Mapping of avocado in the south of the state of Mexico by digital image processing sentinel-2

Authors

  • Dulce Karen Figueroa-Figueroa Facultad de Ciencias Agrícolas-Universidad Autónoma del Estado de México. Carretera Toluca-Ixtlahuaca km 15.5, El Cerrillo Piedras Blancas, Toluca, Estado de México, México. CP. 50295
  • Jose Francisco Ramírez Dávila Facultad de Ciencias Agrícolas-Universidad Autónoma del Estado de México. Carretera Toluca-Ixtlahuaca km 15.5, El Cerrillo Piedras Blancas, Toluca, Estado de México, México. CP. 50295A
  • Xanat Antonio-Némiga Facultad de Geografía-Universidad Autónoma del Estado de México. Cerro Coatepec s/n, Ciudad Universitaria, Toluca Estado de México, México. CP. 50110
  • Andrés González Huerta Facultad de Ciencias Agrícolas-Universidad Autónoma del Estado de México. Carretera Toluca-Ixtlahuaca km 15.5, El Cerrillo Piedras Blancas, Toluca, Estado de México, México. CP. 50295

DOI:

https://doi.org/10.29312/remexca.v11i4.2173

Keywords:

Persea americana Mill., SAM, vegetation indices

Abstract

The avocado crop (Persea americana Mill.) is one of the most important in Mexico, among the states with the highest production is the State of Mexico, which is the third producing state nationwide. Coatepec Harinas and Donato Guerra are two of the most representative municipalities regarding this activity; however, there is no census that specifies the surface of the crop, so the objective of this research was to test vegetation index methods, spectral angle mapper (SAM) and spectral information divergence (SID) algorithms and the combination of these in Sentinel-2 sensor images to evaluate its performance in identifying areas planted with the avocado crop. The results were validated with a confusion matrix and the comparison of the training and validation reference data. The SID algorithm achieved an accuracy of 97.5% to detect avocado, while the SAM treatment obtained an accuracy of 63.1%. The combination of SID with the Anthocyanin Reflectance Index 1 (ARI1), provided a better result on regional validation mapping with 85% accuracy. Other combinations of indices and treatments gave results less than 50% of the precision, so they are not recommended. This methodology could be tested for the detection of other crops of commercial interest, since Sentinel-2 shows to be a viable alternative for this type of study, having a good spectral resolution, as well as being easily accessible and manipulated.

Downloads

Download data is not yet available.

Published

2020-06-24

How to Cite

Figueroa-Figueroa, Dulce Karen, Jose Francisco Ramírez Dávila, Xanat Antonio-Némiga, and Andrés González Huerta. 2020. “Mapping of Avocado in the South of the State of Mexico by Digital Image Processing Sentinel-2”. Revista Mexicana De Ciencias Agrícolas 11 (4). México, ME:865-79. https://doi.org/10.29312/remexca.v11i4.2173.

Issue

Section

Articles

Most read articles by the same author(s)

<< < 1 2 3 

Similar Articles

You may also start an advanced similarity search for this article.