Classification of Crops, Pastures, and Tree Plantations along the Season with Multi-Sensor Image Time Series in a Subtropical Agricultural Region
Timely and efficient land-cover mapping is of high interest, especially in agricultural landscapes. Classification based on satellite images over the season, while important for cropland monitoring, remains challenging in subtropical agricultural areas due to the high diversity of management systems...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-02-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/11/3/334 |
id |
doaj-57d146d2f2c74e07a9db4bd9b5633ae5 |
---|---|
record_format |
Article |
spelling |
doaj-57d146d2f2c74e07a9db4bd9b5633ae52020-11-25T01:11:21ZengMDPI AGRemote Sensing2072-42922019-02-0111333410.3390/rs11030334rs11030334Classification of Crops, Pastures, and Tree Plantations along the Season with Multi-Sensor Image Time Series in a Subtropical Agricultural RegionCecília Lira Melo de Oliveira Santos0Rubens Augusto Camargo Lamparelli1Gleyce Kelly Dantas Araújo Figueiredo2Stéphane Dupuy3Julie Boury4Ana Cláudia dos Santos Luciano5Ricardo da Silva Torres6Guerric le Maire7School of Agricultural Engineering, FEAGRI, University of Campinas, UNICAMP, Campinas 13083-875, Sao Paulo, BrazilInterdisciplinary Center on Energy Planning, NIPE, University of Campinas, UNICAMP, Campinas 13083-896, Sao Paulo, BrazilSchool of Agricultural Engineering, FEAGRI, University of Campinas, UNICAMP, Campinas 13083-875, Sao Paulo, BrazilCIRAD, UMR TETIS, F-34398 Montpellier, FranceParis Institute of Technology for Life, Food and Environmental Sciences, AgroParisTech, 75231 Paris, FranceSchool of Agricultural Engineering, FEAGRI, University of Campinas, UNICAMP, Campinas 13083-875, Sao Paulo, BrazilInstitute of Computing, University of Campinas, UNICAMP, Campinas 13083-852, Sao Paulo, BrazilInterdisciplinary Center on Energy Planning, NIPE, University of Campinas, UNICAMP, Campinas 13083-896, Sao Paulo, BrazilTimely and efficient land-cover mapping is of high interest, especially in agricultural landscapes. Classification based on satellite images over the season, while important for cropland monitoring, remains challenging in subtropical agricultural areas due to the high diversity of management systems and seasonal cloud cover variations. This work presents supervised object-based classifications over the year at 2-month time-steps in a heterogeneous region of 12,000 km<sup>2</sup> in the Sao Paulo region of Brazil. Different methods and remote-sensing datasets were tested with the random forest algorithm, including optical and radar data, time series of images, and cloud gap-filling methods. The final selected method demonstrated an overall accuracy of approximately 0.84, which was stable throughout the year, at the more detailed level of classification; confusion mainly occurred among annual crop classes and soil classes. We showed in this study that the use of time series was useful in this context, mainly by including a small number of highly discriminant images. Such important images were eventually distant in time from the prediction date, and they corresponded to a high-quality image with low cloud cover. Consequently, the final classification accuracy was not sensitive to the cloud gap-filling method, and simple median gap-filling or linear interpolations with time were sufficient. Sentinel-1 images did not improve the classification results in this context. For within-season dynamic classes, such as annual crops, which were more difficult to classify, field measurement efforts should be densified and planned during the most discriminant window, which may not occur during the crop vegetation peak.https://www.mdpi.com/2072-4292/11/3/334land-covertime-series analysisrandom forestOBIAsegmentationdecision treeLandsat 7Landsat 8Sentinel-1 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Cecília Lira Melo de Oliveira Santos Rubens Augusto Camargo Lamparelli Gleyce Kelly Dantas Araújo Figueiredo Stéphane Dupuy Julie Boury Ana Cláudia dos Santos Luciano Ricardo da Silva Torres Guerric le Maire |
spellingShingle |
Cecília Lira Melo de Oliveira Santos Rubens Augusto Camargo Lamparelli Gleyce Kelly Dantas Araújo Figueiredo Stéphane Dupuy Julie Boury Ana Cláudia dos Santos Luciano Ricardo da Silva Torres Guerric le Maire Classification of Crops, Pastures, and Tree Plantations along the Season with Multi-Sensor Image Time Series in a Subtropical Agricultural Region Remote Sensing land-cover time-series analysis random forest OBIA segmentation decision tree Landsat 7 Landsat 8 Sentinel-1 |
author_facet |
Cecília Lira Melo de Oliveira Santos Rubens Augusto Camargo Lamparelli Gleyce Kelly Dantas Araújo Figueiredo Stéphane Dupuy Julie Boury Ana Cláudia dos Santos Luciano Ricardo da Silva Torres Guerric le Maire |
author_sort |
Cecília Lira Melo de Oliveira Santos |
title |
Classification of Crops, Pastures, and Tree Plantations along the Season with Multi-Sensor Image Time Series in a Subtropical Agricultural Region |
title_short |
Classification of Crops, Pastures, and Tree Plantations along the Season with Multi-Sensor Image Time Series in a Subtropical Agricultural Region |
title_full |
Classification of Crops, Pastures, and Tree Plantations along the Season with Multi-Sensor Image Time Series in a Subtropical Agricultural Region |
title_fullStr |
Classification of Crops, Pastures, and Tree Plantations along the Season with Multi-Sensor Image Time Series in a Subtropical Agricultural Region |
title_full_unstemmed |
Classification of Crops, Pastures, and Tree Plantations along the Season with Multi-Sensor Image Time Series in a Subtropical Agricultural Region |
title_sort |
classification of crops, pastures, and tree plantations along the season with multi-sensor image time series in a subtropical agricultural region |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-02-01 |
description |
Timely and efficient land-cover mapping is of high interest, especially in agricultural landscapes. Classification based on satellite images over the season, while important for cropland monitoring, remains challenging in subtropical agricultural areas due to the high diversity of management systems and seasonal cloud cover variations. This work presents supervised object-based classifications over the year at 2-month time-steps in a heterogeneous region of 12,000 km<sup>2</sup> in the Sao Paulo region of Brazil. Different methods and remote-sensing datasets were tested with the random forest algorithm, including optical and radar data, time series of images, and cloud gap-filling methods. The final selected method demonstrated an overall accuracy of approximately 0.84, which was stable throughout the year, at the more detailed level of classification; confusion mainly occurred among annual crop classes and soil classes. We showed in this study that the use of time series was useful in this context, mainly by including a small number of highly discriminant images. Such important images were eventually distant in time from the prediction date, and they corresponded to a high-quality image with low cloud cover. Consequently, the final classification accuracy was not sensitive to the cloud gap-filling method, and simple median gap-filling or linear interpolations with time were sufficient. Sentinel-1 images did not improve the classification results in this context. For within-season dynamic classes, such as annual crops, which were more difficult to classify, field measurement efforts should be densified and planned during the most discriminant window, which may not occur during the crop vegetation peak. |
topic |
land-cover time-series analysis random forest OBIA segmentation decision tree Landsat 7 Landsat 8 Sentinel-1 |
url |
https://www.mdpi.com/2072-4292/11/3/334 |
work_keys_str_mv |
AT cecilialiramelodeoliveirasantos classificationofcropspasturesandtreeplantationsalongtheseasonwithmultisensorimagetimeseriesinasubtropicalagriculturalregion AT rubensaugustocamargolamparelli classificationofcropspasturesandtreeplantationsalongtheseasonwithmultisensorimagetimeseriesinasubtropicalagriculturalregion AT gleycekellydantasaraujofigueiredo classificationofcropspasturesandtreeplantationsalongtheseasonwithmultisensorimagetimeseriesinasubtropicalagriculturalregion AT stephanedupuy classificationofcropspasturesandtreeplantationsalongtheseasonwithmultisensorimagetimeseriesinasubtropicalagriculturalregion AT julieboury classificationofcropspasturesandtreeplantationsalongtheseasonwithmultisensorimagetimeseriesinasubtropicalagriculturalregion AT anaclaudiadossantosluciano classificationofcropspasturesandtreeplantationsalongtheseasonwithmultisensorimagetimeseriesinasubtropicalagriculturalregion AT ricardodasilvatorres classificationofcropspasturesandtreeplantationsalongtheseasonwithmultisensorimagetimeseriesinasubtropicalagriculturalregion AT guerriclemaire classificationofcropspasturesandtreeplantationsalongtheseasonwithmultisensorimagetimeseriesinasubtropicalagriculturalregion |
_version_ |
1725171538045435904 |