Method of national vegetation types identification based on FY-3A mersi data
European Space Agency, (Special Publication) ESA SP(2013)
摘要
Forest distribution mapping is one of the direct comprehensive reports of the achievement in forestry survey. To get the method of national vegetation types identification of China, the 250m FY-3A Medium Resolution Spectral Imager (FY-3A MERSI) data have been selected. The unsupervised classification method, the decision tree classification method and the stratified classification method have been used. It showed that the overall accuracy is 58.29%, and Kappa coefficient is 0.5289 by using the unsupervised classification method; the overall accuracy is 77.45%, and Kappa coefficient is 0.7419 by using the decision tree classification method; and the overall accuracy is 86.14% and Kappa coefficient is 0.8427 the stratified classification method. It showed that the overall accuracy and kappa coefficient by using the Stratified classification method are highest precision than the other two methods'.
更多查看译文
关键词
FY-3A mersi,Stratified classification method,Vegetation type mapping
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要