Subscribe
11 April 2025
Earlier this month, SWIFTT partner Annalisa Appice from the University of Bari presented the paper entitled “GANDALF: A LLM-based approach to map bark beetle outbreaks in semantic stories of Sentinel-2 images” in the 40th ACM/SIGAPP Symposium On Applied Computing (ACM-SAC 2025) held in Catania, on March 31- April 4, 2025.
Authored by Vincenzo Pasquadibisceglie, Vito Recchia, Annalisa Appice, Donato Malerba and Giuseppe Fiameni, the paper describes an approach that leverages the potential of LLMs for mapping bark beetle outbreaks in Sentinel-2 images of forest areas. The approach takes advantage of the rich context of textual data to transform Sentinel-2 images in smart data ready for boosting accurate semantic segmentation modeling. The effectiveness of the proposed approach in a case study regarding bark beetle outbreaks in benchmark Sentinel-2 images of forest scenes in Czech Republic.
The Symposium on Applied Computing (SAC) is a prestigious international forum for computer scientists, engineers, and practitioners to present their research findings across various domains of applied computing.
