基于遥感数据的太湖蓝藻水华信息识别方法

Extraction methods of cyanobacteria bloom in Lake Taihu based on RS data

2007年太湖大规模蓝藻暴发,再次引起了人们对太湖环境的关注.有效地提取蓝藻水华信息对分析蓝藻动态分布有重要意义,而卫星遥感技术是进行太湖水质监测与保护的措施之一.本文以2007年4月23日CBERS-02星CCD数据为主要的数据源,以NDVI值为测试变量,运用CART算法确定分割阈值,从而通过构建决策树的方法识别蓝藻水华信息,分析其蓝藻水华的提取结果,取得了较好的效果.文中还在GIS技术支持下,提取了2007年5月17日MODIS影像中的蓝藻水华信息.本次研究为以后开展长期的太湖蓝藻水华动态监测提供技术参考.

This year blue algae blooms occurred largely in Lake Taihu, which caused people pay close attention to environment of Lake Taihu once again. It is very important to extract the information of cyanobacteria bloom-forming to analyze the distribution of cyanobacteria bloom and remote sensing is one of measures of monitoring and protecting water quality. In this paper, it takes the CBERS-02 CCD data as a main data source. The information of cyanobacteria bloom was extracted by the method of building decision tree, and with NDVI as the test variable, threshold value was determined based on CART. It obtains better effects according to analyzing the extraction result. The information of cyanobacteria bloom is also extracted from MODIS image of May 17th, 2007. The present study provides technical reference for long-term monitoring cyanobacteria bloom-forming in Lake Taihu.