Reliability of Summer Crop Masks Derived from Second Order Polynomial Equations

Christiano L. Arraes, Rubens A. C. Lamparelli, Jansle Rocha, Julio Esquerdo, Pablo Salvador, Javier Rodríguez, José-Luis Casanova Roque, Julia Sanz Justo and Beatriz Benatti

Journal of Agricultural Science, 2013, vol. 5, issue 3, 63

Abstract: Remote Sensing techniques are useful to determine planted areas, especially of commodities like maize and soybeans (summer cultures). The vegetation indexes as NDVI (Normalized Difference Vegetation Index) has been used to map agricultural areas due to its low cost and accessibility. Therefore the objective of this study was to develop a new methodology to generate masks of summer crops based on fitting second order polynomial equations to temporal NDVI profiles. The results showed that selecting polynomial equations with r2 fitting above 0.75, a Kappa index of 0.86 and a global accuracy of 93% is obtained. This is slightly higher than the results obtained when using the maximum-minimum NDVI technique, with a Kappa index of 0.82 and a global accuracy of 91%. However, while quantifying the areas under study, one verified that the mask used by the proposed methodology, was closer to the official IBGE data, with a difference of -10.25%, followed by the vector technique with 23% and by the maximum-minimum NDVI, with a difference of 42.8%.

Date: 2013
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://ccsenet.org/journal/index.php/jas/article/download/22216/15482 (application/pdf)
https://ccsenet.org/journal/index.php/jas/article/view/22216 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ibn:jasjnl:v:5:y:2013:i:3:p:63

Access Statistics for this article

More articles in Journal of Agricultural Science from Canadian Center of Science and Education Contact information at EDIRC.
Bibliographic data for series maintained by Canadian Center of Science and Education ().