Assessing the optimal preprocessing steps of MODIS time series to map cropping systems in Mato Grosso, Brazil
The adoption of new cropping practices such as integrated Crop-Livestock systems (iCL) aims at improving the land use sustainability of the agricultural sector in the Brazilian Amazon. The emergence of such integrated systems, based on crop and pasture rotations over and within years, challenges the...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2020-10-01
|
Series: | International Journal of Applied Earth Observations and Geoinformation |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S0303243419311225 |
_version_ | 1811328852155170816 |
---|---|
author | Patrick Calvano Kuchler Agnès Bégué Margareth Simões Raffaele Gaetano Damien Arvor Rodrigo P.D. Ferraz |
author_facet | Patrick Calvano Kuchler Agnès Bégué Margareth Simões Raffaele Gaetano Damien Arvor Rodrigo P.D. Ferraz |
author_sort | Patrick Calvano Kuchler |
collection | DOAJ |
description | The adoption of new cropping practices such as integrated Crop-Livestock systems (iCL) aims at improving the land use sustainability of the agricultural sector in the Brazilian Amazon. The emergence of such integrated systems, based on crop and pasture rotations over and within years, challenges the remote sensing community who needs to implement accurate and efficient methods to process satellite image time series (SITS) in order to come up with a monitoring protocol. These methods generally include a SITS preprocessing step which can be time consuming. The aim of this study is to assess the importance of preprocessing operations such as temporal smoothing and computation of phenological metrics on the mapping of main cropping systems (i.e. pasture, single cropping, double cropping and iCL), with a special emphasis on the iCL class. The study area is located in the state of Mato Grosso, an important producer of agriculture commodities located in the Southern Brazilian Amazon. SITS were composed of a set of 16-day composites of MODIS Vegetation Indices (MOD13Q1 product) covering a one year period between 2014 and 2015. Two widely used classifiers, i.e. Random Forest (RF) and Support Vector Machine (SVM), were tested using five data sets issued from a same SITS but with different preprocessing levels: (i) raw NDVI; (ii) raw NDVI + raw EVI; (iii) smoothed NDVI; (iv) NDVI-derived phenometrics; (v) raw NDVI + phenometrics. Both RF and SVM classification results showed that the “raw NDVI + raw EVI” data set achieved the highest performance (RF OA = 0.96, RF Kappa = 0.94, SVM OA = 0.95, SVM Kappa = 0.93), followed closely by the “raw NDVI” and the “raw NDVI + phenometrics” datasets. The “NDVI-derived phenometrics” alone achieved the lowest accuracies (RF OA = 0.58 and SVM OA = 0.66). Considering that the implementation of preprocessing steps is computationally expensive and does not provide significant gains in terms of classification accuracy, we recommend to use raw vegetation indices for mapping cropping practices in Mato Grosso, including the integrated Crop-Livestock systems. |
first_indexed | 2024-04-13T15:33:27Z |
format | Article |
id | doaj.art-b5a1cb9beac64b82b678a6921a58ab2b |
institution | Directory Open Access Journal |
issn | 1569-8432 |
language | English |
last_indexed | 2024-04-13T15:33:27Z |
publishDate | 2020-10-01 |
publisher | Elsevier |
record_format | Article |
series | International Journal of Applied Earth Observations and Geoinformation |
spelling | doaj.art-b5a1cb9beac64b82b678a6921a58ab2b2022-12-22T02:41:19ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322020-10-0192102150Assessing the optimal preprocessing steps of MODIS time series to map cropping systems in Mato Grosso, BrazilPatrick Calvano Kuchler0Agnès Bégué1Margareth Simões2Raffaele Gaetano3Damien Arvor4Rodrigo P.D. Ferraz5CIRAD, UMR TETIS, 34093 Montpellier, France; UERJ/FEN/DESC/PPGMA, Rio de Janeiro 20559-900, Brazil; Corresponding author at: UERJ/FEN/DESC/PPGMA, Rio de Janeiro 20559-900, Brazil.CIRAD, UMR TETIS, 34093 Montpellier, France; TETIS, Univ Montpellier, CIRAD, INRAE, AgroParisTech, CNRS, 34093 Montpellier, FranceUERJ/FEN/DESC/PPGMA, Rio de Janeiro 20559-900, Brazil; EMBRAPA Solos, Rio de Janeiro 22460-000, BrazilCIRAD, UMR TETIS, 34093 Montpellier, France; TETIS, Univ Montpellier, CIRAD, INRAE, AgroParisTech, CNRS, 34093 Montpellier, FranceCNRS, UMR LETG 6554, Univ Rennes, 35043 Rennes, FranceEMBRAPA Solos, Rio de Janeiro 22460-000, BrazilThe adoption of new cropping practices such as integrated Crop-Livestock systems (iCL) aims at improving the land use sustainability of the agricultural sector in the Brazilian Amazon. The emergence of such integrated systems, based on crop and pasture rotations over and within years, challenges the remote sensing community who needs to implement accurate and efficient methods to process satellite image time series (SITS) in order to come up with a monitoring protocol. These methods generally include a SITS preprocessing step which can be time consuming. The aim of this study is to assess the importance of preprocessing operations such as temporal smoothing and computation of phenological metrics on the mapping of main cropping systems (i.e. pasture, single cropping, double cropping and iCL), with a special emphasis on the iCL class. The study area is located in the state of Mato Grosso, an important producer of agriculture commodities located in the Southern Brazilian Amazon. SITS were composed of a set of 16-day composites of MODIS Vegetation Indices (MOD13Q1 product) covering a one year period between 2014 and 2015. Two widely used classifiers, i.e. Random Forest (RF) and Support Vector Machine (SVM), were tested using five data sets issued from a same SITS but with different preprocessing levels: (i) raw NDVI; (ii) raw NDVI + raw EVI; (iii) smoothed NDVI; (iv) NDVI-derived phenometrics; (v) raw NDVI + phenometrics. Both RF and SVM classification results showed that the “raw NDVI + raw EVI” data set achieved the highest performance (RF OA = 0.96, RF Kappa = 0.94, SVM OA = 0.95, SVM Kappa = 0.93), followed closely by the “raw NDVI” and the “raw NDVI + phenometrics” datasets. The “NDVI-derived phenometrics” alone achieved the lowest accuracies (RF OA = 0.58 and SVM OA = 0.66). Considering that the implementation of preprocessing steps is computationally expensive and does not provide significant gains in terms of classification accuracy, we recommend to use raw vegetation indices for mapping cropping practices in Mato Grosso, including the integrated Crop-Livestock systems.http://www.sciencedirect.com/science/article/pii/S0303243419311225Mato GrossoIntegrated systemsClassificationPhenometricsSmoothingAgricultural intensification |
spellingShingle | Patrick Calvano Kuchler Agnès Bégué Margareth Simões Raffaele Gaetano Damien Arvor Rodrigo P.D. Ferraz Assessing the optimal preprocessing steps of MODIS time series to map cropping systems in Mato Grosso, Brazil International Journal of Applied Earth Observations and Geoinformation Mato Grosso Integrated systems Classification Phenometrics Smoothing Agricultural intensification |
title | Assessing the optimal preprocessing steps of MODIS time series to map cropping systems in Mato Grosso, Brazil |
title_full | Assessing the optimal preprocessing steps of MODIS time series to map cropping systems in Mato Grosso, Brazil |
title_fullStr | Assessing the optimal preprocessing steps of MODIS time series to map cropping systems in Mato Grosso, Brazil |
title_full_unstemmed | Assessing the optimal preprocessing steps of MODIS time series to map cropping systems in Mato Grosso, Brazil |
title_short | Assessing the optimal preprocessing steps of MODIS time series to map cropping systems in Mato Grosso, Brazil |
title_sort | assessing the optimal preprocessing steps of modis time series to map cropping systems in mato grosso brazil |
topic | Mato Grosso Integrated systems Classification Phenometrics Smoothing Agricultural intensification |
url | http://www.sciencedirect.com/science/article/pii/S0303243419311225 |
work_keys_str_mv | AT patrickcalvanokuchler assessingtheoptimalpreprocessingstepsofmodistimeseriestomapcroppingsystemsinmatogrossobrazil AT agnesbegue assessingtheoptimalpreprocessingstepsofmodistimeseriestomapcroppingsystemsinmatogrossobrazil AT margarethsimoes assessingtheoptimalpreprocessingstepsofmodistimeseriestomapcroppingsystemsinmatogrossobrazil AT raffaelegaetano assessingtheoptimalpreprocessingstepsofmodistimeseriestomapcroppingsystemsinmatogrossobrazil AT damienarvor assessingtheoptimalpreprocessingstepsofmodistimeseriestomapcroppingsystemsinmatogrossobrazil AT rodrigopdferraz assessingtheoptimalpreprocessingstepsofmodistimeseriestomapcroppingsystemsinmatogrossobrazil |