Spatially Explicit Active Learning for Crop-Type Mapping from Satellite Image Time Series
Sensors · 26.03.2024 · 24 (7) · 2108
DOI: 10.3390/s24072108 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 26.03.2024. Verfasst von Beatrice Kaijage und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Geo-Information Science and Earth Observation, University of Twente, 7522 NH Enschede, The Netherlands. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The availability of a sufficient number of annotated samples is one of the main challenges of the supervised methods used to classify crop types from remote sensing images. Creating these samples is time-consuming and costly. Active Learning (AL) offers a solution by streamlining sample annotation, resulting in more efficient training with less effort. Unfortunately, most of the developed AL methods overlook spatial information inherent in remote sensing images. We propose a novel spatially explicit AL that uses the semi-variogram to identify and discard redundant, spatially adjacent samples. It was evaluated using Random Forest (RF) and Sentinel-2 Satellite Image Time Series in two study areas from the Netherlands and Belgium. In the Netherlands, the spatially explicit AL selected 97 samples achieving an overall accuracy of 80%, compared to traditional AL selecting 169 samples with 82% overall accuracy. In Belgium, spatially explicit AL selected 223 samples and obtained 60% overall accuracy, while traditional AL selected 327 samples and obtained an overall accuracy of 63%. We concluded that the developed AL method helped RF achieve a good performance mostly for the classes consisting of individual crops with a relatively distinctive growth pattern such as sugar beets or cereals. Aggregated classes such as ‘fruits and nuts’ posed, however, a challenge.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Geo-Information Science and Earth Observation, University of Twente, 7522 NH Enschede, The Netherlands.
ORCID-Profile: Mariana Belgiu, Wietske Bijker
Zitieren
APA
Kaijage, B., Belgiu, M., & Bijker, W. (2024). Spatially Explicit Active Learning for Crop-Type Mapping from Satellite Image Time Series. Sensors, 24(7), 2108. https://doi.org/10.3390/s24072108
Vancouver
Kaijage B, Belgiu M, Bijker W. Spatially Explicit Active Learning for Crop-Type Mapping from Satellite Image Time Series. Sensors. 2024;24(7):2108. doi:10.3390/s24072108
BibTeX
@article{Kaijage2024,
author = {Kaijage, Beatrice and Belgiu, Mariana and Bijker, Wietske},
title = {Spatially Explicit Active Learning for Crop-Type Mapping from Satellite Image Time Series},
journal = {Sensors},
year = {2024},
volume = {24},
number = {7},
pages = {2108},
doi = {10.3390/s24072108}
}
EUVIMED