English

Antonio Da Silva Junior Carlos,Eri Marta,Fernando Capristo Silva Guilherme,Eduardo Teodoro Paulo,Guerreiro De Lima Mendelson,Rafael Nanni Marcos

doi:10.5897/ajar2016.11572

Abstract

This study aimed to develop and evaluate the Artificial Neural Networks (ANNs) settings to differentiate and estimate areas of soybean by employing the vegetation index with and without time series. Study area comprises the state of Parana, South Brazil. The images used to process the ANN were Normalized Difference Vegetation Index (NDVI), Perpendicular Vegetation Index (PVI) and Enhanced Vegetation Index (EVI) indices, including Julian day 017 and Crop Enhanced Index (CEI), which were derived from time series MOD13Q1 product from MODIS sensor Terra satellite. The samples were demarcated into polygon soybean, non-soybean and others (mainly streams). ANN architecture was performed by the module classification employing Multi-layer Perceptron (MLP) artificial neural networks trained by using back propagation algorithm. CEI as a vegetation index with timed series discrimination of soybean areas, pixels with higher than 0.28 rates, proved to be equivalent to ANN to separate soybean areas. Kappa parameter of 0.40 and 0.34 for CEI index and ANN, respectively, it was found in mapped areas. The major and unique contribution of the current study for remote sensing in agriculture was to show that vegetation indices coupled with artificial neural network techniques may improve the results of crop mapping, especially in soybean areas. Key words: Back propagation neural network, remote sensing, perpendicular vegetation index (PVI), enhanced vegetation index (EVI), crop enhancement index (CEI), time-series.

Highlights

It is important and necessary to monitor crops and other agricultural activities in the country, mainly because some cultivated areas are carried out by government agencies in subjective forms
When analyzing the data obtained by the methods used in the estimates of soybean areas (CEI and Artificial Neural Networks (ANNs)), we found that classifications were equal to Z test reference for the Kappa (κ) and Overall Accuracy (OA) parameters (Table 2)
This study describes the mapping of soybean areas with artificial neural networks with the implementation of vegetation indices

Summary

Introduction

It is important and necessary to monitor crops and other agricultural activities in the country, mainly because some cultivated areas are carried out by government agencies in subjective forms. On taking decisions through learning techniques and acquiring knowledge experience indicated by a user, that is, learning, making mistakes and going on to new discoveries. As the nervous system is composed of several neurons, ANNs is formed by units of small modules which simulate the neuron mechanism (Haykin, 2008)

Objectives

Methods

Results

Conclusion