当前位置: 首页 > 文章 > 基于RBF神经网络的城市森林碳储量遥感建模与动态变化分析——以南京市为例 林业资源管理 2013 (4) 120-125
Position: Home > Articles > Study on Estimation Model and Dynamic Change of Urban Forest Carbon Storage Based on RBF and RS——A Case Study in Nanjing Forest Resources Management 2013 (4) 120-125

基于RBF神经网络的城市森林碳储量遥感建模与动态变化分析——以南京市为例

作  者:
凌子燕;黄进
单  位:
广西民族大学;广西基础地理信息中心
关键词:
森林碳储量;RBF神经网络;遥感;南京
摘  要:
研究将TM遥感数据的归一化植被指数(NDVI)和短波红外植被指数(SWVI)融入径向基神经网络中,构建了森林碳储量估算模型,并应用该模型反演了南京市不同时期的森林碳储量。结果显示:1)该模型的平均估算精度达到74.62%,比线性回归模型精度更高、拟合更稳定,是一种相对简便、易于操作和准确度高的森林碳储量估算方法;2)南京市的森林碳储量总体分布面积较大,但在区域上分布不太均匀,1988—2005年期间各辖区的森林碳储量均有不同程度的减少,减少率由小到大依次排列为:栖霞区<玄武区<下关区<雨花台区<鼓楼区<白下区<秦淮区<建邺区。
译  名:
Study on Estimation Model and Dynamic Change of Urban Forest Carbon Storage Based on RBF and RS——A Case Study in Nanjing
作  者:
LING Ziyan;HUANG Jin;Geomatics Center of Guangxi;Guangxi University for Nationnalities;
关键词:
carbon storage of forest,RBF network,RS,Nanjing
摘  要:
NDVI and SWVI derived from Landsat TM images are blent into Radial Basis Function to generate an estimation model of forest carbon storage in Nanjing,and this model is compared with Regression Model.The results show that:(1) The precision of Radial Basis Function Model is 74.62%,it's more stable and has higher precision than Regression Model,so it's a relatively simple,easy-to-operate and accurate estimation method for carbon storage of forest;(2) From spatial distribution pattern perspective,the forest carbon storage in Nanjing is distributed extensively,but not even regionally.From time dynamic change perspective,during the period of 1988 to 2005,the forest carbon storage of each district declined in different degrees,the descent rates were listed in a low-to-high order: Qixia,Xuanwu,Xiaguan,Yuhuatai,Gulou,Baixia,Qinhuai and Jianye.

相似文章

计量
文章访问数: 13
HTML全文浏览量: 0
PDF下载量: 1

所属期刊

推荐期刊