基于PCA-BP神经网络的温室番茄光合作用速率预测模型研究
首发时间:2013-05-17
摘要:园艺研究表明,CO2作为光合作用速率的主要原料之一,在番茄作物生长中具有重要作用,合理的施用CO2对番茄产量和品质都有所提高。本文对番茄开花期进行CO2施肥量化研究,为该阶段CO2调控提供参考。在本研究中,采用无线传感器网络系统对温室环境信息进行实时监测,包括空气温度、空气湿度、CO2浓度、土壤温度、土壤湿度、光照强度信息,利用LI-6400XT光合仪测定番茄植株叶片净光合作用速率,叶片的环境状况按照一定的规律进行调控。利用BP神经网络建立单叶净光合作用速率的预测模型,环境信息经过主成分分析后作为BP神经网络的输入参数,光合作用速率作为神经网络的输出参数,最后对预测模型进行性能评估。结果表明,利用PCA-BP神经网络建立的光合作用速率模型所得的预测值和实测值相关系数为0.99,均方根误差为0.288,具有较好的预测效果。另一方面,在一定的环境条件下改变CO2浓度的输入值,得到的光合作用速率的预测曲线与实际曲线变化趋势一致。研究结果表明,该模型可以作为温室番茄CO2施肥量化调控的依据之一。
关键词: 模型 主成分分析 BP神经网络 光合作用速率 番茄
For information in English, please click here
Prediction model of the photosynthetic rate of tomato plants based on principal components analysis and BP neural network under greenhouse condition
Abstract:Horticultural research has shown that the yield and quality of tomato crops are increased with the application of the appropriate amount of carbon dioxide (CO2), which is one of the principal raw material of photosynthetic rate. In this paper, flowering stage of tomato plants was studied to provide CO2 fertilization. In this study, a wireless sensor network system was used to monitor greenhouse environmental parameters, including air temperature, air humidity, CO2 concentration, soil temperature, soil moisture, and light intensity, in real time. An LI-6400XT portable photosynthesis analyzer was used to measure the photosynthetic rate of tomato plants, the environmental information of leaves was controlled according to the setting discipline. The photosynthetic rate prediction models of single leaves were established based on the back-propagation neural network. Environmental information were used as input neurons after processed by principal component analysis, photosynthetic rate as an output neuron. And the performance of the prediction model was evaluated. The prediction results of the models built by PCA-BP showed that the correlation coefficient between the simulated and observed data sets was 0.99, RMSE was 0.288. On the other hand, when different CO2 concentrations were selected as the input to predict the photosynthetic rate, the simulated and observed data exhibited the same trend. This model can be used as the basis of the quantitative regulation of CO2 fertilization to tomato in greenhouse .
Keywords: Model Principal component analysis BP neural network Photosynthetic rate Tomato
论文图表:
引用
No.****
同行评议
共计0人参与
勘误表
基于PCA-BP神经网络的温室番茄光合作用速率预测模型研究
评论
全部评论0/1000