A Weakly Supervised and Self-Supervised Learning Approach for Semantic Segmentation of Land Cover in Satellite Images with National Forest Inventory Data

Moraes, Daniel; Campagnolo, Manuel L.; Caetano, Mário

http://hdl.handle.net/10362/179714

Utilize este identificador para referenciar este registo.

Nome:	Descrição:	Tamanho:	Formato:
Weakly_Supervised_Self_Supervised_LASS_Land_Cover_Sat_Images.pdf		7.53 MB	Adobe PDF	Ver/Abrir

Contacte-nos

Autores

Moraes, Daniel

Campagnolo, Manuel L.

Caetano, Mário

Resumo(s)

National Forest Inventories (NFIs) provide valuable land cover (LC) information but often lack spatial continuity and an adequate update frequency. Satellite-based remote sensing offers a viable alternative, employing machine learning to extract thematic data. State-of-the-art methods such as convolutional neural networks rely on fully pixel-level annotated images, which are difficult to obtain. Although reference LC datasets have been widely used to derive annotations, NFIs consist of point-based data, providing only sparse annotations. Weakly supervised and self-supervised learning approaches help address this issue by reducing dependence on fully annotated images and leveraging unlabeled data. However, their potential for large-scale LC mapping needs further investigation. This study explored the use of NFI data with deep learning and weakly supervised and self-supervised methods. Using Sentinel-2 images and the Portuguese NFI, which covers other LC types beyond forest, as sparse labels, we performed weakly supervised semantic segmentation with a convolutional neural network to create an updated and spatially continuous national LC map. Additionally, we investigated the potential of self-supervised learning by pretraining a masked autoencoder on 65,000 Sentinel-2 image chips and then fine-tuning the model with NFI-derived sparse labels. The weakly supervised baseline achieved a validation accuracy of 69.60%, surpassing Random Forest (67.90%). The self-supervised model achieved 71.29%, performing on par with the baseline using half the training data. The results demonstrated that integrating both learning approaches enabled successful countrywide LC mapping with limited training data.

Descrição

Moraes, D., Campagnolo, M. L., & Caetano, M. (2025). A Weakly Supervised and Self-Supervised Learning Approach for Semantic Segmentation of Land Cover in Satellite Images with National Forest Inventory Data. Remote Sensing, 17(4), 1-23. Article 711. https://doi.org/10.3390/rs17040711 --- This research was supported by national funds through the FCT (Fundação para a Ciência e a Tecnologia), under the project UIDB/04152/2020 (DOI: 10.54499/UIDB/04152/2020)—Centro de Investigação em Gestão de Informação (MagIC)/NOVA IMS and grant number PRT/BD/153517/2021.

Palavras-chave

land cover deep learning convolutional neural networks masked autoencoder national forest inventory sentinel-2 General Earth and Planetary Sciences SDG 13 - Climate Action SDG 15 - Life on Land