Home // GEOProcessing 2020, The Twelfth International Conference on Advanced Geographic Information Systems, Applications, and Services // View article

Identifying the Existence of Grass Coverage in Vineyards Applying Time Series Analysis in Sentinel-2 Bands

Authors:
Daniel A. Basterrechea
Lorena Parra
Jaime Lloret
Pedro V. Mauri

Keywords: Precision agriculture; Image processing; Sentinel-2 bands; Vineyard monitoring.

Abstract:
The increasing tendency of the population increment the pressure in vineyards farmers to supply the demand for food. In this context, grass coverage will be a low-cost solution to reduce outlays and reduce the maintenance of crops. In this paper, we present a remote sensing technique for determining the existence or absence of grass coverage in vineyards. To perform this study, we use Sentinel-2 images using red, green, and blue bands, as well as a water vapour band, near-infrared band, and normalized difference vegetation band. This technique has certain limits, such as low spatial resolution, and cloud presence when the images are obtained. The selected images have 10 m x 10 m spatial resolution, except for the band of water vapour band (60 m x 60 m). In this study, we propose the use of time-series analysis to overcome the problem with the low spatial resolution. To perform this study, we obtain images from January and June. Using ArcGIS software, we applied different tools to obtain qualitative and quantitative information. Then, we analyzed the significance of observed differences in the time series analysis, applying Single Analysis of Variance. Our results indicate that the best results are related to the Near-infrared band with a p-value of 0.0020. Finally, the pixel values obtained for the time series analysis of Near-Infrared band indicate that the plots with grass coverage have values from -1000 to -1200. Meanwhile, values from -1200 to -1500 are found in the plots without grass coverage.

Pages: 90 to 95

Copyright: Copyright (c) IARIA, 2020

Publication date: March 22, 2020

Published in: conference

ISSN: 2308-393X

ISBN: 978-1-61208-762-7

Location: Valencia, Spain

Dates: from November 21, 2020 to November 25, 2020