Rice crop detection using LSTM, Bi-LSTM, and machine learning models from sentinel-1 time series
The Synthetic Aperture Radar (SAR) time series allows describing the rice phenological cycle by the backscattering time signature. Therefore, the advent of the Copernicus Sentinel-1 program expands studies of radar data (C-band) for rice monitoring at regional scales, due to the high temporal resolu...
Main Authors: | Castro Filho, Hugo Crisóstomo de, Carvalho Júnior, Osmar Abílio de, Carvalho, Osmar Luiz Ferreira de, Bem, Pablo Pozzobon de, Moura, Rebeca dos Santos de, Albuquerque, Anesmar Olino de, Silva, Cristiano Rosa, Ferreira, Pedro Henrique Guimarães, Guimarães, Renato Fontes, Gomes, Roberto Arnaldo Trancoso |
---|---|
Format: | Artigo |
Language: | Inglês |
Published: |
MDPI
2021
|
Subjects: | |
Online Access: |
https://repositorio.unb.br/handle/10482/41912 https://doi.org/10.3390/rs12162655 https://orcid.org/ 0000-0002-0346-1684 https://orcid.org/ 0000-0002-5619-8525 https://orcid.org/ 0000-0003-3868-8704 https://orcid.org/ 0000-0002-7685-8826 https://orcid.org/ 0000-0003-1561-7583 https://orcid.org/ 0000-0001-6610-3078 https://orcid.org/ 0000-0002-9555-043X https://orcid.org/ 0000-0003-4724-4064 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
ir-10482-41912 |
---|---|
recordtype |
dspace |
spelling |
ir-10482-419122021-08-25T15:25:58Z Rice crop detection using LSTM, Bi-LSTM, and machine learning models from sentinel-1 time series Castro Filho, Hugo Crisóstomo de Carvalho Júnior, Osmar Abílio de Carvalho, Osmar Luiz Ferreira de Bem, Pablo Pozzobon de Moura, Rebeca dos Santos de Albuquerque, Anesmar Olino de Silva, Cristiano Rosa Ferreira, Pedro Henrique Guimarães Guimarães, Renato Fontes Gomes, Roberto Arnaldo Trancoso Monitoramento de safras Imagem multitemporal Aprendizado profundo Aprendizado de máquina Rede neural recorrente The Synthetic Aperture Radar (SAR) time series allows describing the rice phenological cycle by the backscattering time signature. Therefore, the advent of the Copernicus Sentinel-1 program expands studies of radar data (C-band) for rice monitoring at regional scales, due to the high temporal resolution and free data distribution. Recurrent Neural Network (RNN) model has reached state-of-the-art in the pattern recognition of time-sequenced data, obtaining a significant advantage at crop classification on the remote sensing images. One of the most used approaches in the RNN model is the Long Short-Term Memory (LSTM) model and its improvements, such as Bidirectional LSTM (Bi-LSTM). Bi-LSTM models are more effective as their output depends on the previous and the next segment, in contrast to the unidirectional LSTM models. The present research aims to map rice crops from Sentinel-1 time series (band C) using LSTM and Bi-LSTM models in West Rio Grande do Sul (Brazil). We compared the results with traditional Machine Learning techniques: Support Vector Machines (SVM), Random Forest (RF), k-Nearest Neighbors (k-NN), and Normal Bayes (NB). The developed methodology can be subdivided into the following steps: (a) acquisition of the Sentinel time series over two years; (b) data pre-processing and minimizing noise from 3D spatial-temporal filters and smoothing with Savitzky-Golay filter; (c) time series classification procedures; (d) accuracy analysis and comparison among the methods. The results show high overall accuracy and Kappa (>97% for all methods and metrics). Bi-LSTM was the best model, presenting statistical differences in the McNemar test with a significance of 0.05. However, LSTM and Traditional Machine Learning models also achieved high accuracy values. The study establishes an adequate methodology for mapping the rice crops in West Rio Grande do Sul. 2021-08-25T15:25:21Z 2021-08-25T15:25:21Z 2020-08-18 Artigo CASTRO FILHO, Hugo Crisóstomo de et al. Rice crop detection using LSTM, Bi-LSTM, and machine learning models from sentinel-1 time series. Remote Sensing, v. 12, n. 16, 2655, 2020. DOI: https://doi.org/10.3390/rs12162655. Disponível em: https://www.mdpi.com/2072-4292/12/16/2655. Acesso em: 25 ago. 2021. https://repositorio.unb.br/handle/10482/41912 https://doi.org/10.3390/rs12162655 https://orcid.org/ 0000-0002-0346-1684 https://orcid.org/ 0000-0002-5619-8525 https://orcid.org/ 0000-0003-3868-8704 https://orcid.org/ 0000-0002-7685-8826 https://orcid.org/ 0000-0003-1561-7583 https://orcid.org/ 0000-0001-6610-3078 https://orcid.org/ 0000-0002-9555-043X https://orcid.org/ 0000-0003-4724-4064 Inglês Acesso Aberto © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). application/pdf MDPI |
institution |
REPOSITORIO UNB |
collection |
REPOSITORIO UNB |
language |
Inglês |
topic |
Monitoramento de safras Imagem multitemporal Aprendizado profundo Aprendizado de máquina Rede neural recorrente |
spellingShingle |
Monitoramento de safras Imagem multitemporal Aprendizado profundo Aprendizado de máquina Rede neural recorrente Castro Filho, Hugo Crisóstomo de Carvalho Júnior, Osmar Abílio de Carvalho, Osmar Luiz Ferreira de Bem, Pablo Pozzobon de Moura, Rebeca dos Santos de Albuquerque, Anesmar Olino de Silva, Cristiano Rosa Ferreira, Pedro Henrique Guimarães Guimarães, Renato Fontes Gomes, Roberto Arnaldo Trancoso Rice crop detection using LSTM, Bi-LSTM, and machine learning models from sentinel-1 time series |
description |
The Synthetic Aperture Radar (SAR) time series allows describing the rice phenological cycle by the backscattering time signature. Therefore, the advent of the Copernicus Sentinel-1 program expands studies of radar data (C-band) for rice monitoring at regional scales, due to the high temporal resolution and free data distribution. Recurrent Neural Network (RNN) model has reached state-of-the-art in the pattern recognition of time-sequenced data, obtaining a significant advantage at crop classification on the remote sensing images. One of the most used approaches in the RNN model is the Long Short-Term Memory (LSTM) model and its improvements, such as Bidirectional LSTM (Bi-LSTM). Bi-LSTM models are more effective as their output depends on the previous and the next segment, in contrast to the unidirectional LSTM models. The present research aims to map rice crops from Sentinel-1 time series (band C) using LSTM and Bi-LSTM models in West Rio Grande do Sul (Brazil). We compared the results with traditional Machine Learning techniques: Support Vector Machines (SVM), Random Forest (RF), k-Nearest Neighbors (k-NN), and Normal Bayes (NB). The developed methodology can be subdivided into the following steps: (a) acquisition of the Sentinel time series over two years; (b) data pre-processing and minimizing noise from 3D spatial-temporal filters and smoothing with Savitzky-Golay filter; (c) time series classification procedures; (d) accuracy analysis and comparison among the methods. The results show high overall accuracy and Kappa (>97% for all methods and metrics). Bi-LSTM was the best model, presenting statistical differences in the McNemar test with a significance of 0.05. However, LSTM and Traditional Machine Learning models also achieved high accuracy values. The study establishes an adequate methodology for mapping the rice crops in West Rio Grande do Sul. |
format |
Artigo |
author |
Castro Filho, Hugo Crisóstomo de Carvalho Júnior, Osmar Abílio de Carvalho, Osmar Luiz Ferreira de Bem, Pablo Pozzobon de Moura, Rebeca dos Santos de Albuquerque, Anesmar Olino de Silva, Cristiano Rosa Ferreira, Pedro Henrique Guimarães Guimarães, Renato Fontes Gomes, Roberto Arnaldo Trancoso |
author_sort |
Castro Filho, Hugo Crisóstomo de |
title |
Rice crop detection using LSTM, Bi-LSTM, and machine learning models from sentinel-1 time series |
title_short |
Rice crop detection using LSTM, Bi-LSTM, and machine learning models from sentinel-1 time series |
title_full |
Rice crop detection using LSTM, Bi-LSTM, and machine learning models from sentinel-1 time series |
title_fullStr |
Rice crop detection using LSTM, Bi-LSTM, and machine learning models from sentinel-1 time series |
title_full_unstemmed |
Rice crop detection using LSTM, Bi-LSTM, and machine learning models from sentinel-1 time series |
title_sort |
rice crop detection using lstm, bi-lstm, and machine learning models from sentinel-1 time series |
publisher |
MDPI |
publishDate |
2021 |
url |
https://repositorio.unb.br/handle/10482/41912 https://doi.org/10.3390/rs12162655 https://orcid.org/ 0000-0002-0346-1684 https://orcid.org/ 0000-0002-5619-8525 https://orcid.org/ 0000-0003-3868-8704 https://orcid.org/ 0000-0002-7685-8826 https://orcid.org/ 0000-0003-1561-7583 https://orcid.org/ 0000-0001-6610-3078 https://orcid.org/ 0000-0002-9555-043X https://orcid.org/ 0000-0003-4724-4064 |
_version_ |
1710449517910818816 |
score |
13.657419 |