Estimation of Leaf Area Index in vineyards by analysing projected shadows using UAV imagery

Sergio Vélez,Enrique Barajas,Rubén Vacas,Carlos Poblete-Echeverría,José Antonio Rubio

doi:10.20870/oeno-one.2021.55.4.4639

Sergio Vélez, Enrique Barajas + Show 3 more

Open Access

https://doi.org/10.20870/oeno-one.2021.55.4.4639

Copy DOI

Abstract

A few decades ago, farmers could precisely monitor their croplands just by walking over the fields, but this task becomes more difficult as farm size increases. Precision viticulture can help better understand the vineyard and measure some key structural parameters, such as the Leaf Area Index (LAI). Remote Sensing is a typical approach to monitoring vegetation which measures the spectral information directly emitted and reflected from vegetation. This study explores a new method for estimating LAI which measures the projected shadows of plants using UAV (unmanned aerial vehicle) imagery. A flight mission over a vineyard was scheduled in the afternoon (15:30 to 16:00 solar time), which is the optimal time for the projection of vine shadows on the ground. Real LAI was measured destructively by removing all the vegetation from the area. Then, the projected shadows in the image were detected using machine learning methods (k-means and random forest) and analysed at pixel level using a customised R code. A strong linear relationship (R² = 0.76, RMSE = 0.160 m² m-2 and MAE = 0.139 m² m-2) was found between the shaded area and the LAI per vine. This is a quick and simple method, which is non-destructive and gives accurate results; moreover, flights can be scheduled during other periods of the day than solar noon, such as in the morning or afternoon, thus enabling pilots to extend their working day. Therefore, it may be a viable option for determining LAI in vineyards trained on Vertical Shoot Positioned (VSP) systems.

Highlights

According to European Union policies (Zarco‐Tejada et al, 2014), Precision Agriculture is a farming management concept based on observing, measuring, and responding to interand intra-field variability in crops, and in which the spatial variability of vineyards plays a vital role
The results show that, by using simple equations and machine learning methods and by controlling the limitation factors, leaf surface area can be estimated from the shadow of the plants
This study shows a simple and effective method for estimating Leaf Area Index (LAI) in vineyards using machine learning tools and projected shadows captured by a UAV

Summary

Introduction

According to European Union policies (Zarco‐Tejada et al, 2014), Precision Agriculture is a farming management concept based on observing, measuring, and responding to interand intra-field variability in crops, and in which the spatial variability of vineyards plays a vital role. Until a few decades ago, farmers could precisely monitor their croplands just by walking over the fields, but with increasing farm size this task is becoming more difficult without using technology (Balafoutis et al, 2017). All of this has led to a growing interest in precision viticulture and further research efforts (Santesteban, 2019), but results can vary significantly depending on knowledge of the crop. Leaf area is commonly measured using the Leaf Area Index, LAI (Lambers and Oliveira, 2019), which is closely related to photosynthetic active radiation assimilation (Pessarakli, 2014) and is defined as the vegetative development of a crop per unit area of land (Watson, 1947)

Methods

Results

Discussion

Conclusion