Kuva Space, a Finnish space-technology company developing hyperspectral Earth-observation satellites and AI-powered intelligence solutions, has completed a pilot under the Copernicus Contributing Missions program showing that adding hyperspectral satellite data to existing Sentinel-2 imagery improves land-cover classification. Hyperfield is the only hyperspectral data provider with operational hyperspectral satellites selected for the program.
The study combined imagery from Kuva Space’s Hyperfield-1 satellites with Sentinel-2 data and an AI-based classification model. In a targeted validation against land cover manually mapped from up-to-date Very High Resolution imagery in three areas, the combined model achieved nearly 70% overall accuracy, compared with about 68% for either source on its own (68.1% for Hyperfield-1, 68.0% for Sentinel-2) and 66.7% for ESA WorldCover-v200 over the same areas.
The combined model outperformed both single-source models, showing that hyperspectral and multispectral data capture complementary information, with each picking up details the other misses.
What the Pilot Showed
- Tested at scale. Hyperfield-1 collected 98 hyperspectral images covering roughly 90,000 km2 across five test areas in Greece, Romania, France, the UK and Russia between June 2025 and May 2026
- Reliable data quality. Both Hyperfield-1 satellites met the study’s major data-quality targets for radiometric accuracy, temporal stability and geolocation. Checked against RadCalNet, a global network of calibration sites, mean surface-reflectance error was 2.4% for HF-1A and 3.0% for HF-1B, well within the target of below 10%
- Ready to work alongside Copernicus. When one input contained cloud, the combined model learned to rely more heavily on the clearer source, preserving the quality and temporal coverage of the land-cover prediction, so cloud over one source does not leave a gap in that day’s mapping
- Fast to deliver. Kuva Space’s automated AI-based processing pipeline can produce analytics outputs in under 10 minutes once data reaches the ground station
Seeing More from Existing Satellite Infrastructure
Conventional multispectral satellites observe the Earth using a relatively small number of broad wavelength bands. Kuva Space’s Hyperfield satellites instead capture reflected light across dozens of narrow spectral bands, allowing AI models to detect subtle differences between vegetation, soil and other materials that can look alike in conventional imagery.
This matters most for organizations already using Copernicus data. Because the two sources work best together, organizations can add hyperspectral data to established Earth-observation workflows to identify land-cover types more accurately across large areas.
“We already have the satellite imagery. The challenge is getting enough information from it to see what’s actually changing on the ground,” said Jarkko Antila, CEO of Kuva Space. “This pilot shows that hyperspectral data can make the Earth-observation systems governments rely on more precise, helping them distinguish smaller and subtler differences across very large areas.”
“This pilot confirms multimodality improves land cover mapping. With 70+ Hyperfield satellites in orbit by the end of the decade, we will improve not only accuracy but also temporal coverage of land cover mapping and land cover changes globally,” said Tuomas Tikka, Chief Strategy Officer at Kuva Space. “A robust in-house AI model automates various sensor data and analytics processing, continuously updating land-cover changes for global end users.”
Why More Precise Land Monitoring Matters Now
The results come as demand for more detailed, timely land information increases across Europe. EU Member States were due to submit their first draft national restoration plans under the Nature Restoration Regulation by 1 September 2026, setting out how they intend to meet restoration targets through 2030 and beyond.
The regulation requires restoration measures to cover at least 20% of EU land and sea areas by 2030, creating a growing need to understand where ecosystems are changing and whether restoration measures are delivering results.
The Copernicus Land Monitoring Service already uses land-cover information extensively to track changes in vegetation, agriculture, forests, urban areas, and other terrestrial environments. More accurate classification could improve how governments, researchers and companies monitor agricultural land, biodiversity, urban expansion and climate-related land-use change.
From Pilot to Operational Land Monitoring
The pilot also demonstrated consistency between Kuva Space’s HF-1A and HF-1B satellites, an important requirement for scaling monitoring from individual acquisitions to a constellation-based service.
Kuva Space is building its next six Hyperfield satellites, and plans to expand the Hyperfield constellation to provide subdaily global coverage by the end of 2030. Its next-generation Hyperfield-2 satellites will add Short-Wave Infrared sensing and higher-resolution RGB imagery, designed to better separate land-cover types, such as snow, built-up areas, bare soils and shrubs, that current systems still struggle to distinguish.