张掖日光温室最低温度预报模型的主成分回归法构建

白青华,王惟晨

中国农学通报. 2015, 31(32): 223-228

PDF(1467 KB)
PDF(1467 KB)
中国农学通报 ›› 2015, Vol. 31 ›› Issue (32) : 223-228. DOI: 10.11924/j.issn.1000-6850.casb15060118
资源 环境 生态 土壤 气象

张掖日光温室最低温度预报模型的主成分回归法构建

  • 白青华1,2,王惟晨3
作者信息 +

Modeling of the Lowest Temperature Forecast in the Sunlight Greenhouse in Zhangye Based on Principal Component Regression

  • Bai Qinghua1,2, Wang Weichen3
Author information +
History +

摘要

为了有效预报日光温室内部最低温度，减弱低温冷害对设施农业生产的影响。利用张掖日光温室内小气候数据及室外气象观测资料，选取8个影响日光温室最低温度的气象因子进行相关分析和统计检验的多重共线性诊断，应用主成分回归方法建立日光温室最低温度预报模型，并用模型模拟值与温室最低温度实测值比较对模型精度进行检验。结果表明：气象因子X1、X2、X4、X6、X7、X8间存在共线性的问题。通过主成分分析综合提取了3个主成分代替原来的8个变量，建立的温室最低温度预报模型通过α=0.01水平显著性检验，且模型精度检验表明，不同天气条件（晴天、少云—多云、阴天）的模拟值和实测值间R2在0.81~0.89之间，RMSE在0.90~1.16℃之间；不同时段（12月—次年2月）的模拟值和实测值间R2在0.82~0.89之间，RMSE在0.94~1.13℃之间。

Abstract

The paper aims to forecast the lowest temperature in the sunlight greenhouse effectively, reduce impact of chilling damage on facility agriculture production. Based on the data of sunlight greenhouse microclimate and meteorological observation outside the greenhouse, 8 meteorological factors which affected the lowest temperature in the sunlight greenhouse were selected and diagnosed through correlation and statistic test. Then a model for forecasting the lowest temperature of sunlight greenhouse was established by using of principal component regression method. The accuracy of model was verified by comparing model simulated values and actual values of the lowest temperature inside greenhouse. The results showed that collinearity existed among X1, X2, X4, X6, X7 and X8. The former 3 principal components could stand for 8 variables, and the regression equation passed the significance test (α=0.01). The regression coefficients properties of principal component regression equation were consistent with the results of correlation analysis, which made the unreasonable symbols of regression coefficients in the least square estimation reasonable. Model precision analysis showed that the R2 was 0.81-0.89 and the RMSE was 0.90-1.16℃ under different weather conditions; the R2 was 0.82-0.89 and the RMSE was 0.94-1.13℃ at different times.

关键词

日光温室；最低温度；主成分回归；预报模型

Key words

sunlight greenhouse; the lowest temperature; principal component regression; forecast model

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用
白青华,王惟晨. 张掖日光温室最低温度预报模型的主成分回归法构建. 中国农学通报. 2015, 31(32): 223-228 https://doi.org/10.11924/j.issn.1000-6850.casb15060118
Bai Qinghua and Wang Weichen. Modeling of the Lowest Temperature Forecast in the Sunlight Greenhouse in Zhangye Based on Principal Component Regression. Chinese Agricultural Science Bulletin. 2015, 31(32): 223-228 https://doi.org/10.11924/j.issn.1000-6850.casb15060118

参考文献

[1] 李建设,高艳明.宁夏南部干旱半干旱地区设施农业可持续发展对策探讨[J].农业科学研究,2009,30(1):59-62.
[2] 李美荣,刘映宁,赵军,等.陕西省关中地区大棚蔬菜低温冻害预报服务方法[J].干旱地区农业研究,2007,25(5):204-207,231.
[3] 王琼,杜成华,周连科.影响大棚蔬菜的气象灾害变化特点及对策[J].气象科技,2008,36(4):458-461.
[4] 关福来,杜克明,魏瑞江,等.日光温室低温寡照灾害监测预警系统设计[J].中国农业气象,2009,30(4):601-604.
[5] 李德,张学贤,祁宦,等.宿州日光温室内部最高和最低气温的预报模型[J].中国农业气象,2013,34(2):170-178.
[6] 袁静,李树军,崔建云,等.山东寿光冬季日光温室内温度变化特征及低温预报[J].中国农学通报,2012,28(3):300-304.
[7] 金志凤,符国槐,黄海静,等.基于BP神经网络的杨梅大棚内气温预测模型研究[J].中国农业气象,2011,32(3):362-367.
[8] 李倩,申双和,曹雯,等.南方塑料大棚冬春季温湿度的神经网络模拟[J].中国农业气象,2012,33(2):190-196.
[9] 张文彤.SPSS统计分析高级教程[M].北京:高等教育出版社,2004:92-93,114,128,130.
[10] 陈玲燕.多重共线性下的线性回归方法综述[J].市场研究,2008,(4):39-41．
[11] 刘国旗.多重共线性的产生原因及其诊断处理[J].合肥工业大学学报:自然科学版,2001,24(4):607-610.
[12] 魏新光,王密侠,张倩.基于主成分分析的灌区参考作物蒸发蒸腾量预测模型研究[J].节水灌溉,2011(1):29-31.
[13] 曹银贵,周伟,王静,等.基于主成分分析与层次分析的三峡库区耕地集约利用对比[J].农业工程学报,2010,26(4):291-296.
[14] 潘怀兵.基于主成分分析法的沥青路面使用性能评价[J].重庆交通大学学报:自然科学版,2010,29(6):888-890.
[15] 中国气象局.QX/T 45—2007地面气象观测规范第1部分:总则[S].北京:气象出版社,2007:1-7.
[16] 曲继松,张丽娟,冯海萍,等.宁夏干旱风沙区夯土砖土复合墙体日光温室保温性能初步研究[J].西北农业学报,2010,19(1):158-163.
[17] 张国林,宗英飞,王吉宏.辽西日光温室温度变化规律及温度预测模型[J].中国农学通报,2013,29(23):117-122.
[18] 马雄威.线性回归方程中多重共线性诊断方法及其实证分析[J].华中农业大学学报:社会科学版,2008(2):78-81,85.
[19] 陶瑛,卢立新.主成分分析法在气调包装果蔬质量评价中的应用[J].包装工程,2005,26(1):8-9,16.
[20] 唐启义,冯明光,等.实用统计分析及计算机处理平台[M].北京:中国农业出版社,1997.
[21] 孙华,鞠洪波,张怀清,等.三种回归分析方法在Hyperion影像LAI反演中的比较[J].生态学报,2012,32(24):7781-7790.
[22] Efron B, Gong G. A leisurely look at the bootstrap, the jackknife, and cross-validation[J].The American Statistician,1983,37(1):36-48.
[23] 刘克,赵文吉,郭逍宇等,.基于湿地植物光谱的水体总氮估测[J].生态学报,2012,32(8):2410-2419.
[24] 罗文海,万巧云,高永.主成分回归分析与多元线性回归的对比研究[J].数理医药学杂志,2003,16(2):140-143.
[25] 杨坚,童华荣,贾利蓉.豆腐乳感官和理化品质的主成分分析[J].农业工程学报,2002,18(2):131-135.
[26] 陈斐,杨沈斌,申双和,等.基于主成分回归法的长江中下游双季早稻相对气象产量模拟模型[J].中国农业气象,2014,35(5):522-528.
[27] Yang S B, Zhao X Y, Li B B, et al. Interpreting RADARSAT-2 quad-polarization SAR signatures from rice paddy based on experiments[J].Geoscience and Remote Sensing Letters,IEEE,2012,9(1):65-69.
[28] Kebede Gurmessa T, Bardossy A. A principal component regression approach to simulate the bedevolution of reservoirs[J].Journal of Hydrology,2009,368(1-4):30-41.
[29] 李国师,王海东,杨守邦,等.日光温室最低气温的预测预调控[J].中国农业气象,1994,15(6):26-28.
[30] 王孝卿,李楠,薛晓萍.寿光日光温室小气候变化规律及模拟方法[J].中国农学通报,2012,28(10):236-242.
[31] 魏瑞江,王春乙,范增禄.石家庄地区日光温室冬季小气候特征及其与大气候的关系[J].气象,2010,36(1):97-103.
PDF(1467 KB)

15

Accesses

0

Citation

Detail
段落导航
相关文章

/

〈 〉