摘要
土地荒漠化是当今全球面临的重大环境问题之一,它的发生、发展及其逆转是气候、环境和人类社会经济活动综合作用的结果。区域荒漠化信息的提取技术研究是荒漠化研究进一步深入的关键,根据土地荒漠化的遥感探测机理,应用神经网络技术,利用了TM卫星遥感数据中的可见光、热红外和植被指数(NDVI)数据,建立了相应的BP神经网络的土地荒漠化信息的自动提取模型。实验应用表明,基于人工神经网络方法提取土地荒漠化发生的地点和范围等信息,其精度可达到84%。因此,应用人工神经网络方法提取土地荒漠化信息是切实可行的,并具有可推广价值。
Desertification is one of the most serious environment problems in the world today, the generation ,development and reversion of desertification are caused by the results of comprehensive influences from the climatic and environmental change, and human activities. Extracting the information of desertification is one of the key steps in desertification research. An artificial neural network(ANN) method for extracting the information of desertification with TM imagery has been developed.The extraction of the information of desertification is based on the ground's humidity and NDVI. The ANN method uses TM3 TM6 and NDVI as inputs with five nodes in a single hidden layer to model the nonlinear transfer function between the desertification and TM data.The ANN method has been applied to extract the information of desertification in Minqin county of China in 2001.The results have illustrated good performance of the ANN method with a detection accuracy of 84%, and it has show great potential in this field.
出处
《测绘学报》
EI
CSCD
北大核心
2004年第1期58-62,共5页
Acta Geodaetica et Cartographica Sinica
基金
国家科技部重点资助项目(2001DIAI005)
