Earth Observation; Remote Sensing; Geospatial AI; Machine Learning; Forest Monitoring; Biodiversity; Data Harmonisation; Time Series; Sentinel; EnMAP; LiDAR; UAV; Digital Forestry; Decision Support; Copernicus
TOPIC 2 – Adaptive and Multifunctional Forest Management Systems
We contribute expertise in Earth observation, geospatial machine learning, biodiversity data integration, multi-source time-series harmonisation and digital decision-support systems. Our work focuses on transforming heterogeneous environmental data into consistent, analysis-ready information and practical tools for adaptive forest management.
A particular focus of our contribution is the harmonisation of multi-source Earth observation time series. We integrate data from different satellite missions, sensors, spatial resolutions, acquisition frequencies and processing levels into consistent data cubes and indicators. This includes temporal alignment, spatial harmonisation, cloud and quality filtering, sensor-specific preprocessing, gap handling and the generation of comparable indicators across long time periods.
Our relevant experience includes forest monitoring in the LOEWE project Natur 4.0, the integration of animal and plant observation data in the DFG project GFBio, work related to the GEO BON EBV Data Analyzer, an ESA BIC machine-learning pipeline for satellite-image time series, and hyperspectral classification using EnMAP data.
We can contribute to:
- harmonisation and temporal alignment of multi-source Earth observation time series;
- integration of Sentinel-1/-2, Landsat, EnMAP, UAV and field data;
- generation of consistent, analysis-ready data cubes and geospatial indicators;
- machine-learning and computer-vision workflows for forest structure, tree species, forest condition and disturbance detection;
- time-series analysis and change detection;
- biodiversity indicators and Essential Biodiversity Variable-related applications;
- integration of Earth observation with ecological observations and expert knowledge;
- reproducible geospatial data and machine-learning pipelines;
- web-based dashboards, exploration tools and digital decision-support demonstrators;
- user research, co-design, training, dissemination and exploitation.
We are particularly interested in partners who can provide forest-ecological and silvicultural expertise, field and biodiversity data, demonstration sites, operational forest-management use cases, validation activities, Living Labs and stakeholder networks.
We are open to joining an existing consortium or co-developing a new proposal. We could contribute to a work package on Earth observation, multi-source data harmonisation, geospatial AI, biodiversity indicators, validation or digital decision support.
We are a German Earth-observation and geospatial technology company developing scalable solutions for the analysis, harmonisation and visualisation of environmental datasets.
Our Geo Engine platform enables the processing, analysis and visualisation of raster, vector and time-series data in web-based environments. It supports the integration of satellite data, field observations, machine-learning workflows and domain-specific indicators.
A core part of our expertise is the harmonisation of heterogeneous Earth observation data sources over time. We combine data from different sensors and satellite missions, align spatial and temporal characteristics, apply quality controls and preprocessing, and generate consistent, analysis-ready data products for monitoring and decision support.
Our experience covers forest monitoring, biodiversity observation, environmental data integration and geospatial machine learning. Relevant examples include the LOEWE project Natur 4.0, the DFG project GFBio, work related to the GEO BON EBV Data Analyzer, an ESA BIC machine-learning pipeline for satellite-image time series and hyperspectral classification using EnMAP data.
We combine software engineering, Earth observation and applied data science to support researchers, public authorities, environmental organisations and other users in making evidence-based decisions.
We are interested in transferring advanced Earth-observation and geospatial analytics into practical, interoperable and user-oriented solutions for adaptive and multifunctional forest management.