| 基于BP神经网络的城市总生态足迹预测研究——以武汉市为例 |
| |
| 引用本文： | 李湘梅,周敬宣.基于BP神经网络的城市总生态足迹预测研究——以武汉市为例[J].环境科学与技术,2007,30(8):68-70. |
| |
| 作者姓名： | 李湘梅 周敬宣 |
| |
| 作者单位： | 华中科技大学环境科学与工程学院,武汉,430074 |
| |
| 摘 要： | 鉴于BP网络在处理非线性复杂系统的优势,以武汉市为研究对象,构建一个10-4-1结构的BP神经网络预测模型,将1978-2002年和2003年的相关数据作为模型的训练和测试样本,以2004年的社会、经济、环境数据作为网络的预测输入,对该年的总生态足迹进行预测。结果表明,BP神经网络预测结果与实际足迹值的相对误差为0.69%,预测精度优于传统的多元回归统计模型。
|
| 关 键 词： | 生态环境 BP神经网络 生态足迹 预测 |
| 文章编号： | 1003-6504（2007）08-0068-03 |
| 修稿时间： | 2006-09-062007-01-08 |
Forecasting of Urban Total Ecological Footprint Based on BP Neural Network-A Case Study of Wuhan |
| |
| LI Xiang-mei,ZHOU Jing-xuan.Forecasting of Urban Total Ecological Footprint Based on BP Neural Network-A Case Study of Wuhan[J].Environmental Science and Technology,2007,30(8):68-70. |
| |
| Authors: | LI Xiang-mei ZHOU Jing-xuan |
| |
| Abstract: | Since eco-environment is a complex system and increase of ecological footprint is propelled by social and economic factors, back propagation (BP) algorithm was introduced to predict urban total ecological footprint in Wuhan. Multi-regression analysis model was also established to evaluate precision of BP neutral prediction model. Results showed that the relative error between value predicted by BP neural network and actual value was 0.69%. BP neural network has a higher precision and better effectiveness than multi-regression analysis. |
| |
| Keywords: | eco-environment BP neural network ecological footprint prediction |
| 本文献已被 维普 万方数据 等数据库收录！ |
