地理科学 ›› 2005, Vol. 25 ›› Issue (6): 731-736.doi: 10.13249/j.cnki.sgs.2005.06.731

• 论文 • 上一篇    下一篇

基于机器学习规则推理的湿地识别研究

阮仁宗1, 冯学智2, 肖鹏峰2, 沈渭寿3   

  1. 1. 河海大学水文水资源与水利工程科学国家重点实验室, 江苏 南京 210098;
    2. 南京大学城市与资源学系, 江苏 南京 210093;
    3. 国家环境保护总局南京环境科学研究所, 江苏 南京 210042
  • 收稿日期:2004-09-04 修回日期:2005-01-11 出版日期:2005-11-20 发布日期:2005-11-20
  • 基金资助:
    中德合作SILUP二期支持项目。

Identification of Wetland Based on Machine Learning Rule Inferring

RUAN Ren-Zong1, FENG Xue-Zhi2, XIAO Peng-Feng2, SHEN Wei-Shou3   

  1. 1. State Key Laboratory of Hydrology, Water Resources and Hydrallic Engineering, Hohai University, Nanjing, Jiangsu 210098;
    2. Department of Urban and Resources Sciences, Nanjing University, Nanjing, Jiangsu 210093;
    3. Nanjing Institute of Environmental Science, State Environmental Protection Administration, Nanjing, Jiangsu 210042
  • Received:2004-09-04 Revised:2005-01-11 Online:2005-11-20 Published:2005-11-20

摘要: 遥感作为人类获取地表信息最重要的手段之一,对于湿地研究具有重要的价值。文章运用机器学习规则推理的方法克服常规遥感研究方法在湿地研究中的弊端,使分类精度得到很大的提高。与传统的最大似然法相比,分类精度提高了13.51%, 达到了83.81%。基于机器学习规则推理分类,不仅利用了光谱信息,而且利用了纹理信息和坐标信息,并使用了掩膜技术。研究发现,这种方法能使湿地类型以及湿地与高地之间的混淆现象得到有效的克服。

Abstract: Wetland, which lies between land and aquatic systems, is one of the most important systems on the earth, and one of crucial links of matter and energy exchange in the earth systems. Remote sensing, one of the significant methods for the acquisition of the information on the earth surface, is a valuable tool to the researches of wetland. In the paper, the machine learning methodology is used to identify the wetland in order to overcome the shortcomings of traditional methodology in the research of wetland. Compared with traditional classification method, rule-based inferring method has improved the accuracy of classification by 13.81%. In the classification of wetland by using machine learning methodology, not only the spectral features of geo-objects, but also other features such as textural features, location features are used. Moreover, the mask technique is used too. It is proven that the technology can really improve the accuracy of classification of wetland greatly.

中图分类号: 

  • TP79