An Automated Method for Annual Cropland Mapping along the Season for Various Globally-Distributed Agrosystems Using High Spatial and Temporal Resolution Time Series

Remote Sensing

Nicolas Matton⁴  Guadalupe Sepulcre Canto⁴  François Waldner⁴  Silvia Valero³  David Morin³  Jordi Inglada³  Marcela Arias³  Sophie Bontemps⁴  Benjamin Koetz¹  Pierre Defourny⁴  Clement Atzberger² 

[1] European Space Agency, European Space Research Institute, Via Galileo Galilei, Casella Postale 64, 00044 Roma, Italy; E-Mail:Earth and Life Institute, Université Catholique de Louvain, Croix du Sud 2, 1348 Louvain-la-Neuve, Belgium;;Centre d’Etudes Spatiales de la BIOSphère, Unité Mixte CNES-CNRS-UPS-IRD, Toulouse 31401, France; E-Mails:;Earth and Life Institute, Université Catholique de Louvain, Croix du Sud 2, 1348 Louvain-la-Neuve, Belgium; E-Mails:

关键词: agriculture monitoring;    cropland;    timeliness;    high resolution time series;    Sen2Agri;    Sentinel-2;    SPOT 4 (Take 5);    JECAM;   

DOI  :  10.3390/rs71013208

来源: mdpi

【 摘 要 】

Cropland mapping relies heavily on field data for algorithm calibration, making it, in many cases, applicable only at the field campaign scale. While the recently launched Sentinel-2 satellite will be able to deliver time series over large regions, it will not really be compatible with the current mapping approach or the available in situ data. This research introduces a generic methodology for mapping annual cropland along the season at high spatial resolution with the use of globally available baseline land cover and no need for field data. The methodology is based on cropland-specific temporal features, which are able to cope with the diversity of agricultural systems, prior information from which mislabeled pixels have been removed and a cost-effective classifier. Thanks to the JECAM network, eight sites across the world were selected for global cropland mapping benchmarking. Accurate cropland maps were produced at the end of the season, showing an overall accuracy of more than 85%. Early cropland maps were also obtained at three-month intervals after the beginning of the growing season, and these showed reasonable accuracy at the three-month stage (>70% overall accuracy) and progressive improvement along the season. The trimming-based method was found to be key for using spatially coarse baseline land cover information and, thus, avoiding costly field campaigns for prior information retrieval. The accuracy and timeliness of the proposed approach shows that it has substantial potential for operational agriculture monitoring programs.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.