地理学报 ›› 2000, Vol. 67 ›› Issue (S1): 64-70.doi: 10.11821/xb2000S1011

• 论文 • 上一篇    下一篇

土地覆被的气候预测模型

黄玫1, 李克让1, 李晓兵2, 陈育峰1   

  1. 1. 中国科学院地理科学与资源研究所,北京100101;
    2. 北京师范大学资源与环境研究所,北京100875
  • 收稿日期:2000-07-03 修回日期:2000-09-29 出版日期:2000-12-15 发布日期:2000-12-15
  • 基金资助:
    中国科技部“九五”重中之重项目(96-908-03-03)

Climatic Forecast Models of Land Cover

HUANG Mei1, LI Ke-rang1, LI Xiao-bing2, CHEN Yu-feng1   

  1. 1. Institute of Geographic Sciences and Natural Resources, Chinese Academy of Sciences, Beijing 100101;
    2. Institute of Resources Science, Open Laboratory of Environmental Changes and Natural Disaster, Beijing 100875
  • Received:2000-07-03 Revised:2000-09-29 Online:2000-12-15 Published:2000-12-15
  • Supported by:
    National key project of the National plinth Five Year Plan, No.96-908-03-03

摘要: 在全国挑选了东北、华北、华中、西南、华南、西北、新疆和西藏8个试验区,采用人工神经网络和逐步回归方法,应用温度、降水对植被指数进行预报(气候因子超前土地覆盖特征量24个月).试报结果表明:在对植被指数的预报上,人工神经网络优于逐步回归。同时尝试性的将神经网络预报方法与逐步回归方法结合起来作预报,即应用逐步回归挑选出来的预报因子作为神经网络的外部输入精选因子,进行神经网络模拟预报。研究表明,对神经网络的预报因子进行精选,可事先排除一些干扰信息,对提高神经网络的预报准确率有所帮助。

关键词: 植被指数, 神经网络, 逐步回归

Abstract: Observed data of temperature and precipitation are used to predict Normalization Difference Vegetation index (NDVI) in eight selected areas which is Dongbei, Huabei, Huazhong, Xinan, Huanan, Xibei, Xinjiang and Tibet in China by methods of artificial neural networks and stepwise regression. The climatic factors are 24 months ahead of NDVI. The testing forecast shows that the method of artificial neural networks is much better than that of stepwise regression in prediction of NDVI. Meanwhile above two methods are combined to predict NDVI, that is the factors selected by stepwise regression are used to be the input factors of artificial neural networks in predictions. The result shows that combining the two methods is helpful in improving forecast accuracy.

Key words: normalization difference vegetation index (NDVI), artificial neural networks, stepwise regression

中图分类号: 

  • P467