基于GIS和神经网络的森林植被分类(英文)

被引：4

作者：

刘旭升 ^{[1
]}

李锋 ^{[2
]}

昝国胜 ^{[1
]}

张晓丽 ^{[3
]}

王军厚 ^{[1
]}

机构：

[1] 国家林业局调查规划设计院

[2] 中国科学院生态环境研究中心

[3] 北京林业大学资源与环境学院

来源：

遥感学报 | 2007年 / 05期

关键词：

遥感; 分类; 森林; 神经网络;

D O I：

暂无

中图分类号：

S757 [森林经理学]; S712 [森林物理学];

学科分类号：

摘要：

本文综述了国际遥感分类研究,使用Landsat7ETM+遥感数据和地理辅助数据,应用BP神经网络方法,将莽汉山林场作为研究区进行了遥感影像的分类研究。比较了BP神经网络分类与最大似然、简单和复杂非监督分类法之间的类型与数量精度。BP神经网络分类的总类型精度是70.5%,总数量精度为84.65%,KAPPA系数是0.6455。结果说明BP神经网络的分类质量优于其他方法,其总的类型精度与其他三种分类方法相比分别增加了10.5%、32%和33%,总的质量精度增加了5.3%。因此,辅以地理参考数据的BP神经网络分类可以作为一种有效的分类方法。

引用

页码：710 / 717

页数：8

共 12 条

[1]

Remote sensing of forested wetlands: application of multitemporal and multispectral satellite imagery to determine plant community composition and structure in southeastern USA[J] . Philip A. Townsend,Stephen J. Walsh.Plant Ecology . 2001 (2)

[2]

Artificial neural networks as a tool in ecological modelling, an introduction[J] . Sovan Lek,J.F. Guégan.Ecological Modelling . 1999 (2)

[3]

Developing an empirical model of phytoplankton primary production: a neural network case study[J] . Michele Scardi,Lawrence W Harding.Ecological Modelling . 1999 (2)

[4] Fuzzy mapping of tropical land cover along an environmental gradient from remotely sensed data with an artificial neural network [J].

Foody G.M. ;

Boyd D.S. .

Journal of Geographical Systems, 1999, 1 (1) :23-35

[5] A technique for monitoring ecological disturbance in tallgrass prairie using seasonal NDVI trajectories and a discriminant function mixture model [J].

Goodin, DG ;

Henebry, GM .

REMOTE SENSING OF ENVIRONMENT, 1997, 61 (02) :270-278

[6]

On the relation between NDVI, fractional vegetation cover, and leaf area index[J] . Toby N. Carlson,David A. Ripley.Remote Sensing of Environment . 1997 (3)

[7]

Artificial neural network approach for modelling and prediction of algal blooms[J] . Friedrich Recknagel,Mark French,Pia Harkonen,Ken-Ichi Yabunaka.Ecological Modelling . 1997 (1)

[8] Mapping tropical forest fractional cover from coarse spatial resolution remote sensing imagery [J].

Foody, GM ;

Lucas, RM ;

Curran, PJ ;

Honzak, M .

PLANT ECOLOGY, 1997, 131 (02) :143-154

[9] Artificial neural networks as empirical models for estimating phytoplankton production [J].

Scardi, M .

MARINE ECOLOGY PROGRESS SERIES, 1996, 139 (1-3) :289-299

[10] LAND-COVER CLASSIFICATION BY AN ARTIFICIAL NEURAL-NETWORK WITH ANCILLARY INFORMATION [J].

FOODY, GM .

INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SYSTEMS, 1995, 9 (05) :527-542

← 1 2 →