PALSAR-2/ALOS-2 AND OLI/LANDSAT-8 DATA INTEGRATION FOR LAND USE AND LAND COVER MAPPING IN NORTHERN BRAZILIAN AMAZON

João Arthur Pompeu Pavanelli,Maristela Xaud,Lênio Soares Galvão,Haron Abrahim Magalhães Xaud,João Roberto Dos Santos

doi:10.1590/s1982-21702018000200017

Abstract

Abstract: In northern Brazilian Amazon, the crops, savannahs and rainforests form a complex landscape where land use and land cover (LULC) mapping is difficult. Here, data from the Operational Land Imager (OLI)/Landsat-8 and Phased Array type L-band Synthetic Aperture Radar (PALSAR-2)/ALOS-2 were combined for mapping 17 LULC classes using Random Forest (RF) during the dry season. The potential thematic accuracy of each dataset was assessed and compared with results of the hybrid classification from both datasets. The results showed that the combination of PALSAR-2 HH/HV amplitudes with the reflectance of the six OLI bands produced an overall accuracy of 83% and a Kappa of 0.81, which represented an improvement of 6% in relation to the RF classification derived solely from OLI data. The RF models using OLI multispectral metrics performed better than RF models using PALSAR-2 L-band dual polarization attributes. However, the major contribution of PALSAR-2 in the savannahs was to discriminate low biomass classes such as savannah grassland and wooded savannah.

Highlights

Optical remote sensing has been generally used to map land use and land cover (LULC) changes (Silva et al 2014)
Classification accuracy and Kappa values were lower for PALSAR-2 models than for Operational Land Imager (OLI) models and improved with the combination of optical and Synthetic Aperture Radar (SAR) metrics in hybrid models (Table 3)
This issue had already been reported in the literature, indicating the importance of the Random Forest (RF) parameter of calibration before LULC classification with remote sensing data (Odindi et al 2014)

Summary

Introduction

Optical remote sensing has been generally used to map land use and land cover (LULC) changes (Silva et al 2014). The Finer Resolution Observation and Monitoring of Global Land Cover (FROM-GLC) (Gong et al 2013) and the GlobeLand (Chen et al 2015) are examples of high-resolution global LULC projects. They had limiting results in tropical landscapes, especially in the Amazon, with Kappa values of 0.262 and 0.677, respectively. The fragmentation of tropical landscapes and the subtle transitions between the vegetation types are sources of uncertainties for LULC mapping using optical remote sensing (Laurin et al 2013)

Objectives

Methods

Results

Discussion

Conclusion