基于Landsat 8影像的地表水体指数提取方法研究——以鄱阳湖为例

Study on the extraction methods of surface water index based on Landsat 8 image:a case study of Poyang Lake

为探究不同水体提取方法在鄱阳湖的提取效果,明确不同水体指数的影响因素和适用范围,以鄱阳湖主湖区Landsat 8遥感影像为基础,构建归一化差异水体指数(MNDWI)、自动水体指数(AWEIsh)、WI2015指数以及浮游藻类指数(FAI)对水体信息进行提取,并采用Sentinel-2 MSI卫星影像人工目视解译的成果验证各项指数提取精度。结果表明:Landsat 8影像能够支持大范围复杂地形水体提取研究,可以为水体提取提供丰富的地物光谱信息。四种水体指数在基于阈值提取的情况下,MNDWI指数提取水体的精度最高为95.50%、Kappa系数为0.870 8,能较好的去除大气影响,适用于各种典型区域、效果最佳。AWEIsh精度仅次于MNDWI指数,且在提取内陆湖泊方面优于MNDWI指数,在后期的研究中对于内陆湖泊范围较大的区域水体提取可以作为补充指数。

In order to investigate the extraction effect of different water extraction methods for Poyang Lake,and to clarify the influencing factors and application range of different water indices,the Modified Normalized Difference Water Index(MNDWI),Automated Water Extraction Index(AWEIsh),Water Index(WI2015),and Floating Algae Index(FAI)were constructed to extract the water body information based on Landsat 8 remote sensing images of the main lake area of Poyang Lake,and the results of manual visual interpretation of Sentinel-2 MSI satellite images were used to verify the extraction accuracy of each index.The results show that Landsat 8 imagery can support large scale complex terrain water extraction studies and can provide rich feature spectral information for water body extraction.Compared with the other four water body indices based on threshold extraction,the MNDWI index has the highest accuracy of 95.50%with the Kappa coefficient of 0.8708 in extracting water bodies.It performes best in eliminating the atmospheric influence and can be applied to various typical areas.The accuracy of AWEIsh is second only to MNDWI index,but it is better than MNDWI index in extracting inland lakes and can be used as a complementary index for the extraction of regional water bodies with relatively large range of inland lakes in future studies.