Vine yield estimation from block to regional scale employing remote sensing, weather, and management data

Knowledge of the spatial variation in vine yield at different scales is crucial for the wine business, and combined with estimations of vine size variability enables within-block mapping of vegetative-reproductive balance. Remote sensing combined with other data that excludes field sampling appears...

Full description

Saved in:
Bibliographic Details
Main Authors: Pedro C. Towers, Sean E. Roulet, Carlos Poblete-Echeverría
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Information Processing in Agriculture
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2214317324000519
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730327675666432
author Pedro C. Towers
Sean E. Roulet
Carlos Poblete-Echeverría
author_facet Pedro C. Towers
Sean E. Roulet
Carlos Poblete-Echeverría
author_sort Pedro C. Towers
collection DOAJ
description Knowledge of the spatial variation in vine yield at different scales is crucial for the wine business, and combined with estimations of vine size variability enables within-block mapping of vegetative-reproductive balance. Remote sensing combined with other data that excludes field sampling appears as an optimal approach for yield estimation for a broad range of scales. In this study, mean yield and factors known to affect yield components were collected for over 8000 blocks, over 18 seasons, in the western oasis of Mendoza, Argentina. Partial Least Squares (PLS) and Random Forest (RF) models were used to analyse the relationship between these factors and yield. The PLS model delivered very poor results, with coefficients of determination lower than 0.08. RF models with 49 to 19 variables produced predictions with coefficients of determination of 0.96 to 0.90, respectively. Some factors traditionally considered important in yield determination, such as trellis, frost occurrence, or planting density had limited influence, whereas location weighed heavily. Results suggest a successful approach to spatial prediction of yield that requires no fieldwork and indicates VRB mapping at block-scale may be possible with these tools. Several improvements to inputs are proposed.
format Article
id doaj-art-70781017c7f24c2fa4cf97553641303e
institution DOAJ
issn 2214-3173
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Information Processing in Agriculture
spelling doaj-art-70781017c7f24c2fa4cf97553641303e2025-08-20T03:08:55ZengElsevierInformation Processing in Agriculture2214-31732025-06-0112219520810.1016/j.inpa.2024.06.001Vine yield estimation from block to regional scale employing remote sensing, weather, and management dataPedro C. Towers0Sean E. Roulet1Carlos Poblete-Echeverría2South African Grape and Wine Research Institute (SAGWRI), Department of Viticulture and Oenology, Faculty of AgriSciences, Stellenbosch University, Matieland 7602, South Africa; AgriSat SA—Remote Sensing for Agriculture, Pasaje La Loma 983, (5178) La Cumbre, Córdoba, ArgentinaAgriSat SA—Remote Sensing for Agriculture, Pasaje La Loma 983, (5178) La Cumbre, Córdoba, ArgentinaSouth African Grape and Wine Research Institute (SAGWRI), Department of Viticulture and Oenology, Faculty of AgriSciences, Stellenbosch University, Matieland 7602, South Africa; Corresponding author.Knowledge of the spatial variation in vine yield at different scales is crucial for the wine business, and combined with estimations of vine size variability enables within-block mapping of vegetative-reproductive balance. Remote sensing combined with other data that excludes field sampling appears as an optimal approach for yield estimation for a broad range of scales. In this study, mean yield and factors known to affect yield components were collected for over 8000 blocks, over 18 seasons, in the western oasis of Mendoza, Argentina. Partial Least Squares (PLS) and Random Forest (RF) models were used to analyse the relationship between these factors and yield. The PLS model delivered very poor results, with coefficients of determination lower than 0.08. RF models with 49 to 19 variables produced predictions with coefficients of determination of 0.96 to 0.90, respectively. Some factors traditionally considered important in yield determination, such as trellis, frost occurrence, or planting density had limited influence, whereas location weighed heavily. Results suggest a successful approach to spatial prediction of yield that requires no fieldwork and indicates VRB mapping at block-scale may be possible with these tools. Several improvements to inputs are proposed.http://www.sciencedirect.com/science/article/pii/S2214317324000519Precision viticultureRemote sensingSpatial variabilityMachine learningRandom ForestPartial least square regression
spellingShingle Pedro C. Towers
Sean E. Roulet
Carlos Poblete-Echeverría
Vine yield estimation from block to regional scale employing remote sensing, weather, and management data
Information Processing in Agriculture
Precision viticulture
Remote sensing
Spatial variability
Machine learning
Random Forest
Partial least square regression
title Vine yield estimation from block to regional scale employing remote sensing, weather, and management data
title_full Vine yield estimation from block to regional scale employing remote sensing, weather, and management data
title_fullStr Vine yield estimation from block to regional scale employing remote sensing, weather, and management data
title_full_unstemmed Vine yield estimation from block to regional scale employing remote sensing, weather, and management data
title_short Vine yield estimation from block to regional scale employing remote sensing, weather, and management data
title_sort vine yield estimation from block to regional scale employing remote sensing weather and management data
topic Precision viticulture
Remote sensing
Spatial variability
Machine learning
Random Forest
Partial least square regression
url http://www.sciencedirect.com/science/article/pii/S2214317324000519
work_keys_str_mv AT pedroctowers vineyieldestimationfromblocktoregionalscaleemployingremotesensingweatherandmanagementdata
AT seaneroulet vineyieldestimationfromblocktoregionalscaleemployingremotesensingweatherandmanagementdata
AT carlospobleteecheverria vineyieldestimationfromblocktoregionalscaleemployingremotesensingweatherandmanagementdata