为了获得不同监测采样间隔对作物生长模型的影响规律,避免现有研究和应用中存在的主观性或随意性,以番茄叶片蒸腾速率和CO2交换率为对象,采用3 种采样间隔数据及2 种常用方法进行建模、预测和比较研究。研究结果显示,在15、30、60 min的监测采样间隔下,番茄叶片蒸腾速率模型和CO2交换率模型的预测误差是不同的,GA-BP神经网络模型的预测能力普遍优于纯二次回归模型,但两者的结论是一致的,即对蒸腾速率和CO2交换率而言,最合适的监测采样间隔分别为30 min和15 min。本研究结果为监测采样间隔的设定、试验数据的选取和建模方法的运用提供依据,对作物模型研究和应用具有重要意义。
Abstract
In order to obtain the impact of different monitoring and sampling intervals on crop model performance, and avoid the subjectivity and randomness in the existing research and application, the transpiration rate and CO2 exchange rate of tomato leaf were modeled by two common methods with three kinds of sampling intervals, then the prediction error of these models were compared. The results showed that the prediction errors of transpiration rate model and CO2 exchange rate model were different respectively with the sampling intervals of 15, 30 and 60 minutes, the prediction ability of the GA-BP neural network model was generally superior to the pure quadratic regression model, but the conclusions were consistent, showing that the most appropriate sampling interval was 30 minutes for transpiration rate model and 15 minutes for CO2 exchange rate model respectively. The results of this study provided the basis for the setting of monitoring and sampling intervals, the selection of experimental data and the application of the modeling methods, which was of great significance for the research and application of crop model.
关键词
作物模型;监测实验;采样间隔;预测误差
{{custom_keyword}} /
Key words
crop model; monitoring experiment; sampling interval; forecasting error
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 曹卫星,朱艳,田永超,等. 作物精确栽培技术的构建与实现[J]. 中国农业科学, 2011, 19: 3955- 3969.
[2] 曹宏鑫,赵锁劳,葛道阔,等. 作物模型发展探讨[J]. 中国农业科学,2011,17:3520-3528.
[3] Jones J W, Hoogenboom G, Porter C H, et al. The DSSAT Cropping System Model[J]. European Journal of Agronomy, 2003, 18(31):235-265.
[4] 马丽丽. 番茄生长模型及日光温室小气候建模的研究[D]. 沈阳农业大学, 2009.
[5] 郭正昊. 北方地区日光温室生态动力学研究[D].吉林大学,2012.
[6] 倪纪恒.温室番茄生长发育模拟模型研究[D].南京农业大学,2005.
[7] 汪小旵. 南方现代化温室小气候模拟及其能耗预测研究[D].南京农业大学,2003.
[8] 于婵. 人工牧草生理生态过程模拟及高效用水灌溉制度研究[D].内蒙古农业大学,2011.
[9] 胡笑涛.温室番茄局部控制灌溉节水调控机制与水分亏缺诊断[D].西北农林科技大学, 2012.
[10] Jiang Zhaohui, Wang Chunsheng, Zhang Jing, Yue Yi, Li Shaowen. Online monitoring and analysis of plant photosynthetic physiology and environmental factors [J]. Applied Mechanics and Materials, 2013, 241:75~80.
[11] 武维华.植物生理学[M].北京:科学出版社, 2008.59-69.
[12] Zhang Jing, Jiang Zhaohui, Wang Chunsheng, Yang Chunhe. Modeling and prediction of CO2 exchange response to environment for small sample size in cucumber [J]. Computers and Electronics in Agriculture, 2014, 108: 39- 45.
[13] 任玉忠,董新光,王志国. 基于灰色关联分析的参考作物腾发量影响因素分析[J]. 中国农学通报,2010,12:376-379.
[14] 张静. 小样本数据作物模型研究[D]. 安徽农业大学, 2015.
[15] 李柏年,吴礼斌.MATLAB数据分析方法[M].北京:机械工业出版社, 2012.
[16] 张德丰.MATLAB神经网络应用设计[M].北京:机械工业出版社, 2011.
[17] 潘昊,王晓勇,陈琼,等. 基于遗传算法的BP神经网络技术的应用[J]. 计算机应用, 2005, 12: 61- 63.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}