Assessing the optimal preprocessing steps of MODIS time series to map cropping systems in Mato Grosso, Brazil

Kuchler Calvano Patrick, Bégué Agnès, Simoes Margareth, Gaetano Raffaele, Arvor Damien, Ferraz Rodrigo P.D.. 2020. Assessing the optimal preprocessing steps of MODIS time series to map cropping systems in Mato Grosso, Brazil. International Journal of Applied Earth Observation and Geoinformation, 92:102150, 6 p.

https://doi.org/10.1016/j.jag.2020.102150

Article de revue ; Article de recherche ; Article de revue à facteur d'impact

Prévisualisation

Version publiée - Anglais
Sous licence

.
1-s2.0-S0303243419311225-main.pdf
Télécharger (1MB) | Prévisualisation

Quartile : Q1, Sujet : REMOTE SENSING

Résumé : 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.

Mots-clés Agrovoc : système de culture, analyse de séries chronologiques, cartographie de l'utilisation des terres, évaluation des technologies

Mots-clés géographiques Agrovoc : Brésil

Mots-clés libres : Integrated systems, Classification, Smoothing, Phenometrics, Timesat

Classification Agris : F08 - Systèmes et modes de culture
U30 - Méthodes de recherche

Champ stratégique Cirad : CTS 2 (2019-) - Transitions agroécologiques

Agences de financement européennes : European Commission

Projets sur financement : (EU) Observatory of the Dynamics of Interactions between Societies and Environment in the Amazon

Auteurs et affiliations