Examining rice distribution and cropping intensity in a mixed single- and double-cropping region in South China using all available Sentinel 1/2 images

• Published in: International journal of applied earth observation and geoinformation 2021-09, Vol.101, p.102351, Article 102351
• Main Authors: He, Yingli, Dong, Jinwei, Liao, Xiaoyong, Sun, Li, Wang, Zhipan, You, Nanshan, Li, Zhichao, Fu, Ping
• Format: Article
• Language: English
• Subjects: Cropping intensity; Google Earth Engine; Rice mapping; Sentinel-1/2; Time series
• ISSN: 1569-8432; 1872-826X
• DOI: 10.1016/j.jag.2021.102351

•Optimize sensors and features for identifying early, middle, and late rice.•Generate 10-m cropping intensity map by integrating Sentinel-1 and -2 images.•Single rice cropping dominates the cropping system in the study area in 2017. Paddy rice agriculture in Southern China, especially Hunan Province, has been suffered from soil contamination. Several policies including rice fallow and decreasing cropping intensity have been implemented for food safety here. It is thus important to monitor rice planting area and cropping intensity to understand the effectiveness of those land-use policies. However, it is challenging to map rice planting areas due to the complex cropping systems (mixed single- and double-cropping), persistent cloud covers, small crop fields, let alone cropping intensity. Here we used all the available Sentinel-2 and all-weather Sentinel-1 imagery to generate a time series data cube to extract paddy rice planting areas and the rice cropping intensity in the Changsha, Zhuzhou, and Xiangtan areas, which is a traditional rice-growing region with small farms in China. Specifically, we investigated the performances of different features (i.e., spectral, seasonal, polarization backscatter) by comparing five scenarios with different combinations of sensors and features, and identified the most suitable features for certain rice types (early, middle, and late rice). The random forest classifier was used for the classification in the Google Earth Engine (GEE) platform, and a reference map in 2017 based on visual interpretation on the GaoFen-2 images were used for collecting the training and validation samples. The results showed the combined data from Sentinel-1/2 generally outperformed classifications using only a single sensor (Sentinel-1/2), but the contribution of different sensors to certain rice types varied. The early, middle and late rice with the highest accuracies within the five scenarios had the overall accuracies of 85%, 95%, and 95%, respectively (F1 = 0.55, 0.85, and 0.85). The compositing of different types of rice allowed us to generate the rice cropping intensity map with an overall accuracy of 81%, which to our limited knowledge is the first effort to map cropping intensity at 10-m resolution in such a fragmented subtropical region. The result showed the single cropping dominated the rice cropping system in the study area 88%, which used to be a typical area with double cropping of rice. Our study demonstrates the potential of mappi