Reusing Pre-trained Semantic Segmentation Models to Map Bark Beetle Outbreaks in Sentinel-2 Images

Andresini, G., Appice, A., Ardimento, P., Boffoli, N., Carlucci, M., Recchia, V. (2026). Reusing Pre-trained Semantic Segmentation Models to Map Bark Beetle Outbreaks in Sentinel-2 Images. In Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2024. Communications in Computer and Information Science, vol 2560. DOI: 10.1007/978-3-032-25311-8_4

The use of supervised deep learning techniques to monitor the health of forests through the analysis of satellite data is rapidly increasing. However, the key challenge with supervised deep learning techniques is that they require big volumes of accurate, error-free annotations to boost accurate model development. Although, several Earth observation satellite datasets are today available free of charge, the fieldwork for collecting their accurate annotations is time-consuming and costly. On the other hand, the emerging Data-Centric Artificial Intelligence (DCAI) paradigm promises to mitigate this issue saving time and money, while gaining accuracy promoting the reuse of foundation semantic segmentation models to specific Earth observation problems. In particular, this study addresses the task of mapping bark beetle outbreaks causing forest tree dieback through the lens of the model reuse in the DCAI paradigm. To this aim, we explore the performance of fine-tuning as a learning strategy to reuse a pre-trained, sophisticated semantic segmentation model developed for land cover segmentation with a big amount of accurately annotated multi-temporal Sentinel-2 data. We assess the effectiveness of the model reuse approach in two case studies regarding forest scenes that were annotated with bark beetle outbreaks observed in October 2028 in the Northeast of France and September 2020 in the Czech Republic.