DUAN Guangjun,ZHAO Jiasong,LIU Zhenyang,et al.Construction of Lettuce Growth Model Based on Growing Degree Days[J].Northern Horticulture,2024,(6):9-16.[doi:10.11937/bfyy.20233874]
基于有效积温的生菜生长模型构建
- Title:
- Construction of Lettuce Growth Model Based on Growing Degree Days
- 文章编号:
- 1001-0009(2024)06-0009-08
- 关键词:
- 生长模型; Logistic回归; 岭回归; 支持向量回归
- 分类号:
- S 636.2
- 文献标志码:
- A
- 摘要:
- 以生菜为试材,采用Logistic回归、岭回归和支持向量回归3种算法,研究了不同算法对生菜生长模型的拟合效果和预测能力,以期更灵活和准确地掌握生菜的生长规律,为后续生菜生产的有效规划、生长预测和增产措施等提供参考依据。结果表明:Logistic回归、岭回归和支持向量回归的生菜生长模型实测值与预测值基于1∶1直线的平均R2分别为0.818、0.897和0.957。支持向量回归对生菜生长的模拟表现最好,其次是岭回归,而Logistic回归表现最差。
- Abstract:
- Taking lettuce as the test material,using three algorithms,Logistic regression,ridge regression and support vector regression,the fitting effect and prediction ability of different algorithms on the lettuce growth model were studied,in order to provide reference for effective planning,growth prediction and yield-increasing measures for subsequent lettuce production.The results showed that the average R2 of the measured values and predicted values of the lettuce growth model of Logistic regression,ridge regression and support vector regression based on the 1∶1 straight line were 0.818,0.897 and 0.957 respectively,and the average RMSE were 27.631,19.505 and 6.901,respectively.Therefore support vector regression performed the best in simulating lettuce growth,followed by ridge regression,and Logistic regression was the worst.
参考文献/References:
[1]陈永快,黄语燕,兰婕,等.基于辐热积的NFT栽培生菜生长模型[J].江苏农业科学,2021,49(19):201-204,215.[2]de WIT C T.Photosynthesis of leaf canopies[M].Wageningen:Centre for Agricultural Publications and Documentation,1965.[3]HEUVELINK E.Dry matter partitioning in tomato:validation of a dynamic simulation model[J].Annals of Botany,1996,77(1):71-80.[4]GIJZEN H,HEUVELINK E,CHALLA H,et al.Hortisim:A model for greenhouse crops and greenhouse climate[J].Acta Horticulturae,1998(456):441-450.[5]高亮之,金之庆,黄耀,等.水稻计算机模拟模型及其应用之一 水稻钟模型:水稻发育动态的计算机模型[J].中国农业气象,1989,10(3):3-10.[6]黄策,王天铎.水稻群体物质生产过程的计算机模拟[J].作物学报,1986,12(1):1-8.[7]殷新佑,戚昌瀚.水稻生长日历模拟模型及其应用研究[J].作物学报,1994,20(3):339-346.[8]高亮之,金之庆,黄耀,等.作物模拟与栽培优化原理的结合-RCSODS[J].作物杂志,1994(3):4-7.[9]陈杨.有效积温与夏玉米生长发育和氮磷钾积累定量化研究[D].北京:中国农业科学院,2021.[10]陈永快,黄语燕,王涛,等.基于有效积温的NFT栽培小白菜生长模型[J].江苏农业科学,2020,48(17):229-233.[11]于志民,康文娟,涂淑萍.基于Logistic、Gompertz模型的圆齿野鸦椿幼苗生长模拟与分析[J].江西农业大学学报,2017,39(6):1187-1195.[12] 陈琦,潘好芹,亓延凤,等.不同LED补光对日光温室黄瓜生长、产量及品质的影响[J].北方园艺,2022(21):50-57.[13] 谷端银,常青,王晓云,等.日光温室秋冬茬不同品种樱桃番茄生长及品质特性研究[J].北方园艺,2022(18):46-51.[14]洪苗,柳平增,张艳,等.基于主要环境因子的设施黄瓜生长模型研究[J].中国农机化学报,2022,43(4):32-37.[15]李德,陈文涛,乐章燕,等.基于随机森林算法和气象因子的砀山酥梨始花期预报[J].农业工程学报,2020,36(12):143-151.[16]曾妍,王迪,赵小娟.基于支持向量回归的关中平原冬小麦估产研究[J].中国农业信息,2019,31(6):10-20.[17]刘小锐,黄成东,祝红伟.叶用莴苣叶面积测定方法的研究[J].中国蔬菜,2020(12):78-81.[18]李书钦,诸叶平,刘海龙,等.冬小麦返青后叶片高度模型构建及三维可视化[J].中国农业科技导报,2017,19(11):59-67.[19]朱尚伟,李景华.岭回归估计的向量参数方法[J].应用概率统计,2018,34(5):501-514.[20]杨楠.岭回归分析在解决多重共线性问题中的独特作用[J].统计与决策,2004(3):14-15.[21]武琼.基于支持向量回归的短时交通流预测方法研究与应用[D].西安:长安大学,2016.[22]殷志奇.基于气象数据的柳州甘蔗产量预测研究[D].柳州:广西科技大学,2021.
相似文献/References:
[1]张涛,任德元,张国桢.“秦冠”苹果果实和叶生长规律的研究[J].北方园艺,2012,36(21):15.
ZHANG Tao,REN De-yuan,ZHANG Guo-zhen.Study on Growth Regular Fruit and Leaf of the ‘Qinguan’ Apple[J].Northern Horticulture,2012,36(6):15.
[2]吕雅辉,周瑾,张亮,等.新型职业农民对子女继承农业意愿的影响因素研究[J].北方园艺,2016,40(04):202.[doi:10.11937/bfyy.201604048]
LYU Yahui,ZHOU Jin,ZHANG Liang,et al.Study on the Influence Factors of the New Type of Professional Farmers’ Willings for Their Children to Inherit Agriculture[J].Northern Horticulture,2016,40(6):202.[doi:10.11937/bfyy.201604048]
[3]焦文献,黄雅涛,张莉莉,等.河南连片特困区农户家庭特征的致贫机制研究[J].北方园艺,2020,44(19):152.[doi:10.11937/bfyy.20194636]
JIAO Wenxian,HUANG Yatao,ZHANG Lili,et al.Study on the Mechanism of Poverty Caused by Family Characteristics of Farmers in Contiguous Poor Areas of Henan Province[J].Northern Horticulture,2020,44(6):152.[doi:10.11937/bfyy.20194636]
备注/Memo
第一作者简介:段光俊(1999-),男,硕士研究生,研究方向为数据挖掘及作物生长模型。E-mail:1952241198@qq.com.责任作者:赵家松(1975-),男,博士,副教授,硕士生导师,现主要从事数据挖掘、人工智能与农业应用等研究工作。E-mail:zhaojiasong@ynau.edu.cn.基金项目:云南省农业基础研究联合专项基金资助项目(202301BD070001-202);云南农业大学博士科研启动基金资助项目(A2032002507)。收稿日期:2023-11-10