Recognition of Maize Phenology in Sentinel Images with Machine Learning.

Alvaro Murguia-Cozar,Demetrio Salvador Fernandez-Reynoso,Antonia Macedo-Cruz,Jorge Arturo Salgado Transito

doi:10.3390/s22010094

Abstract

The scarcity of water for agricultural use is a serious problem that has increased due to intense droughts, poor management, and deficiencies in the distribution and application of the resource. The monitoring of crops through satellite image processing and the application of machine learning algorithms are technological strategies with which developed countries tend to implement better public policies regarding the efficient use of water. The purpose of this research was to determine the main indicators and characteristics that allow us to discriminate the phenological stages of maize crops (Zea mays L.) in Sentinel 2 satellite images through supervised classification models. The training data were obtained by monitoring cultivated plots during an agricultural cycle. Indicators and characteristics were extracted from 41 Sentinel 2 images acquired during the monitoring dates. With these images, indicators of texture, vegetation, and colour were calculated to train three supervised classifiers: linear discriminant (LD), support vector machine (SVM), and k-nearest neighbours (kNN) models. It was found that 45 of the 86 characteristics extracted contributed to maximizing the accuracy by stage of development and the overall accuracy of the trained classification models. The characteristics of the Moran’s I local indicator of spatial association (LISA) improved the accuracy of the classifiers when applied to the L*a*b* colour model and to the near-infrared (NIR) band. The local binary pattern (LBP) increased the accuracy of the classification when applied to the red, green, blue (RGB) and NIR bands. The colour ratios, leaf area index (LAI), RGB colour model, L*a*b* colour space, LISA, and LBP extracted the most important intrinsic characteristics of maize crops with regard to classifying the phenological stages of the maize cultivation. The quadratic SVM model was the best classifier of maize crop phenology, with an overall accuracy of 82.3%.

Highlights

The mismanagement of water resources and deficiencies in their distribution and application are serious problems that increase the volume of water necessary for the establishment of crops, which has a negative impact on the availability of water resources and results in large economic losses in the agricultural sector
A methodology was presented to classify the phenological stages of maize cultivation through the processing of Sentinel 2 satellite images and pattern recognition techniques
To recognize the six phenological stages of maize crops, three supervised classifiers linear discriminant (LD), quadratic support vector machine (SVM), and k-nearest neighbours (kNN) were trained using 86 characteristics extracted from Sentinel 2 satellite images with MATLAB Classification Learner software

Summary

Introduction

The mismanagement of water resources and deficiencies in their distribution and application are serious problems that increase the volume of water necessary for the establishment of crops, which has a negative impact on the availability of water resources and results in large economic losses in the agricultural sector. The modernization of hydro-agricultural infrastructure and the application of more efficient irrigation systems are actions that are being applied in several countries of the world to increase irrigation efficiency and improve water management. González-Trinidad et al [2] evaluated water efficiency and agricultural productivity in a modernized semi-arid region in central-north Mexico. Their results indicated a 30% increase in global efficiency and higher yields in all crops. In Spain, for three decades, they have promoted the use of pressurized irrigation systems to reach 72% of the arable area [4], in Brazil, the main modern irrigation technique is the central pivot irrigation system with a 78.3% of irrigable area [5]

Objectives

Methods

Results