引用本文:
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
过刊浏览    高级检索
本文已被:浏览 34次   下载 0  
分享到: 微信 更多
基于支持向量机回归的关中平原冬小麦估产研究
曾妍, 王迪
中国农业科学院农业资源与农业区划研究所
摘要:
【目的】小麦在中国是仅次于水稻、玉米的第三大粮食作物,小麦产量估测可为有关部门制定政策和经济计划提供依据,在粮食的宏观调控中发挥重要作用。本文采用支持向量机回归(Support Vector Regression, SVR)方法估测冬小麦产量,为粮食估产研究提供参考。【方法】选取陕西省关中平原的5个市(西安市、宝鸡市、铜川市、渭南市、咸阳市)作为研究区,将2011-2016年研究区内冬小麦4个生育时期(返青期、拔节期、抽穗-灌浆期、乳熟期)的条件植被温度指数(Vegetation Temperature Condition Index, VTCI)、叶面积指数(Leaf Area Index, LAI)和每年的单产数据作为总样本,划分训练集和试验集。基于MATLAB平台和LIBSVM-3.23软件包,建立研究区域冬小麦产量回归预测模型,得到产量预测结果并评价模型精度。【结果】回归模型的决定系数为0.88,平均绝对百分比误差为6.12%,均方根误差336.39 kg?hm-2。【结论】支持向量机回归模型拟合较为理想,有较高的预测精度和较强的泛化能力。回归时的重要参数有惩罚因子C和核参数σ,其中核参数σ对模型精度影响更大。研究表明用该回归模型进行冬小麦产量预测是可行的,支持向量机回归方法在粮食产量预测领域有良好的应用前景。
关键词:  冬小麦产量;支持向量机;预测
DOI:
分类号:
基金项目:中国农业科学院科技创新工程项目
Study on yield prediction of winter wheat in Guanzhong Plain Based on SVR
zengyan, wangdi
Institute of Agricultural Resources and Regional Planning
Abstract:
[Purpose] Wheat is the third largest grain crop after rice and Maize in China. Prediction of wheat yield can provide basis for relevant departments to formulate policies and economic plans, and play an important role in macro-control of grain. Support Vector Regression (SVR) method is used to estimate winter wheat yield, which provides a reference for the study of grain yield estimation. [Method] Five cities in Guanzhong Plain of Shaanxi Province (Xi''an City, Baoji City, Tongchuan City, Weinan City and Xianyang City) were selected as the study area. Vegetation Temperature Condition Index(VTCI)and Leaf Area Index(LAI)of four growth stages (green-turning stage, jointing stage, Heading-Filling stage and milk-ripening stage) of Winter Wheat in the study area from 2011 to 2016 were selected. VTCI, LAI and annual yield data were used as total samples to divide training set and experimental set. Based on the MATLAB platform and LIBSVM-3.23 software package to establish the prediction model of winter wheat yield in the study area, get the output prediction results and evaluate the accuracy of the model. [Result] The determinant coefficient of the regression model was 0.88. The average absolute percentage error was 6.12%. The root mean square error of the model was 336.39kg/hm2. [Conclusion] The regression model of Support Vector Machine (SVM) is ideal, with high prediction accuracy and strong generalization ability. The important parameters in regression are penalty factor C and kernel parameter σ, in which kernel parameter σ has more influence on model accuracy. The results show that it is feasible to use this regression model to predict winter wheat yield, and the support vector machine regression method has a good application prospect in the field of grain yield prediction.
Key words:  winter wheat yield; support vector machines; prediction