基于SAR影像的广东省垦造水田监测应用研究

垦造水田每年至少种植一次水稻,是垦造水田监管的重点内容。为了实现低成本、高效率监测,本文基于高时序的Sentinel-1A影像水稻识别技术,在广东省垦造水田监测中开展应用,并结合外业实地拍摄照片进行结果验证。选取广东省2020年前验收的垦造水田项目中新增水田为监测对象进行试验。结果显示,早稻识别结果总体精度达85.02%,晚稻识别结果总体精度达90.46%,说明该方法用于判断水稻种植情况是可行的,可有效缩小外业核查范围,提高监测效率。

Study on the application of SAR images in monitoring the build paddy fields in Guangdong province

The top priority of the monitoring the build paddy fields is to cultivate rice at least once a year. In order to realize low-cost and high-efficiency monitoring, the rice recognition technology based on Sentinel-1A images with high revisit is applied in the monitoring of built paddy fields in Guangdong province, and the results are verified by field photos. The results show that the overall accuracy of the identification results of the first rice is 85.02%, and that of the second rice is 90.46%, which indicates that this method is practicable to judge the rice planting situation, and can effectively narrow the field verification scope and improve the monitoring efficiency.