Short-interval monitoring of land use and land cover change using a time series of RADARSAT-2 polarimetric SAR images

Abstract

There are many illegal land use sites in developing countries that are experiencing a process of rapid urbanization. Short-interval, such as monthly, land use and land cover (LULC) change information is important for detecting and preventing illegal land development at its early stage. Conventional optical remote sensing is limited by weather conditions and has great limitation in collecting images in regions characterized by frequent cloud cover. Radar remote sensing, not affected by clouds, is therefore an effective tool for collecting timely LULC information in these regions. Polarimetric synthetic aperture radar (PolSAR) is a currently advanced radar remote sensing technique. This study explores the potential of PolSAR data in short-interval monitoring of LULC change by using RADARSAT-2 PolSAR images. Monthly LULC changes were extracted from a time series of RADARSAT-2 images by using change vector analysis and post-classification comparison based on object-oriented image analysis. The average detection accuracy, average false alarm rate, and average overall error rate for change detection were 91.29 %, 1.37 %, and 1.97 % respectively. The average overall accuracy and average kappa value for determining types of changes were 72.44 % and 0.68 respectively. The results indicate that it is effective in using a time series of RADARSAT-2 PolSAR images in short-interval monitoring of LULC change, especially in monitoring potential illegal land development.