Using unmanned aerial vehicle and machine learning algorithm to monitor leaf nitrogen in coffee

Taya Cristo Parreiras,Ronaldo Luiz Mincato,Derielsen Brandão Santana,Guilherme Henrique Expedito Lense,Rodrigo Santos Moreira

doi:10.25186/.v15i.1736

Abstract

Nitrogen is an essential element for coffee production. However, when fertilization do not consider the spatial variability of the agricultural parameters, it can generate economic losses, such as low productivity, and environmental impacts, such as pollution of air and eutrophication of water bodies. Thus, the monitoring of the nitrogen during different phases of the production is a key factor for the fertilization management, and remote sensing based on unmanned aerial vehicles imagery has been evaluated for this task. Thus, this work aimed to evaluate the potential of visible vegetation indices obtained from such images to monitor the spatial variability of the leaf nitrogen content in a coffee farm located in Divisa Nova Municipality, Minas Gerais. Therefore, we performed a leaf analysis using the Kjeldahl method to determine leaf nitrogen, and to process the images and produce the vegetation indices, we use Geographic Information Systems and photogrammetry software. As analyze methods, we used the Random Forest classification algorithm as an estimator and performed ordinary kriging to visualize the spatial variability as nitrogen content. Lastly, the Pearson correlation coefficient was employed to evaluate the relationship between the variables. However, the Random Forest models were unable to explain nitrogen variability, and we did not find any significant correlations between the tested vegetation indices and nitrogen content. Therefore, it is indicated the replication of the study in the vegetative phase of the coffee plants, with the establishment of different fertilization treatments, as well as the use of multispectral sensors and radiometric calibration techniques. Keys words: Vegetation indices; RGB; machine learning; Coffea arabica.

Highlights

Coffee production can be impacted by several factors such as plagues, climate variations, planting system and density, terrain slope, soil quality, as well as the physiological characteristics of the plants (Ferraz et al, 2012)
Researchers have been analyzing the potential vegetation indices (VI) obtained with visible sensors mounted to unmanned aerial vehicles (UAV), along with digital image processing techniques, to monitor the spatial variability of the nitrogen content in different kinds of crops like barley (Escalante et al, 2019), grasses (Caturegli et al, 2019; Näsi et al, 2018), potatoes (Hunt Junior et al, 2018), wheat (Schirrmann et al, 2016), and maize (Zhang et al, 2020)
The Random Forest models were not able to explain and predict the nitrogen variability, since the regression model achieved an R2 of -0.06, while the classification model presented an overall accuracy of 33%, with a Kappa coefficient of -0.02

Summary

Introduction

Coffee production can be impacted by several factors such as plagues, climate variations, planting system and density, terrain slope, soil quality, as well as the physiological characteristics of the plants (Ferraz et al, 2012). Management planning and the monitoring of the crops are key-factors to guarantee good productivity and to reduce socioeconomics and environmental impacts (Näsi et al, 2018). Precision agriculture (PA) has been gained space on the field, approaching science and technology to agricultural practices, helping to reduce costs, improve productivity by area, and minimize environmental impacts through the planning of actions as fertilization, irrigation, and disease control (Vega et al, 2015), and remote sensing is an important technology of the PA (Hunt Junior et al, 2018). Researchers have been analyzing the potential vegetation indices (VI) obtained with visible sensors mounted to unmanned aerial vehicles (UAV), along with digital image processing techniques, to monitor the spatial variability of the nitrogen content in different kinds of crops like barley (Escalante et al, 2019), grasses (Caturegli et al, 2019; Näsi et al, 2018), potatoes (Hunt Junior et al, 2018), wheat (Schirrmann et al, 2016), and maize (Zhang et al, 2020)

Objectives

Methods

Findings

Conclusion