大沽河口湿地变化的遥感监测

Remote Sensing Monitoring of Wetland Changes in Dagu River Estuary

遥感影像分类是遥感影像应用研究的重点。本文以大沽河口湿地为研究对象,利用2009年到2017年的Landsat ETM+和OLI影像,使用支持向量机分类法对研究区域中的河流、盐田、养殖区、耕地、建设用地、滩涂进行分类,分类结果的总体分类精度达到98%,Kappa系数达到0.98,表明该方法在湿地分类方面具有很大应用潜力。对分类结果的面积进行统计分析并研究其变化原因,结果显示,该区域受人类活动和自然因素双重影响,这九年来建设用地、河流面积分别增加772.27hm^2、75.30hm^2,耕地、养殖区面积分别减少了39.54hm^2、522.95hm^2。

Dagu estuary wetland was studied using Landsat ETM+and OLI images from^2009 to 2017 in this paper and Support Vector Machine classification method was used to classify river,salt field,breeding pool,cultivated field,construction land and beach.The overall accuracy of the results could reach98%,and the highest value of Kappa coefficient was 0.98,which showed the method had great application potential in wetland classification.The areas of the classification results were statistically analyzed and the reasons for the changes were further studied.The results showed that the area was affected by human activities and natural factors.It was found that the areas of construction land and river have increased by 772.27 hm^2 and 75.30 hm^2 respectively,and for cultivated field and breeding pool,they had decreased by 39.54 hm^2 and 522.95 hm^2 respectively in the past nine years.