A Comparative Assessment of Machine-Learning Techniques for Land Use and Land Cover Classification of the Brazilian Tropical Savanna Using ALOS-2/PALSAR-2 Polarimetric Images

Remote Sensing

EdsonE. Sano¹  JoséC. Mura²  CláudiaM. Almeida²  FlávioF. Camargo³  Tati Almeida³ 

[1] Embrapa Cerrados, BR-020 km 18, CEP: 73310-970 Planaltina, DF, Brazil;National Institute for Space Research, Av. Dos Astronautas, 1758, CEP: 12227-010 São José dos Campos, SP, Brazil;University of Brasília, Institute of Geosciences, CEP: 70297-400 Brasília, DF, Brazil;

关键词: SAR;    polarimetry;    data mining;    thematic mapping;    Cerrado;   

DOI  :  10.3390/rs11131600

来源: DOAJ

【 摘 要 】

This study proposes a workflow for land use and land cover (LULC) classification of Advanced Land Observing Satellite-2 (ALOS-2) Phased Array type L-band Synthetic Aperture Radar-2 (PALSAR-2) images of the Brazilian tropical savanna (Cerrado) biome. The following LULC classes were considered: forestlands; shrublands; grasslands; reforestations; croplands; pasturelands; bare soils/straws; urban areas; and water reservoirs. The proposed approach combines polarimetric attributes, image segmentation, and machine-learning procedures. A set of 125 attributes was generated using polarimetric ALOS-2/PALSAR-2 images, including the van Zyl, Freeman−Durden, Yamaguchi, and Cloude−Pottier target decomposition components, incoherent polarimetric parameters (biomass indices and polarization ratios), and HH-, HV-, VH-, and VV-polarized amplitude images. These attributes were classified using the Naive Bayes (NB), DT J48 (DT = decision tree), Random Forest (RF), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) algorithms. The RF, MLP, and SVM classifiers presented the most accurate performances. NB and DT J48 classifiers showed a lower performance in relation to the RF, MLP, and SVM. The DT J48 classifier was the most suitable algorithm for discriminating urban areas and natural vegetation cover. The proposed workflow can be replicated for other SAR images with different acquisition modes or for other types of vegetation domains.

【 授权许可】

Unknown