A Constrained Semi-Supervised Learning Algorithm for Deforestation Mapping
Proceedings of the AAAI Symposium Series · 06.11.2026 · 10 (1) · 687-694
DOI: 10.1609/aaaiss.v10i1.43476 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 06.11.2026. Verfasst von Ranga Raju Vatsavai und 1 weiteren Autor:innen.
Abstract (Originalsprache)
The United Nations reports that the world lost an average of 10 million hectares of forest annually between 2015 and 2020. Deforestation has widespread consequences, including increased greenhouse gas emissions, climate change, ecosystem disruption, reduced water quality, and loss of livelihoods. Remote sensing imagery provides excellent spatial and temporal coverage for monitoring deforestation. However, ground truth data is often sparse and expensive to acquire, hindering the training of effective machine learning models. In this work, we present a novel semi-supervised learning algorithm to address the challenge of limited ground truth data in deforestation studies. Experiments on a real-world remote sensing dataset demonstrate the efficacy of our proposed model.
Zitieren
APA
Vatsavai, R. R., & Shekhar, S. (2026). A Constrained Semi-Supervised Learning Algorithm for Deforestation Mapping. Proceedings of the AAAI Symposium Series, 10(1), 687-694. https://doi.org/10.1609/aaaiss.v10i1.43476
Vancouver
Vatsavai RR, Shekhar S. A Constrained Semi-Supervised Learning Algorithm for Deforestation Mapping. Proceedings of the AAAI Symposium Series. 2026;10(1):687-694. doi:10.1609/aaaiss.v10i1.43476
BibTeX
@article{Vatsavai2026,
author = {Vatsavai, Ranga Raju and Shekhar, Shashi},
title = {A Constrained Semi-Supervised Learning Algorithm for Deforestation Mapping},
journal = {Proceedings of the AAAI Symposium Series},
year = {2026},
volume = {10},
number = {1},
pages = {687--694},
doi = {10.1609/aaaiss.v10i1.43476}
}
EUVIMED