TreeSatAI – Artificial Intelligence with Earth Observation and Multi-Source Geodata

A drone ready to take off for field tests
TU Berlin / FG Geoinformation in der Umweltplanung

The goal of the TreeSatAI project is the development of artificial intelligence methods for the monitoring of forests and tree populations at local, regional and global level. The project is funded by the German Federal Ministry of Education and Research (BMBF). Using freely accessible geodata from different sources (remote sensing data, administrative information, social media, mobile apps, monitoring libraries, open image databases) prototypes for deep learning based extraction and classification of tree and stand features for four different use cases in the fields of forest, nature conservation and infrastructure monitoring are developed.

Remote sensing data from various satellite missions of ESA and NASA, aerial image data as well as geodata on the state of the environment are increasingly available free of charge and in large quantities. At the same time, texts, photos and videos from social media platforms such as Flickr, Twitter or Open Street Map provide access to further information about our environment. However, a manual evaluation of the resulting huge amounts of data would be too time-consuming and labor-intensive.

The Deep Learning Competence Center of DFKI and the research area Smart Data and Knowledge Services have been developing AI procedures for the analysis of aerial and satellite images for some time now, which enable both local evaluation and global analysis. In TreeSatAI, the scientists intend to use CNNs (Convolutional Neural Networks) as well as specialized LSTM models (Long Short-Term Memory) from the field of Deep Learning to enable the automated temporal analysis of forest areas over a large area and thus support environmental and forest experts. One of the major challenges is the acquisition of sufficient, high-quality training data to train the algorithms and the evaluation of the resulting models by experts from the forest and environmental sector. Therefore, the project will use and combine the different competences of the project partners to meet the numerous challenges of this ambitious project.

Partner:
• TU Berlin: Geoinformation in Environmental Planning (Consortium management)
• TU Berlin: Remote Sensing Image Analysis Group
• LiveEO GmbH
• LUP GmbH
• Vision Impulse GmbH

Runtime:
01.06.2020 – 31.05.2022

Funding reference: BMBF 01IS20014D

Press Contact:
Christian Heyer
Head of Corporate Communications DFKI Kaiserslautern
E-Mail: Christian.Heyer@dfki.de
Phone: +49 631 20575 1710

Wissenschaftliche Ansprechpartner:

Dr. Jörn Hees
Smart Data & Knowledge Services
Competence Center Deep Learning
E-Mail: Joern.Hees@dfki.de
Phone: +49 631 20575 1180

http://www.dfki.de

Media Contact

Udo Urban DFKI Kaiserslautern
Deutsches Forschungszentrum für Künstliche Intelligenz GmbH, DFKI

All latest news from the category: Information Technology

Here you can find a summary of innovations in the fields of information and data processing and up-to-date developments on IT equipment and hardware.

This area covers topics such as IT services, IT architectures, IT management and telecommunications.

Back to home

Comments (0)

Write a comment

Newest articles

Giant mantle plume reveals Mars is more active than previously thought

Orbital observations unveil the presence of an enormous mantle plume pushing the surface of Mars upward and driving intense volcanic and seismic activity. On Earth, shifting tectonic plates reshuffle the…

Space atomic clocks could help uncover the nature of dark matter

Studying an atomic clock on-board a spacecraft inside the orbit of Mercury and very near to the Sun might be the trick to uncovering the nature of dark matter, suggests…

Photon-efficient volumetric imaging with light-sheet scanning fluorescence microscopy

New method harnesses image scanning superresolution for enhanced photon efficiency in light-sheet microscopy. In biological imaging, researchers aim to achieve 3D, high-speed, and high-resolution, with low photobleaching and phototoxicity. The…

Partners & Sponsors