Evaluation of early season mapping of integrated crop livestock systems using Sentinel-2 data.
ABSTRACT. Various approaches were developed considering the need to increase agricultural productivity in cultivated areas without more deforestation, such as the Integrated Crop livestock systems (ICLS). The ICLS could be composed of annual crops followed by pastureland with the presence of cattle. Due to the high temporal dynamic of rotation between crops over the season, monitoring these areas is a big challenge. Also, agricultural organizations worldwide highlight the need for early-season maps for this kind of work. In this context, this study evaluated the potential of open data (Sentinel-2) data to map ICLS areas. The performance of two classifiers was evaluated: one of Machine Learning (random forest) and the other of Deep Learning (LSTM). Three different time windows of data were tested (Entire season, 180 days, and 120 days). Using the RF classifier, it was possible to achieve satisfactory results (Overall accuracy higher than 80%) for the early season (180 days). However, further studies are needed to explain better the lower(when compared to Random Forest) accuracy achieved by LSTM net (0.79 % for 180 days) and compare the results achieved here with results for a study area with different rates of cloud cover.
Main Authors: | , , , , , , , , |
---|---|
Other Authors: | |
Format: | Artigo de periódico biblioteca |
Language: | Ingles English |
Published: |
2022-08-24
|
Subjects: | Agricultura regenerativa, Identificação de culturas, Floresta aleatória, Aprendizado profundo, LSTM, Regenerative agriculture, Crop identification, Random forest, Sensoriamento Remoto, Remote sensing, |
Online Access: | http://www.alice.cnptia.embrapa.br/alice/handle/doc/1145714 https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-1335-2022 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-alice-doc-1145714 |
---|---|
record_format |
koha |
spelling |
dig-alice-doc-11457142022-08-24T19:26:09Z Evaluation of early season mapping of integrated crop livestock systems using Sentinel-2 data. TORO, A. P. S. G. D. WERNER, J. P. S. REIS, A. A. dos ESQUERDO, J. C. D. M. ANTUNES, J. F. G. COUTINHO, A. C. LAMPARELLI, R. A. C. MAGALHÃES, P. S. G. FIGUEIREDO, G. K. D. A. FEAGRI/UNICAMP; FEAGRI/UNICAMP; UNICAMP; JULIO CESAR DALLA MORA ESQUERDO, CNPTIA, FEAGRI/UNICAMP; JOAO FRANCISCO GONCALVES ANTUNES, CNPTIA; ALEXANDRE CAMARGO COUTINHO, CNPTIA; UNICAMP; UNICAMP; FEAGRI/UNICAMP. Agricultura regenerativa Identificação de culturas Floresta aleatória Aprendizado profundo LSTM Regenerative agriculture Crop identification Random forest Sensoriamento Remoto Remote sensing ABSTRACT. Various approaches were developed considering the need to increase agricultural productivity in cultivated areas without more deforestation, such as the Integrated Crop livestock systems (ICLS). The ICLS could be composed of annual crops followed by pastureland with the presence of cattle. Due to the high temporal dynamic of rotation between crops over the season, monitoring these areas is a big challenge. Also, agricultural organizations worldwide highlight the need for early-season maps for this kind of work. In this context, this study evaluated the potential of open data (Sentinel-2) data to map ICLS areas. The performance of two classifiers was evaluated: one of Machine Learning (random forest) and the other of Deep Learning (LSTM). Three different time windows of data were tested (Entire season, 180 days, and 120 days). Using the RF classifier, it was possible to achieve satisfactory results (Overall accuracy higher than 80%) for the early season (180 days). However, further studies are needed to explain better the lower(when compared to Random Forest) accuracy achieved by LSTM net (0.79 % for 180 days) and compare the results achieved here with results for a study area with different rates of cloud cover. Edition of proceedings of the 2022 edition of the XXIVth ISPRS Congress, Nice, France. 2022-08-24T19:26:01Z 2022-08-24T19:26:01Z 2022-08-24 2022 Artigo de periódico The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, v. 43, B3, p. 1335-1340, 2022. http://www.alice.cnptia.embrapa.br/alice/handle/doc/1145714 https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-1335-2022 Ingles en openAccess |
institution |
EMBRAPA |
collection |
DSpace |
country |
Brasil |
countrycode |
BR |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-alice |
tag |
biblioteca |
region |
America del Sur |
libraryname |
Sistema de bibliotecas de EMBRAPA |
language |
Ingles English |
topic |
Agricultura regenerativa Identificação de culturas Floresta aleatória Aprendizado profundo LSTM Regenerative agriculture Crop identification Random forest Sensoriamento Remoto Remote sensing Agricultura regenerativa Identificação de culturas Floresta aleatória Aprendizado profundo LSTM Regenerative agriculture Crop identification Random forest Sensoriamento Remoto Remote sensing |
spellingShingle |
Agricultura regenerativa Identificação de culturas Floresta aleatória Aprendizado profundo LSTM Regenerative agriculture Crop identification Random forest Sensoriamento Remoto Remote sensing Agricultura regenerativa Identificação de culturas Floresta aleatória Aprendizado profundo LSTM Regenerative agriculture Crop identification Random forest Sensoriamento Remoto Remote sensing TORO, A. P. S. G. D. WERNER, J. P. S. REIS, A. A. dos ESQUERDO, J. C. D. M. ANTUNES, J. F. G. COUTINHO, A. C. LAMPARELLI, R. A. C. MAGALHÃES, P. S. G. FIGUEIREDO, G. K. D. A. Evaluation of early season mapping of integrated crop livestock systems using Sentinel-2 data. |
description |
ABSTRACT. Various approaches were developed considering the need to increase agricultural productivity in cultivated areas without more deforestation, such as the Integrated Crop livestock systems (ICLS). The ICLS could be composed of annual crops followed by pastureland with the presence of cattle. Due to the high temporal dynamic of rotation between crops over the season, monitoring these areas is a big challenge. Also, agricultural organizations worldwide highlight the need for early-season maps for this kind of work. In this context, this study evaluated the potential of open data (Sentinel-2) data to map ICLS areas. The performance of two classifiers was evaluated: one of Machine Learning (random forest) and the other of Deep Learning (LSTM). Three different time windows of data were tested (Entire season, 180 days, and 120 days). Using the RF classifier, it was possible to achieve satisfactory results (Overall accuracy higher than 80%) for the early season (180 days). However, further studies are needed to explain better the lower(when compared to Random Forest) accuracy achieved by LSTM net (0.79 % for 180 days) and compare the results achieved here with results for a study area with different rates of cloud cover. |
author2 |
FEAGRI/UNICAMP; FEAGRI/UNICAMP; UNICAMP; JULIO CESAR DALLA MORA ESQUERDO, CNPTIA, FEAGRI/UNICAMP; JOAO FRANCISCO GONCALVES ANTUNES, CNPTIA; ALEXANDRE CAMARGO COUTINHO, CNPTIA; UNICAMP; UNICAMP; FEAGRI/UNICAMP. |
author_facet |
FEAGRI/UNICAMP; FEAGRI/UNICAMP; UNICAMP; JULIO CESAR DALLA MORA ESQUERDO, CNPTIA, FEAGRI/UNICAMP; JOAO FRANCISCO GONCALVES ANTUNES, CNPTIA; ALEXANDRE CAMARGO COUTINHO, CNPTIA; UNICAMP; UNICAMP; FEAGRI/UNICAMP. TORO, A. P. S. G. D. WERNER, J. P. S. REIS, A. A. dos ESQUERDO, J. C. D. M. ANTUNES, J. F. G. COUTINHO, A. C. LAMPARELLI, R. A. C. MAGALHÃES, P. S. G. FIGUEIREDO, G. K. D. A. |
format |
Artigo de periódico |
topic_facet |
Agricultura regenerativa Identificação de culturas Floresta aleatória Aprendizado profundo LSTM Regenerative agriculture Crop identification Random forest Sensoriamento Remoto Remote sensing |
author |
TORO, A. P. S. G. D. WERNER, J. P. S. REIS, A. A. dos ESQUERDO, J. C. D. M. ANTUNES, J. F. G. COUTINHO, A. C. LAMPARELLI, R. A. C. MAGALHÃES, P. S. G. FIGUEIREDO, G. K. D. A. |
author_sort |
TORO, A. P. S. G. D. |
title |
Evaluation of early season mapping of integrated crop livestock systems using Sentinel-2 data. |
title_short |
Evaluation of early season mapping of integrated crop livestock systems using Sentinel-2 data. |
title_full |
Evaluation of early season mapping of integrated crop livestock systems using Sentinel-2 data. |
title_fullStr |
Evaluation of early season mapping of integrated crop livestock systems using Sentinel-2 data. |
title_full_unstemmed |
Evaluation of early season mapping of integrated crop livestock systems using Sentinel-2 data. |
title_sort |
evaluation of early season mapping of integrated crop livestock systems using sentinel-2 data. |
publishDate |
2022-08-24 |
url |
http://www.alice.cnptia.embrapa.br/alice/handle/doc/1145714 https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-1335-2022 |
work_keys_str_mv |
AT toroapsgd evaluationofearlyseasonmappingofintegratedcroplivestocksystemsusingsentinel2data AT wernerjps evaluationofearlyseasonmappingofintegratedcroplivestocksystemsusingsentinel2data AT reisaados evaluationofearlyseasonmappingofintegratedcroplivestocksystemsusingsentinel2data AT esquerdojcdm evaluationofearlyseasonmappingofintegratedcroplivestocksystemsusingsentinel2data AT antunesjfg evaluationofearlyseasonmappingofintegratedcroplivestocksystemsusingsentinel2data AT coutinhoac evaluationofearlyseasonmappingofintegratedcroplivestocksystemsusingsentinel2data AT lamparellirac evaluationofearlyseasonmappingofintegratedcroplivestocksystemsusingsentinel2data AT magalhaespsg evaluationofearlyseasonmappingofintegratedcroplivestocksystemsusingsentinel2data AT figueiredogkda evaluationofearlyseasonmappingofintegratedcroplivestocksystemsusingsentinel2data |
_version_ |
1756028579864379392 |