Characterization of vineyard training systems based on remote sensing and crop indices

In the context of precision viticulture, this work presents the implementation of remote sensing techniques to analyze the spatial variability of a vineyard (Vitis vinifera L.). This work seeks to continue a preliminary investigation conducted in 2020; this time, the study area within the vineyard w...

Descripción completa

Detalles Bibliográficos
Autores principales: Capraro, Flavio, Pacheco, Daniela, Campillo, Pedro
Formato: info:ar-repo/semantics/documento de conferencia
Lenguaje:Español
Publicado: IEEE 2025
Materias:
Acceso en línea:http://hdl.handle.net/20.500.12123/23992
https://ieeexplore.ieee.org/document/10735888
https://doi.org/10.1109/ARGENCON62399.2024.10735888
_version_ 1855038856998420480
author Capraro, Flavio
Pacheco, Daniela
Campillo, Pedro
author_browse Campillo, Pedro
Capraro, Flavio
Pacheco, Daniela
author_facet Capraro, Flavio
Pacheco, Daniela
Campillo, Pedro
author_sort Capraro, Flavio
collection INTA Digital
description In the context of precision viticulture, this work presents the implementation of remote sensing techniques to analyze the spatial variability of a vineyard (Vitis vinifera L.). This work seeks to continue a preliminary investigation conducted in 2020; this time, the study area within the vineyard was expanded, and the campaigns of 2023 and 2024 were considered. This trial was conducted in a vineyard located in the province of San Juan, Argentina. The vineyard was divided into three blocks (replicates), and within each block, three training systems were randomly implemented: Free Cordon, Minimal Pruning and Box Pruning. The analysis was mainly based on extracting information from various vineyard maps constructed from high-resolution (2.5 cm pixel size) multispectral and thermographic images. These images were captured using special cameras mounted on an unmanned aerial vehicle (UAV). Vegetation indices NDVI and NDRE were calculated from the orthomosaics. The spatial distribution of each index and the crop temperature (Tc) were studied, and measurements were subsequently recorded in plants within each training system. Based on these measurements, significant differences were identified among the three training systems. The results demonstrated the usefulness of the high-resolution images acquired to assess the vineyard's condition at the plant level, allowing the producer to manage each training system specifically.
format info:ar-repo/semantics/documento de conferencia
id INTA23992
institution Instituto Nacional de Tecnología Agropecuaria (INTA -Argentina)
language Español
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher IEEE
publisherStr IEEE
record_format dspace
spelling INTA239922025-09-30T10:40:03Z Characterization of vineyard training systems based on remote sensing and crop indices Capraro, Flavio Pacheco, Daniela Campillo, Pedro Imagen Multiespectral Vitis vinífera Vid Agricultura Digital Agricultura de Precisión Digital Agriculture Precision Agriculture Vehículo Aéreo No Tripulado Multispectral Imagery Unmanned Aerial Vehicles Grapevines Remote Sensing Teledetección Imágenes Termográficas In the context of precision viticulture, this work presents the implementation of remote sensing techniques to analyze the spatial variability of a vineyard (Vitis vinifera L.). This work seeks to continue a preliminary investigation conducted in 2020; this time, the study area within the vineyard was expanded, and the campaigns of 2023 and 2024 were considered. This trial was conducted in a vineyard located in the province of San Juan, Argentina. The vineyard was divided into three blocks (replicates), and within each block, three training systems were randomly implemented: Free Cordon, Minimal Pruning and Box Pruning. The analysis was mainly based on extracting information from various vineyard maps constructed from high-resolution (2.5 cm pixel size) multispectral and thermographic images. These images were captured using special cameras mounted on an unmanned aerial vehicle (UAV). Vegetation indices NDVI and NDRE were calculated from the orthomosaics. The spatial distribution of each index and the crop temperature (Tc) were studied, and measurements were subsequently recorded in plants within each training system. Based on these measurements, significant differences were identified among the three training systems. The results demonstrated the usefulness of the high-resolution images acquired to assess the vineyard's condition at the plant level, allowing the producer to manage each training system specifically. EEA San Juan Fil: Capraro, Flavio. Universidad Nacional de San Juan. Facultad de Ingeniería. Instituto de Automática; Argentina Fil: Pacheco, Daniela Elizabeth. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria San Juan; Argentina. Fil: Campillo, Pedro. Universidad Nacional de San Juan. Facultad de Ingeniería. Instituto de Automática; Argentina 2025-09-30T10:34:29Z 2025-09-30T10:34:29Z 2024-09-18 info:ar-repo/semantics/documento de conferencia info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/publishedVersion http://hdl.handle.net/20.500.12123/23992 https://ieeexplore.ieee.org/document/10735888 979-8-3503-6593-1 https://doi.org/10.1109/ARGENCON62399.2024.10735888 spa info:eu-repograntAgreement/INTA/2023-PE-L01-I002, Aportes para la innovación y el desarrollo en los territorios a través del fortalecimiento de la viticultura info:eu-repo/semantics/restrictedAccess http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf IEEE VII Congreso Bienal ARGENCON. 18 al 20 de septiembre 2024. San Nicolás de los Arroyos. Argentina
spellingShingle Imagen Multiespectral
Vitis vinífera
Vid
Agricultura Digital
Agricultura de Precisión
Digital Agriculture
Precision Agriculture
Vehículo Aéreo No Tripulado
Multispectral Imagery
Unmanned Aerial Vehicles
Grapevines
Remote Sensing
Teledetección
Imágenes Termográficas
Capraro, Flavio
Pacheco, Daniela
Campillo, Pedro
Characterization of vineyard training systems based on remote sensing and crop indices
title Characterization of vineyard training systems based on remote sensing and crop indices
title_full Characterization of vineyard training systems based on remote sensing and crop indices
title_fullStr Characterization of vineyard training systems based on remote sensing and crop indices
title_full_unstemmed Characterization of vineyard training systems based on remote sensing and crop indices
title_short Characterization of vineyard training systems based on remote sensing and crop indices
title_sort characterization of vineyard training systems based on remote sensing and crop indices
topic Imagen Multiespectral
Vitis vinífera
Vid
Agricultura Digital
Agricultura de Precisión
Digital Agriculture
Precision Agriculture
Vehículo Aéreo No Tripulado
Multispectral Imagery
Unmanned Aerial Vehicles
Grapevines
Remote Sensing
Teledetección
Imágenes Termográficas
url http://hdl.handle.net/20.500.12123/23992
https://ieeexplore.ieee.org/document/10735888
https://doi.org/10.1109/ARGENCON62399.2024.10735888
work_keys_str_mv AT capraroflavio characterizationofvineyardtrainingsystemsbasedonremotesensingandcropindices
AT pachecodaniela characterizationofvineyardtrainingsystemsbasedonremotesensingandcropindices
AT campillopedro characterizationofvineyardtrainingsystemsbasedonremotesensingandcropindices