any training samples.
Unlike unsupervised clustering routines or machine learning approaches, color33 is based on a physical-model, producing a known set of spectral categories with known semantic associations. The service is parameter-free, fully-automated and application-independent.
Semantic enrichment of EO-data as a cloud service:
On-demand semantic enrichment
Fully automated
Scalable
Globally deployable
Output for workflows (e.g. change detection, water monitoring,…)
Semantic enrichment of Sentinel-2 images
Examples:
Construction activities/ soil sealing
The automatic identification of construction activities is based on the semantic analysis of dense time series of Sentinel-2 satellite data. Spectral changes – such as the transition from vegetation or bare soil to sealed surfaces – are continuously captured mathematically and directly translated into semantic categories (e.g., “construction site,” “new building”). This layer enables the precise, fully automated, and large-scale monitoring of soil sealing, infrastructure projects, and urban growth dynamics over time.
Vizualisation of construction activities based on semantic categorization over time (Sentinel-2 images)
Vegetation change
Identify patterns and trends hidden within your Sentinel-2 imagery with color33’s automated workflows. Color33 enables users to select pixels that look like vegetation based on their spectral category before calculating vegetation indices, such as NDVI, removing or minimizing the need for thresholding to extract meaningful information about vegetation.
Search for patterns to detect vegetation loss
Observation over several months or years
e.g. landslides, forest damage, deforestation, forest fire impact
Multitemporal analysis of landslide event using color33 vegetation and bare soil categories through time (Sentinel-2 images)
Here is an illustration of what Terranis and the project team developed in the Occitanie, French Region. Occitanie region is a patchwork of varying climate conditions. The region faces significant climate change challenges, including rising temperatures, changing precipitation patterns, and heightened risk of droughts and heatwaves, particularly near the Mediterranean.
For the Occitania region, the VALORADA project focused on two specific territorial entities, Sicoval (southeastern suburbs of Toulouse) and Montpellier. For these entities, VALORADA focused on two main climate hazards and risks the region is facing:
Agricultural water needs, to integrate local data and model future scenarios.
Population vulnerability to heat waves, through specific indicators, to support city authorities in dealing with challenges related to urban heat island effect.
A list of indicators have been settled, together with local stakeholders, to characterize and quantify the interaction between territorial, environmental and socio-economic factors and changing climatic conditions. These indicators form the backbone of the regional analysis, providing the basis for evidence-based adaptation strategies.
To complement the local data, climate projections were obtained from the Copernicus Climate Data Store to ensure a consistent, scientifically robust basis for understanding current and future climatic trends. The resulting VALORADA dashboards for Sicoval and Montpellier provide a comprehensive user-friendly overview of the region' s climate and vulnerability indicators. It combines two main types of information: climate indicators and tailor-made ones, co-designed with the regional administrations to address local adaptation priorities and data needs. These relate to agricultural areas, irrigation rate, potential crops, water needs, urban vegetation and well-being, population vulnerability to heat waves, and many more.
The VALORADA dashboards integrate data from multiple sources, including various national and local datasets, Earth Observation and land cover data from the Copernicus services, and historical and projected climate data from the Copernicus Climate Data Store operated by ECMWF which provides the consistent climate baseline and future scenarios.
Such developed dashboards support their efforts to identify emerging risks, to prioritize adaptation measures and to monitor progress in reducing vulnerability over time. Most importantly, it transforms scientific and statistical information into actionable insights, helping decision-makers to strengthen resilience and adaptation policies and actions.
Developed by TerraNIS, the Pixagri Irrigation service is a decision-support tool designed to maximise crop potential by enabling users to carry out their irrigation cycles at the right time, should there be a risk of water stress on their plots. It is aimed at players in the agricultural supply chain (agricultural co-operatives and agricultural suppliers), seed companies and agri-food businesses. All of these stakeholders have a common interest in monitoring water stress on their plots, given the increase in drought events and the growing number of water restrictions.
The tool is based on a water balance model and integrates field data (plot boundaries and available soil analyses), combined with meteorological data and satellite data (Sentinel-2 to date, with Trishna or LSTM data to be used in the future). Available via a web interface and mobile app, its aim is to provide irrigation recommendations in millimetres in the event of a risk of water stress – estimated on a daily basis – on agricultural plots.
An evolution of the service, integrated into the Pixagri Irrigation commercial offering and utilizing thermal infrared data, is being developed as part of the CNES’s ‘Ambition aval’ programme (2025–2026). Data from Trishna will provide a crop evapotranspiration value derived from observational data, enabling better calibration and adjustment of the model’s outputs. The ultimate aim is to move towards targeted irrigation.
CloudFerro, a Polish sovereign cloud provider, has presented Bastion, a sovereign cloud architecture developed for defence, civil security organisations and operators of critical infrastructure.
Rather than being a standalone product, Bastion represents an operational cloud architecture designed for organisations that require full control over sensitive workloads, secure processing environments and resilient deployment models.
The solution combines cloud computing, AI capabilities and Earth Observation data processing within infrastructures operating under European jurisdiction. It can be deployed in different operational scenarios, ranging from permanent installations to isolated environments supporting mission-critical operations.
Earth Observation data increasingly plays a central role in civil protection, crisis response and security applications. Satellite imagery, together with AI-assisted analytics, enables faster situational awareness, infrastructure monitoring and decision support during emergencies.
Bastion builds on CloudFerro’s long-standing experience in delivering cloud infrastructure for European Earth Observation programmes and demonstrates how technologies originally developed for the EO sector can also support emerging dual-use applications while maintaining interoperability with broader European digital ecosystems.
The initiative reflects the growing importance of sovereign digital infrastructure as part of Europe’s resilience strategy, where secure cloud environments become an integral element of operational services based on satellite data.
CloudFerro, a Polish sovereign cloud provider, has launched a new public cloud region in Łódź, Poland, further expanding its European cloud infrastructure dedicated to Earth Observation, AI and data-intensive workloads.
The new region has been designed to support organisations processing large volumes of satellite and geospatial data while ensuring that critical workloads remain under European jurisdiction. Together with CloudFerro's existing cloud regions, the new deployment increases infrastructure resilience, enables multi-region architectures and provides additional capacity for operational EO services.
The region is AI-ready and prepared for next-generation GPU workloads, making it suitable for machine learning, large-scale geospatial analytics and advanced processing pipelines.
For the Earth Observation community, growing cloud capacity is becoming increasingly important as Copernicus data volumes continue to expand and AI becomes a standard component of EO workflows. Reliable cloud infrastructure is no longer only about storage and compute resources – it is becoming an essential part of the digital value chain supporting operational EO services.
CloudFerro currently supports a number of major European EO initiatives and platforms, including Copernicus Data Space Ecosystem, Destination Earth Data Lake, and CODE-DE, providing cloud infrastructure and services for institutional, scientific and commercial users across Europe.
The new region represents another step in strengthening Europe's sovereign digital infrastructure supporting the growing Earth Observation ecosystem.
At sea, operational decisions are made while ocean conditions are constantly changing. Vessel operators, route planners, offshore teams, maritime software providers and performance analysts all work with conditions that are never completely fixed or easily predictable: wind fields evolve, wave systems interact, coupled currents shift and local effects can alter the picture significantly.
For example, a voyage plan may look efficient before departure, but its operational value depends on the quality of the metocean layer behind it. A post-voyage performance report may show a deviation in speed, fuel use or emissions, but interpreting that deviation requires a reliable understanding of the sea-state conditions the vessel actually encountered. Bottom line, for maritime operations marine weather is not just background information. It is an integral part of the outcome on which human decisions depend.
The maritime sector is not short of data sources. Forecasts, ensembles, hindcasts, reanalysis products, satellite observations, vessel reports, in-situ measurements and operational data streams are all increasingly available. The harder question is whether this information is accurate and relevant enough, aggregated and harmonized, operations-ready and explainable for each specific workflow in which it is needed and eventually used.
That is why the discussion is moving from raw and scattered metocean data feeds towards marine-weather intelligence. The difference matters. A data layer may estimate waves, wind and currents at a given timeframe and spatiotemporal resolution. Intelligence can go further: it can be traceable, explainable, defensible, context-specific and ultimately useful for critical decisions at sea that directly impact safety, risk, efficiency and profitability.
Even modest bias in the estimation of critical metocean variables affects interpretation when the information is integrated to outcomes such as a vessel route, a narrow operational window or a performance review. A general metocean map and a maritime decision workflow do not have the same requirements. The closer marine-weather data gets to an operational or commercial decision, the more important it becomes to understand its limitations, provenance and fitness for purpose.
Earth Observation has an important role in this shift. Satellite missions provide increasingly independent, repeated and scalable observations of the ocean and atmosphere. These observations can complement numerical marine-weather prediction, ensembles and reanalysis datasets, in-situ measurements and operational metocean products, especially in regions where direct observations are limited or unevenly distributed.
Considering, however, the vast areas of the global oceans, Earth Observation is not a standalone answer to marine-weather forecasting or the reconstruction of past conditions. Added value can actually come from combining space-based observations with oceanographic expertise, physical understanding, operational datasets and AI-enabled processing. The ocean-atmosphere system is complex. Waves, wind, currents, bathymetry, coastlines, location and vessel-specific operating conditions interact in ways that require a combination of quality data, physics-aware AI models/services and interdisciplinary domain knowledge. For maritime users, the value lies not in the source alone, but in how well the resulting information supports a practical decision.
AlongRoute Data, a Greek deep-tech company, works at this intersection. The company develops EO-enabled marine-weather intelligence for maritime operations, combining Earth Observation, operational metocean datasets, well-trained physics-aware AI technology, observation-informed reconstruction of past conditions and proprietary predictive models. Its focus is to turn complex metocean information into a clearer marine-weather layer for maritime workflows.
This approach is particularly relevant for waves, wind and currents, which directly affect vessel performance, safety margins, arrival-time reliability, emissions interpretation and offshore planning. AlongRoute Data treats these parameters not as informative map layers, but as dynamic conditions that need to be reconstructed, forecast, packaged and tested in relation to the decisions they support.
The term “physics-aware AI” is not used here as just a label. In oceanographic and marine-weather applications, AI cannot be detached from physical laws. Models need to respect the behaviour of the ocean-atmosphere system, the interaction and coupling of ocean processes, the energy balance, the structure of existing metocean datasets and the meaning of the outputs for maritime users. AI can support bias correction, data fusion, pattern recognition and meaningful assimilation, as well as forecast refinement, but only when trained with suitable datasets, fed with appropriate inputs, guided by domain expertise and assessed against relevant baselines.
What makes AlongRoute Data different is that it does not start with the forecast model, as many typical providers do. It starts with the sea-state evidence layer that the forecast builds on and depends on. If the training data or the initial forecast state carries persistent bias, the final marine-weather output will inherit part of that weakness. The proprietary technology therefore reconstructs past sea-state conditions before building forecasting and decision-support logic on top of them. It combines established metocean products, EO observations, buoy data, vessel reports and other publicly available oceanographic sources to describe the variables that matter most at sea. A key part of the system is the ability to use indirect observations that are often underexploited. Ship reports, vessel behaviour, profile measurements and navigation signals can all contain information about sea-state effects. AlongRoute Data uses AI-enabled translation services to turn these signals into usable marine-weather context, while respecting the physical role and limitations of each source.
The next step is AI-enabled assimilation. The company compares baseline metocean fields with direct observations and translated signals to identify bias, correct persistent errors and fill sparse-observation gaps in a physically consistent way. The result is a reconstructed sea-state layer that can support historical analysis, near-real-time initialisation and physics-aware training and forecasting.
This is not simply a repackaging of existing metocean feeds. It is an observation-informed marine-weather intelligence layer designed to be tested against current baselines, integrated through APIs and used inside maritime workflows where these conditions directly affect operational interpretation. The same marine-weather intelligence context can support several maritime workflows. In routing, it can help users assess the sea-state conditions affecting a voyage and better understand route confidence. In post-voyage analysis, it can support reconstruction of the wind, wave and current conditions experienced along a route segment or during a specific event in space and time. In performance and emissions workflows, it can help separate environmental forcing from vessel behaviour or operational choices. For offshore and coastal activities, it can contribute to marine-weather-window assessment and planning. For maritime software companies, it can add a specialised marine-weather capability without forcing end users to change platform.
This is also a wider opportunity for the European EO sector. Downstream EO services are increasingly judged not only by technical capability, but by operational relevance, integration potential and sector-specific value. Maritime is a demanding but important market for this transition. It is global, data-intensive and under pressure to improve efficiency, transparency, explainability and downstream performance. Yet many digital maritime decisions still depend on metocean layers that were not always designed for highly specific operational workflows.
AlongRoute Data’s recognition as winner of the EXPANDEO Start-Up Award 2026 reflects this direction. The award is a valuable milestone within the European Earth Observation community, but its importance is not only symbolic. It points to the role of downstream EO companies that can connect space-based data with real industrial needs and translate observation capacity into usable intelligence.
Moreover, for AlongRoute Data, EXPANDEO and the EARSC ecosystem provide an important bridge between EO innovation and maritime adoption. They bring visibility, but also context: the need for European space capabilities to reach operational users, commercial platforms and global blue-economy markets in forms that are practical, tested and understandable.
The next generation of maritime digital operations will not be shaped by data volume alone. It will depend on whether environmental information can be assessed, explained and integrated into the workflows that industry professionals already use. EO has a central role to play in that future, not as a single solution, but as a powerful foundation for better commercial understanding and performance.
