OpenPrioBio - Early prioritisation of areas for the biodiversity by fusing multimodal earth observation data with
open geodata and AI

As a result of climate change and the encroachment of humans into various ecosystems, biodiversity is increasingly under threat worldwide.

Improving field crop identification of western Kenya based on hyperspectral EnMAP data using Geo Engine

Smallholder agriculture makes a key contribution to the food supply of Southwest Africa. Environmental and climate change are increasingly threatening the agricultural yields and thus the livelihoods of smallholder farmers and the region's food security.

Remote sensing with deep learning for land surveying task in Lower Saxony

In a joint research and development project with the Institute of Photogrammetry and Geoinformation (IPI) of the Leibniz Universität Hannover and the State Office of Lower Saxony for Geoinformation and Surveying (LGLN), new AI remote sensing methods are developed since 2019-07-01.

Deep Learning for forest disturbance detection using Sentinel-2 time series

Forest disturbance is a viral topic in times of climate change, which leaves stressed trees vulnerable to calamities such as bark beetle infestations and drought damage.

Deep learning for the recognition of individual trees in aerial images

Deep learning methods are used to recognise individual trees in digital orthophotos with 20 cm ground resolution. The background is the generation of reference data for the classification of satellite data from the Copernicus mission in the KlimBa project.

Pre-Training Applicability in Earth Observation

The goal of the PreTrainAppEO project is to make the use of AI in the field of Earth observation and remote sensing more attractive and efficient. To this end, a methodology is being developed that uses the approach of pre-trained AI models to achieve generalisability to various standard applications in the remote sensing field.

Joint Project of Constructor University (Project Lead), TU Berlin and rasdaman GmbH

Added value from Big Earth Data by combining AI and federated data cubes

Data cubes offer a natural, analysis-oriented view of spatiotemporal data that also scales very well. AI, on the other hand, improves the understanding of EO data with new methods. Interestingly, both techniques are based on the same mathematical foundations, namely tensor algebra.