Polarimetric decomposition methods for LULC mapping using ALOS L-band PolSAR data in Western parts of Mizoram, Northeast India

Abstract

The rapid advancement of remote sensing and availability of polarimetric SAR (PolSAR) data have facilitated to monitor the land use land cover (LULC) dynamics. In the recent past, polarimetric decomposition theorems are applied widely to perform LULC classification with the help of machine learning techniques. In this study, we utilized ALOS PALSAR-1 L-band quad polarimetric data for performing polarimetric decomposition, textural information extraction, and to generate LULC maps over the western part of Mizoram state, northeast India. The study area comprises three districts, namely Mamit, Lunglei, and Lawngtlai. We adopted two representative full-polarimetric decomposition models: classical model-based Freeman-Durden and Yamaguchi decomposition. These methods decompose the coherency matrix of PolSAR images into surface, double-bounce, and volume scattering. Textural measures, such as variance, contrast, entropy, homogeneity, dissimilarity, and uniformity are also retrieved using grey-level co-occurrence matrix (GLCM) for LULC classification. For LULC classification, we employed a support vector machine classifier and calculated the area statistics of LULC. The outcomes were checked with the help of confusion matrix derived for six classes, such as built-up, deciduous forest, evergreen forest, scrubland, bareland, and waterbody. Each LULC class is separated using the scattering properties of PolSAR images. Results exhibited that Yamaguchi four-component decomposition (overall accuracy 90% and kappa coefficient 0.88) gives relatively better LULC classification results than the Freeman-Durden three-component decomposition (overall accuracy 87% and kappa coefficient 0.84). Use of textural images of GLCM has supported the classification accuracy at par with the Yamaguchi model. Integration of polarimetric information offers a new dimension in LULC classification and produces high accuracy maps. This approach overcomes the limitations of optical data in cloud covering areas, and furthermore, it provides better classification accuracy.

Assessing the performance of machine learning algorithms in Google Earth Engine for land use and land cover analysis: A case study of Muğla province, Türkiye

“…70% of all developed samples (840 points) are used to train the algorithms, while the remaining 30% (360 points) are utilized to validate and evaluate the accuracy of the algorithms. Classification and assessment are performed in GEE, and accuracy Page| 229 metrics are obtained through the standard confusion matrix approach (Cohen, 1960;Parida & Mandal, 2020) based on the validation data.…”

Assessment of the land use classification surrounding a dam in the semi arid of Pernamuco/Brazil from OLI, MUX images and WorldCover data

“…Traditionally, these machine learning algorithms only use spectral information although classi cation accuracy can be improved or evaluated by combining spatial information with spectral information (Parida and Mandal, 2020) or o cial spatial reference data. Therefore, supervised learning techniques have shown great ability to extract spatial information from raw images (Gibril et al 2016).…”

Deep support vector machine for PolSAR image classification

“…GLCM being a renounced feature texture model has found application in several PolSAR image applications. More recently, Parida and Mandal (2020) retrieved the textural measures from a decomposed ALOS L-band PolSAR image in Western parts of Mizoram, Northeast India using the GLCM. Here, we present for the first time the classification of PolSAR imagery using Deep Support Vector Machine (DSVM) based on Gray Level Co-occurrence Matrix (GLCM) texture feature.…”