Discover the projects we have completed in cooperation with our partners. Let’s start a new collaboration together.
AURORA develops and validates AI-based super-resolution algorithms trained on real-world hyperspectral datasets.
The project integrates data from PRISMA, EnMAP, and airborne campaigns to improve the spatial resolution of hyperspectral images, bridging the gap between research missions and operational applications.
By increasing the level of spatial detail while preserving spectral fidelity, AURORA demonstrates how enhanced hyperspectral imagery can support a wide range of use cases — from agriculture and soil mapping to urban environment and land management.
Financed:
Partners:
AgriCEM focuses on developing advanced methods for monitoring sugar beet health and stress in preparation for the upcoming Copernicus Hyperspectral Imaging Mission for the Environment (CHIME) and Copernicus Land Surface Temperature Monitoring mission (LSTM).
The project generates and analyzes synthetic hyperspectral and thermal datasets that replicate the spectral and spatial characteristics of these future missions. These simulated data are used to train and validate retrieval algorithms for key sugar beet parameters such as leaf chlorophyll content, water stress, transpiration, and photosynthetic activity.
By integrating simulated CHIME and LSTM data with in-situ and field spectroscopy measurements, AgriCEM demonstrates how next-generation satellites will enable early detection of stress factors.
Financed:
Partners:
HyLAP explores how hyperspectral data from the German EnMAP satellite can be used to monitor forage quality and crop condition in real agricultural environments.
The project demonstrates how spaceborne hyperspectral observations can provide detailed information on plant biochemical composition,which are crucial for assessing forage quality and crop productivity. QZ Solutions was responsible for providing in-situ reference data, as well as for the ordering, coordination, and management of EnMAP satellite acquisitions over the agricultural test sites.
Financed:
Partners:
HYPER-AMPLIFAI brings together state-of-the-art AI foundation models and high-resolution hyperspectral imagery to unlock new insights into forests and soils. Over three years, a joint team from DLR, GFZ and precision-agriculture partner QZ Solutions will harness self-supervised learning methods to estimate forest biomass and predict soil nutrient content — empowering smarter environmental monitoring and sustainable land management.
Financed:
Partners:
SoilEO is a cutting-edge system for the analysis of spaceborne hyperspectral images to estimate key soil macronutrients — phosphorus (P), potassium (K), and magnesium (Mg) — as well as soil pH.
The system enables non-invasive, large-scale soil diagnostics that complement or even replace traditional laboratory sampling.
SoilEO has already been implemented in several European countries, including Poland, Romania, France, and Germany, proving its operational maturity and reliability.
Financed:
Partners:
The GENESIS project aims to revolutionize soil monitoring by leveraging machine learning and hyperspectral imaging from space. Using data from Intuition-1, a 6U satellite equipped with a state-of-the-art hyperspectral instrument, the project explores how onboard AI can enhance the mapping of key soil parameters directly in orbit.
Key achievements and innovations:
Supported by ESA Φ-lab.
Financed:
Partners:
