SubscribeFind below SWIFTT’s news articles, press releases, digests of scientific papers, as well as other outreach materials.
Timbtrack provides field training in data collection with the SWIFTT mobile app to Rīgas Meži’s foresters
15 January 2025
This data collection process is not only important for testing the platform and the associated apps, and to train machine-learning models
SWIFTT project highlighted in video by the EU Agency for the Space Programme
08 January 2025
EUSPA supports the market development of the EU Space downstream sector and the uptake of space-based solutions through its Horizon Europe calls.
SWIFTT highlighted at the Da Vinci Dialogues
27 November 2024
Event co-organised by project partner Da Vinci Labs and La Fabrique du Futur was held on November 26th, in Paris, France.
SWIFTT partner presents work at the 27th International Conference on Discovery Science
17 October 2024
Research presented proposes a deep learning-based approach, named AVALON, that implements a CNN to detect tree dieback events in Sentinel-2 images of forest areas.
Publication: Semi-supervised European forest types mapping using high-fidelity satellite data
27 September 2024
In this work, SWIFTT partners from the Space Research Institute of Ukraine introduce an innovative semi-supervised approach for mapping European forest types by harnessing the power of high-resolution Sentinel-1 and Sentinel-2 satellite data from the Copernicus program.
Researchers explore novel approach to map forest dieback in satellite images
25 September 2024
Study published in the Journal of Intelligent Information Systems investigated the performance of a data-centric semantic segmentation approach to detect bark beetle infestation in satellite images. The results are part of the EU/EUSPA-funded project SWIFTT.
Publication: A Deep Semantic Segmentation Approach to Map Forest Tree Dieback in Sentinel-2 Data
16 September 2024
In this work, SWIFTT partners from the University of Bari Aldo Moro illustrate a deep learning approach that trains a U-Net model for the semantic segmentation of Sentinel-2 images of forest areas.
SWIFTT partners present work at ECMLPKDD 2024
13 September 2024
The flagship European machine learning and data mining conference was held in Vilnius, Lithuania, on September 9-13, 2024
Publication: A multimodal dataset for forest damage detection and machine learning
05 September 2024
In this work, SWIFTT partners from the Space Research Institute of Ukraine provide a useful and reliable dataset of Ukraine’s territory for scientists, conservationists, foresters and other stakeholders involved in monitoring forest damage and its consequences for forest ecosystems and their services.
