Identification and characterization of crops through the analysis of spectral data with machine learning algorithms

This paper assesses the capability of an spectrometer used in field experiments of soybean, maize and wheat. The objective of this work is to select different wavelengths intervals of the spectral reflectance curve, within the range 632-1125 nm, as features for classification using machine learning...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Rigalli, Nicolás Francisco, Montero Bulacio, Enrique, Romagnoli, Martín, Terissi, Lucas D., Portapila, Margarita Isabel
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2018
Materias:
Ciencias Informáticas
remote sensing
NIR
spectral feature selection
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/71510
http://47jaiio.sadio.org.ar/sites/default/files/CAI-50.pdf
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-71510
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
remote sensing
NIR
spectral feature selection
spellingShingle Ciencias Informáticas
remote sensing
NIR
spectral feature selection
Rigalli, Nicolás Francisco
Montero Bulacio, Enrique
Romagnoli, Martín
Terissi, Lucas D.
Portapila, Margarita Isabel
Identification and characterization of crops through the analysis of spectral data with machine learning algorithms
topic_facet Ciencias Informáticas
remote sensing
NIR
spectral feature selection
description This paper assesses the capability of an spectrometer used in field experiments of soybean, maize and wheat. The objective of this work is to select different wavelengths intervals of the spectral reflectance curve, within the range 632-1125 nm, as features for classification using machine learning methods. Two different classifications are presented, species selection and growth stage identification. For species classification accuracy of 92% is reached, while 99% is obtained for stage classification. In addition we propose a new index that outperforms analyzed established vegetation indices, which shows the potential advantage of using this type of devices.
format Objeto de conferencia
Objeto de conferencia
author Rigalli, Nicolás Francisco
Montero Bulacio, Enrique
Romagnoli, Martín
Terissi, Lucas D.
Portapila, Margarita Isabel
author_facet Rigalli, Nicolás Francisco
Montero Bulacio, Enrique
Romagnoli, Martín
Terissi, Lucas D.
Portapila, Margarita Isabel
author_sort Rigalli, Nicolás Francisco
title Identification and characterization of crops through the analysis of spectral data with machine learning algorithms
title_short Identification and characterization of crops through the analysis of spectral data with machine learning algorithms
title_full Identification and characterization of crops through the analysis of spectral data with machine learning algorithms
title_fullStr Identification and characterization of crops through the analysis of spectral data with machine learning algorithms
title_full_unstemmed Identification and characterization of crops through the analysis of spectral data with machine learning algorithms
title_sort identification and characterization of crops through the analysis of spectral data with machine learning algorithms
publishDate 2018
url http://sedici.unlp.edu.ar/handle/10915/71510
http://47jaiio.sadio.org.ar/sites/default/files/CAI-50.pdf
work_keys_str_mv AT rigallinicolasfrancisco identificationandcharacterizationofcropsthroughtheanalysisofspectraldatawithmachinelearningalgorithms
AT monterobulacioenrique identificationandcharacterizationofcropsthroughtheanalysisofspectraldatawithmachinelearningalgorithms
AT romagnolimartin identificationandcharacterizationofcropsthroughtheanalysisofspectraldatawithmachinelearningalgorithms
AT terissilucasd identificationandcharacterizationofcropsthroughtheanalysisofspectraldatawithmachinelearningalgorithms
AT portapilamargaritaisabel identificationandcharacterizationofcropsthroughtheanalysisofspectraldatawithmachinelearningalgorithms
bdutipo_str Repositorios
_version_ 1764820482396258304

Ejemplares similares