|
|||||
|
|
| 基于主成分分析与BP神经网络的参考作物腾发量预测 | |
| 引用本文： | 曹伟,魏光辉,邓丽娟.基于主成分分析与BP神经网络的参考作物腾发量预测[J].节水灌溉,2009(9). |
| 作者姓名： | 曹伟 魏光辉 邓丽娟 |
| 作者单位： | 1. 新疆水利水电科学研究院,新疆,乌鲁木齐,830049 2. 新疆农业大学水利与土木工程学院,新疆,乌鲁木齐,830052 3. 新疆水利水电科学研究院,新疆,乌鲁木齐,830049;新疆农业大学水利与土木工程学院,新疆,乌鲁木齐,830052 |
| 基金项目： | 国家“863”计划(2006AA100218);;国家科技支撑计划:2007BAD38B08;;新疆维吾尔自治区科技攻关和重点科技项目(200633131) |
| 摘 要： | 为解决采用神经网络模型预测参考作物腾发量研究中预测能力不足的问题.将气象因子包括最高、最低和日平均温度、日照时数、气压、水汽压、相对湿度和风速进行主成分分析.提取主成分,建立了基于主成分的三层BP神经网络模型.选取新疆昌吉市气象站2006年3-6月的日气象资料.采用Matlab神经网络工具箱进行模型训练与预测,并以传统BP网络模型作为对照.结果表明,主成分网络模型能够很好地反映诸多影响因子与参考作物腾发量之间的关系,尤其时训练样本以外的验证样本,主成分网络模型具有显著优于传统BP网络模型的识别能力,取得更为可靠的预测结果. |
| 关 键 词： | 主成分分析 BP神经网络 参考作物腾发量 预测能力 |
Estimation Model for Reference Crop Evapotranspiration Based on Principal Components Analysis and BP Neural Network |
|
| CAO Wei , WEI Guang-hui , DENG Li-juan.Estimation Model for Reference Crop Evapotranspiration Based on Principal Components Analysis and BP Neural Network[J].Water Saving Irrigation,2009(9). | |
| Authors: | CAO Wei WEI Guang-hui DENG Li-juan |
| Institution: | 1.Xinjiang Institute of Hydraulic & Hydropower Research;Urumqi 830049;China;2.School of Water Resources & Civil Engineering;Xinjiang Agricultural university;Urumqi 830052;China |
| Abstract: | In order to improve the performance of neural network model for the prediction of reference crop evapotranspiration,principal component analysis is applied to the weather data,including the maximum,minimum and average daily temperature,sunshine duration,air pressure,humidity of exposure field,air relative humidity and wind velocity,and a three-layer BP neural network model is constructed based on the principal components.Based on daily weather data from March 2006 to June 2006 in the Changji city meteorolog... |
| Keywords: | principal component analysis neural network reference crop evapotranspiration prediction ability |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |