Crop recognition at orchard level in Mediterranean conditions using time series of Sentinel-2 spectral indices

The Valencian agricultural landscape is made up of a multitude of small-sized plots. Most remote sensing research has been focused on the discrimination of the large-scale land covers or uses, however, in Spain, crop recognition at plot level is crucial to develop management policies at different sc...

Full description

Bibliographic Details
Main Authors: Moltó, Enrique, Izquierdo-Sanz, Héctor
Format: conferenceObject
Language:Inglés
Published: Wageningen Academic Publishers 2023
Subjects:
Online Access:https://hdl.handle.net/20.500.11939/8682
https://www.wageningenacademic.com/doi/abs/10.3920/978-90-8686-947-3_121
_version_ 1855032835018063872
author Moltó, Enrique
Izquierdo-Sanz, Héctor
author_browse Izquierdo-Sanz, Héctor
Moltó, Enrique
author_facet Moltó, Enrique
Izquierdo-Sanz, Héctor
author_sort Moltó, Enrique
collection ReDivia
description The Valencian agricultural landscape is made up of a multitude of small-sized plots. Most remote sensing research has been focused on the discrimination of the large-scale land covers or uses, however, in Spain, crop recognition at plot level is crucial to develop management policies at different scales. This work describes preliminary work for constructing and validating a classification model for automatic identification of crops in an agricultural zone where different species of fruit trees are cultivated. The model is based on the analysis of time series of two spectral indices obtained from Sentinel-2 images and using a Fourier decomposition approach. A two-step classification procedure is proposed: a random forest classifier at pixel level, followed by a plot classification. The overall accuracy achieved was 84.18% and the Kappa index was 0.71.
format conferenceObject
id ReDivia8682
institution Instituto Valenciano de Investigaciones Agrarias (IVIA)
language Inglés
publishDate 2023
publishDateRange 2023
publishDateSort 2023
publisher Wageningen Academic Publishers
publisherStr Wageningen Academic Publishers
record_format dspace
spelling ReDivia86822025-04-25T14:50:51Z Crop recognition at orchard level in Mediterranean conditions using time series of Sentinel-2 spectral indices Moltó, Enrique Izquierdo-Sanz, Héctor Sentinel-2 Spectral index Time series Fourier decomposition Supervised classification E90 Agrarian structure N01 Agricultural engineering U10 Mathematical and statistical methods The Valencian agricultural landscape is made up of a multitude of small-sized plots. Most remote sensing research has been focused on the discrimination of the large-scale land covers or uses, however, in Spain, crop recognition at plot level is crucial to develop management policies at different scales. This work describes preliminary work for constructing and validating a classification model for automatic identification of crops in an agricultural zone where different species of fruit trees are cultivated. The model is based on the analysis of time series of two spectral indices obtained from Sentinel-2 images and using a Fourier decomposition approach. A two-step classification procedure is proposed: a random forest classifier at pixel level, followed by a plot classification. The overall accuracy achieved was 84.18% and the Kappa index was 0.71. 2023-07-25T13:44:34Z 2023-07-25T13:44:34Z 2023 conferenceObject Moltó, E., & Izquierdo-Sanz, H. (2023). Crop recognition at orchard level in Mediterranean conditions using time series of Sentinel-2 spectral indices. Precision agriculture’23, pp. 963-969. https://hdl.handle.net/20.500.11939/8682 10.3920/978-90-8686-947-3_121 https://www.wageningenacademic.com/doi/abs/10.3920/978-90-8686-947-3_121 en 2023-07 Precision Agriculture '23 Bologna info:eu-repo/grantAgreement/ERDF/PCV 2021-2027/52204/ES/Tecnología inteligente para una agricultura digital, sostenible y precisa en la comunitat valenciana/AgrIntel·ligència-CV Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ openAccess Wageningen Academic Publishers electronico
spellingShingle Sentinel-2
Spectral index
Time series
Fourier decomposition
Supervised classification
E90 Agrarian structure
N01 Agricultural engineering
U10 Mathematical and statistical methods
Moltó, Enrique
Izquierdo-Sanz, Héctor
Crop recognition at orchard level in Mediterranean conditions using time series of Sentinel-2 spectral indices
title Crop recognition at orchard level in Mediterranean conditions using time series of Sentinel-2 spectral indices
title_full Crop recognition at orchard level in Mediterranean conditions using time series of Sentinel-2 spectral indices
title_fullStr Crop recognition at orchard level in Mediterranean conditions using time series of Sentinel-2 spectral indices
title_full_unstemmed Crop recognition at orchard level in Mediterranean conditions using time series of Sentinel-2 spectral indices
title_short Crop recognition at orchard level in Mediterranean conditions using time series of Sentinel-2 spectral indices
title_sort crop recognition at orchard level in mediterranean conditions using time series of sentinel 2 spectral indices
topic Sentinel-2
Spectral index
Time series
Fourier decomposition
Supervised classification
E90 Agrarian structure
N01 Agricultural engineering
U10 Mathematical and statistical methods
url https://hdl.handle.net/20.500.11939/8682
https://www.wageningenacademic.com/doi/abs/10.3920/978-90-8686-947-3_121
work_keys_str_mv AT moltoenrique croprecognitionatorchardlevelinmediterraneanconditionsusingtimeseriesofsentinel2spectralindices
AT izquierdosanzhector croprecognitionatorchardlevelinmediterraneanconditionsusingtimeseriesofsentinel2spectralindices