高粱产量预测模型研究——以屯留区为例  

Prediction Model of Sorghum Production:An Example of Tunliu District

作　　者：赵汝男 杨华[1] 徐民孜 杨怀卿[1] Zhao Runan;Yang Hua;Xu Minzi;Yang Huaiqing(College of Information Science and Engineering,Shanxi Agricultural University,Jinzhong Shanxi 030801;College of Engineering,Shanxi Agricultural University,Jinzhong Shanxi 030801)

机构地区：[1]山西农业大学信息科学与工程学院,山西晋中030801 [2]山西农业大学工学院,山西晋中030801

出　　处：《中国农学通报》2020年第14期28-33,共6页Chinese Agricultural Science Bulletin

基　　金：国家自然基金“物联网温室环境控制系统随机模型建立及鲁棒控制研究”(31671571)。

摘　　要：研究屯留区高粱产量对气候环境条件的响应,探讨气候因子与高粱产量的关系,为屯留区高粱高效生产提供理论和技术参考。首先,通过粒子群优化算法对指数平滑系数进行优化,进而运用三次指数平滑法将高粱产量分解成趋势产量与气象产量2部分。其次,采用灰色绝对关联法得出对高粱气象产量影响较大的气候因子。最后,对屯留区2004-2017年高粱实际产量进行多元线性回归模型拟合,并利用2018年高粱实际产量对其模型进行验证。结果表明:影响高粱产量的主要气候因子有5月降雨量、5月光照时长、6月平均相对湿度、6月降雨量、7月降雨量、7月光照时长、8月降水量、9月光照时长。2018年高粱产量验证多元线性回归模型的精确度为81.06%,表明该模型能相对准确地拟合屯留区的高粱产量,可为高粱产量的准确预测提供了方法借鉴。To study the response of sorghum production to climate and environmental conditions in Tunliu District we explore the relationship between climatic factors and sorghum yield to provide theoretical and technical references for efficient production of sorghum.Firstly,the exponential smooth factor coefficient was optimized by the particle swarm optimization,and then the sorghum production was decomposed into two parts:trend production and meteorological production by the exponential smoothing for three times.Secondly,the absolute grey relational analysis was used to obtain the climate factors which had great influence on the meteorological production of sorghum,Finally,the multivariable linear regression model was fitted to the actual sorghum production in Tunliu District from 2004 to 2017.The model was verified by using the actual sorghum production in 2018.The results showed that the main climatic factors that affecting sorghum production were rainfall and duration of light in May,average relative humidity and rainfall in June,rainfall and duration of light in July,precipitation in August,and duration of light in September.In 2018,the accuracy of the multivariable linear regression model for sorghum production verification was verified to be 81.06%,which indicated that the model could fit the sorghum production in Tunliu District relatively accurately,and provided a method for precise prediction of sorghum production.

关 键 词：气候 产量 三次指数平滑法 粒子群优化算法 灰色绝对关联 多元线性回归 

分 类 号：S162.5[农业科学—农业气象学]