| 基于MATLAB神经网络的温室草皮腾发量预测研究 |
| |
| 引用本文： | 李雪,毛罕平,左志宇,张晓东,付为国.基于MATLAB神经网络的温室草皮腾发量预测研究[J].安徽农业科学,2008,36(16):6609-6610. |
| |
| 作者姓名： | 李雪 毛罕平 左志宇 张晓东 付为国 |
| |
| 作者单位： | 江苏大学江苏省现代农业装备与技术重点实验室,江苏镇江,212013 |
| |
| 摘 要： | 目的]明确基于MATLAB的BP神经网络预测温室草皮腾发量的可行性。方法]在9月温室实测气象资料的基础上,对温室内的平均气温、相对湿度、光照强度和草皮日腾发量(ET)进行回归分析,建立了BP网络ET预报模型(BP-ET)。结果]气温、光照强度与草皮腾发量呈显著正相关(P<0.05),相对湿度与草皮腾发量呈显著负相关(P<0.05)。BP神经网络模型具有极高的拟合精度,9月资料检验预报模型的平均相对误差为5.58%,模拟与检验均有很高的拟合精度。BP网络可以用于草皮日腾发量的预测,是对传统草皮日腾发量计算的补充。结论]该研究为气象数据缺测条件下温室草皮日腾发量的估算提供了新思路。
|
| 关 键 词： | 温室 作物蒸腾量 人工神经网络 模型 |
| 文章编号： | 0517-6611(2008)16-06609-02 |
| 修稿时间： | 2008年3月21日 |
Study on the Prediction of Turf Evapotranspiration in the Greenhouse by Using the Neural Network Based on MATLAB |
| |
| LI Xue et al.Study on the Prediction of Turf Evapotranspiration in the Greenhouse by Using the Neural Network Based on MATLAB[J].Journal of Anhui Agricultural Sciences,2008,36(16):6609-6610. |
| |
| Authors: | LI Xue |
| |
| Abstract: | Objective] The research aimed to confirm the feasibility of predicting the turf evapotranspiration by using BP neural network based on MATLAB.Method] On basis of the measured meteorological data in the greenhouse in September,the regression analysis was made on the average temperature, the relative humidity,light intensity in the greenhouse and turf evaportranspiration(ET) to establish ET prediction model of BP network(BP-ET).Result] Temperature and light intensity showed a significantly positive correlation with turf evaportranspiration(P<0.05),while relative humidity showed a significantly negative correlation with turf evaportranspiration(P<0.05).BP neural network model had an extremely high fitting precision.Through testing with the data in September,the average relative error of the prediction model was 5.58% and both stimulating and testing had higher fitting precision.BP network could be used in the prediction of turf evaportranspiration and it was a supplement to traditional calculation of turf evaportranspiration.Conclusion] This research provided a new thought for calculating turf evaportranspiration in the greenhouse under the condictions that the meteorological data was not determined. |
| |
| Keywords: | Greenhouse Crop evapotranspiration Artificial neural network Model |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
