Cropland Mapping Using Sentinel-1 Data in the Southern Part of the Russian Far East

Abstract

Crop identification is one of the most important tasks in digital farming. The use of remote sensing data makes it possible to clarify the boundaries of fields and identify fallow land. This study considered the possibility of using the seasonal variation in the Dual-polarization Radar Vegetation Index (DpRVI), which was calculated based on data acquired by the Sentinel-1B satellite between May and October 2021, as the main characteristic. Radar images of the Khabarovskiy District of the Khabarovsk Territory, as well as those of the Arkharinskiy, Ivanovskiy, and Oktyabrskiy districts in the Amur Region (Russian Far East), were obtained and processed. The identifiable classes were soybean and oat crops, as well as fallow land. Classification was carried out using the Support Vector Machines, Quadratic Discriminant Analysis (QDA), and Random Forest (RF) algorithms. The training (848 ha) and test (364 ha) samples were located in Khabarovskiy District. The best overall accuracy on the test set (82.0%) was achieved using RF. Classification accuracy at the field level was 79%. When using the QDA classifier on cropland in the Amur Region (2324 ha), the overall classification accuracy was 83.1% (F1 was 0.86 for soybean, 0.84 for fallow, and 0.79 for oat). Application of the Radar Vegetation Index (RVI) and VV/VH ratio enabled an overall classification accuracy in the Amur region of 74.9% and 74.6%, respectively. Thus, using DpRVI allowed us to achieve greater performance compared to other SAR data, and it can be used to identify crops in the south of the Far East and serve as the basis for the automatic classification of cropland.

Associations between Surface Deformation and Groundwater Storage in Different Landscape Areas of the Loess Plateau, China

“…Then, the interferogram was generated (Figure 2b,c, taking the fifth image position as an example). Taking the first scene image of each orbit in January 2020 as the super main image, 83,85,84,86,89,87,89,84,79,85, and 87 interference pairs were generated, respectively. After eliminating the interferograms with poor coherence, a multi-view coefficient of 1:5 was set in the range and azimuth directions to improve the processing interference quality.…”

“…In this study, the time interval of the images was in the range of 24~36 days, and the lower image coverage reduces the image coherence and has an impact on the accuracy of surface deformation monitoring [84]. Due to the limitation of satellite orbit and lifetime, Sentinel-1B images could not be acquired in the Loess Plateau region to obtain three-dimensional surface deformation [85]. The radar lineof-sight direction is not exactly perpendicular to the surface, and even the nearest neighbor method still has some errors.…”