基于最小二乘支持向量机模型预测田面糙率  

Field Roughness Prediction Based on Least Square Support Vector Machine Models

作　　者：李建文[1] 郭向红[1] 孙西欢[1] 马娟娟[1] 

机构地区：[1]太原理工大学水利科学与工程学院,山西太原030024

出　　处：《节水灌溉》2015年第1期1-3,共3页Water Saving Irrigation

基　　金：国家自然科学基金资助项目(51109154);教育部博士点基金项目(20111402120006);山西省青年科技研究基金资助项目(2012021026-2);山西省科技攻关项目(20110311018-1);山西省高等学校创新人才支持计划资助

摘　　要：田面糙率是影响地面灌溉质量的重要参数。基于最小二乘支持向量机建立了两类4个田面糙率预测模型,并进行了验证。结果表明第一类模型预测值(即作物地采用LSSVM-N-I3、裸地采用LSSVM-N-I1,翻耕地采用LSSVM-N-I2)相对误差最大值为9.7%;第二类模型预测值(即LSSVM-N-II模型)相对误差最大值为10.5%,由此可见两类模型都具有较高的预测精度,可以用于田面糙率的预测。Field roughness is a prime parameter affecting the quality of surface irrigation.In this paper,based on least-square support vector machine（LSSVM）,four prediction models of field roughness in two classes are established and verified.The results show that the relative prediction errors among the first class models（adopting the model of LSSVM-N-I3 for cropland,LSSVM-N-I2 for ploughed land,and LSSVM-N-I1 for bareland）are no more than 9.7%,while that among the second class models（adopting the model of LSSVM-N-II for all the three kinds of fields）have the maximum value of 10.5%.Thus,both the two class models manifest adequate precision and can be used for the field roughness estimation of surface irrigation.

关 键 词：最小二乘支持向量机 田面糙率 预测模型 

分 类 号：S152.7[农业科学—土壤学]