Research on crop classification in Northeast China based on multi-source and multi-temporal SAR Images

Abstract

Crop classification can accurately estimate crop area, structure, and spatial distribution, as well as provide important input parameters for crop yield models. The crop yield information is an important basis for the country to formulate food policies and economic plans, so the study of crop classification is of great significance. Traditional optical remote sensing is susceptible to sunlight and clouds, and Synthetic Aperture Radar (SAR) can be used all-time and all-weather. Compared to single- polarization SAR, full-polarization SAR has more abundant information. In this paper, C-band GF- 3(GaoFen-3) satellite data and multi-temporal Sentinel-1 data were used as data sources. Changchun City in northeastern China is selected as the experimental area and the scattering characteristics of typical crops in this area are analyzed. Firstly, the GF-3 and multi-temporal Sentinel-1 SAR data were preprocessed. Then, polarization decomposition of GF-3 data was performed to obtain three polarization characteristics: scattering angle, entropy and anisotropy (H/α/A). The Supports vector machine (SVM) algorithm was implemented as the classifier. Polarization characteristics, multi-source and multi-temporal SAR were used for classification features. The overall accuracy reached 91.9537%, nearly 10% higher than using full-polarization information alone, and the kappa coefficient was 0.8827. It shows that multi-source and multi-temporal SAR has obvious advantages in crop identification.