EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mapping Integrated Crop–Livestock Systems Using Fused Sentinel-2 and PlanetScope Time Series and Deep Learning

João P. S. Werner, Mariana Belgiu, Inacio T. Bueno, Aliny A. Dos Reis, Ana P. S. G. D. Toro, João F. G. Antunes, Alfred Stein, Rubens A. C. Lamparelli, Paulo S. G. Magalhães, Alexandre C. Coutinho, Júlio C. D. M. Esquerdo, Gleyce K. D. A. Figueiredo

Remote Sensing · 17.04.2024 · 16 (8) · 1421

DOI: 10.3390/rs16081421 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 17.04.2024. Verfasst von João P. S. Werner und 11 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: São Paulo Research Foundation (FAPESP), National Council for Scientific and Technological Development (CNPq), Coordination for the Improvement of Higher Education Personnel.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Integrated crop–livestock systems (ICLS) are among the main viable strategies for sustainable agricultural production. Mapping these systems is crucial for monitoring land use changes in Brazil, playing a significant role in promoting sustainable agricultural production. Due to the highly dynamic nature of ICLS management, mapping them is a challenging task. The main objective of this research was to develop a method for mapping ICLS using deep learning algorithms applied on Satellite Image Time Series (SITS) data cubes, which consist of Sentinel-2 (S2) and PlanetScope (PS) satellite images, as well as data fused (DF) from both sensors. This study focused on two Brazilian states with varying landscapes and field sizes. Targeting ICLS, field data were combined with S2 and PS data to build land use and land cover classification models for three sequential agricultural years (2018/2019, 2019/2020, and 2020/2021). We tested three experimental settings to assess the classification performance using S2, PS, and DF data cubes. The test classification algorithms included Random Forest (RF), Temporal Convolutional Neural Network (TempCNN), Residual Network (ResNet), and a Lightweight Temporal Attention Encoder (L-TAE), with the latter incorporating an attention-based model, fusing S2 and PS within the temporal encoders. Experimental results did not show statistically significant differences between the three data sources for both study areas. Nevertheless, the TempCNN outperformed the other classifiers with an overall accuracy above 90% and an F1-Score of 86.6% for the ICLS class. By selecting the best models, we generated annual ICLS maps, including their surrounding landscapes. This study demonstrated the potential of deep learning algorithms and SITS to successfully map dynamic agricultural systems.

Förderung

  • São Paulo Research Foundation (FAPESP)
  • National Council for Scientific and Technological Development (CNPq)
  • Coordination for the Improvement of Higher Education Personnel

Zitieren

APA

Werner, J. P. S., Belgiu, M., Bueno, I. T., Reis, A. A. D., Toro, A. P. S. G. D., Antunes, J. F. G., Stein, A., Lamparelli, R. A. C., Magalhães, P. S. G., Coutinho, A. C., Esquerdo, J. C. D. M., & Figueiredo, G. K. D. A. (2024). Mapping Integrated Crop–Livestock Systems Using Fused Sentinel-2 and PlanetScope Time Series and Deep Learning. Remote Sensing, 16(8), 1421. https://doi.org/10.3390/rs16081421

Vancouver

Werner JPS, Belgiu M, Bueno IT, Reis AAD, Toro APSGD, Antunes JFG, et al. Mapping Integrated Crop–Livestock Systems Using Fused Sentinel-2 and PlanetScope Time Series and Deep Learning. Remote Sensing. 2024;16(8):1421. doi:10.3390/rs16081421

BibTeX
@article{Werner2024,
  author = {Werner, João P. S. and Belgiu, Mariana and Bueno, Inacio T. and Reis, Aliny A. Dos and Toro, Ana P. S. G. D. and Antunes, João F. G. and Stein, Alfred and Lamparelli, Rubens A. C. and Magalhães, Paulo S. G. and Coutinho, Alexandre C. and Esquerdo, Júlio C. D. M. and Figueiredo, Gleyce K. D. A.},
  title = {Mapping Integrated Crop–Livestock Systems Using Fused Sentinel-2 and PlanetScope Time Series and Deep Learning},
  journal = {Remote Sensing},
  year = {2024},
  volume = {16},
  number = {8},
  pages = {1421},
  doi = {10.3390/rs16081421}
}
Kostenlos starten →