KNOWLEDGE BASED CLASSIFIER BASED ON BACKSCATTERING COEFFICIENT FOR MONITORING THE CROP GROWTH ANALYSIS USING MULTI-TEMPORAL IMAGES OF SPACE-BORNE SYNTHETIC APERTURE RADAR (SAR) SENSORS

Abstract. Space-based observation of crops and agro-system on the Earth surface is one of the most important applications of remote sensing using the sensors in optical and microwave spectrum to assess the crop growth for decision making for developing crop information and management system. Remote sensing technology provides scalable and reliable information in respect of rice crop grown area, its crop growth and prediction of crop yield due to acquisition of satellite imagery during the revisit of the orbit by space-borne sensors in optical and microwave spectrum. Synthetic Aperture Radar has the advantages of all-weather, day and night imaging, canopy penetration, and high-resolution capabilities, which makes Space-borne SAR sensors as an effective system for monitoring crop growth, crop classification and mapping of crop area based on the crop canopy interaction of SAR signals due to backscattering coefficients of the earth surface. SAR data from ERS-1/2 SAR, ENVISAT ASAR, ALOS-1/2 PALSAR, Radarsat-1/2 SAR, TerraSAR, COSMO-SkyMed, and Sentinel-1 have been used by various researchers for identification and analysis of rice crop growth based on the backscattering values in different regions of Asia and European region, where backscattered image depends of various earth surface and SAR sensors parameters. In this paper, knowledge based classifier using SAR images of existing space-borne-SAR sensors have been developed based on modeling of SAR backscattering coefficients in C-band and X-band for monitoring the rice crop growth and its analysis using multi-temporal and multi-frequency- SAR sensors data.