基于随机森林算法构建白眉野草螟监测预警模型
|
摘要
为科学防治白眉野草螟Agriphila aeneociliella,以16种气象因子为自变量,以白眉野草螟发生程度为因变量,采用随机森林算法构建白眉野草螟的监测预警模型,并利用构建的模型对2010—2016年影响鲁东地区白眉野草螟发生程度的关键气象因子进行分析。结果表明,当特征值为9,决策树数量为400时,白眉野草螟监测预警模型的袋外估计错误率最低,为17.88%,轻度发生和重度发生的错误率分别为17.58%和18.18%。利用测试数据检验模型,模型错误率为20.00%。通过所构建的模型分析显示影响鲁东地区白眉野草螟发生程度的关键气象因子为平均水汽压、日最低气温、平均气温和日最高气温,其Gini值分别为18.82、14.84、13.67和9.30。
In order to control eastern grass veneer Agriphila aeneociliella scientifically, the random forest algorithm was used to construct a monitoring and forecasting model, in which 16 meteorological factors were used as independent variables and the degree of occurrence of A. aeneociliella was used as dependent variable. The model was then used to analyze the key meteorological factors which affected the occurrence of A. aeneociliella in eastern Shandong from 2010 to 2016. The results showed that, when the number of eigenvalues was nine, and the number of decision trees was 400, the least estimated error rate of the out-of-bag estimation of the model was 17.88%, and the point error rate of low and severe occurrence was 17.58% and 18.18%, respectively. The error rate of the model was 20.00% when tested by the testing data. The constructed model showed that the key meteorological factors affecting the occurrence degree of A. aeneociliella were average water vapor pressure, daily minimum temperature; average temperature and daily maximum temperature. Their Gini values were 18.82, 14.84, 13.67 and 9.30,respectively.
In order to control eastern grass veneer Agriphila aeneociliella scientifically, the random forest algorithm was used to construct a monitoring and forecasting model, in which 16 meteorological factors were used as independent variables and the degree of occurrence of A. aeneociliella was used as dependent variable. The model was then used to analyze the key meteorological factors which affected the occurrence of A. aeneociliella in eastern Shandong from 2010 to 2016. The results showed that, when the number of eigenvalues was nine, and the number of decision trees was 400, the least estimated error rate of the out-of-bag estimation of the model was 17.88%, and the point error rate of low and severe occurrence was 17.58% and 18.18%, respectively. The error rate of the model was 20.00% when tested by the testing data. The constructed model showed that the key meteorological factors affecting the occurrence degree of A. aeneociliella were average water vapor pressure, daily minimum temperature; average temperature and daily maximum temperature. Their Gini values were 18.82, 14.84, 13.67 and 9.30,respectively.
引文
Chi BJ,Zheng X,Liang XC,Liu Y.2016.Temperature-dependent demography of Agriphila aeneociliella(Lepidoptera:Crambidae),a new insect pest of wheat in China.Agricultural and Forest Entomology,18(3):189-197
Dong SS,Huang ZX.2013.A brief theoretical overview of random forests.Journal of Integration Technology,2(1):1-7(in Chinese)[董师师,黄哲学.2013.随机森林理论浅析.集成技术,2(1):1-7]
Fang KN,Wu JB,Zhu JP,Xie BC.2011.A review of random forest methods.Statistics&Information Forum,26(3):32-38(in Chinese)[方匡南,吴见彬,朱建平,谢邦昌.2011.随机森林方法研究综述.统计与信息论坛,26(3):32-38]
Genuer R,Poggi JM,Tuleau-Malot C,Villa-Vialaneix N.2017.Random forests for big data.Big Data Research,9:28-46
Iverson LR,Prasad AM,Matthews SN,Peters M.2008.Estimating potential habitat for 134 eastern US tree species under six climate scenarios.Forest Ecology and Manage,254:390-406
Ji YC,Qin M,Wu LF,Chen XL,Zhang RZ.2014.Potential distribution of two wheat pests,Agriphila aeneociliella and A.vulgivagella,in China.Chinese Journal of Applied Entomology,51(1):271-277(in Chinese)[季英超,秦萌,吴立峰,陈小龙,张润志.2014.二种危害小麦的草螟在中国的适生区.应用昆虫学报,51(1):271-277]
Lai CG,Chen XH,Zhao SW,Wang ZL,Wu SX.2015.A flood risk assessment model based on random forest and its application.Journal of Hydraulic Engineering,46(1):58-66(in Chinese)[赖成光,陈晓宏,赵仕威,王兆礼,吴旭树.2015.基于随机森林的洪灾风险评价模型及其应用.水利学报,46(1):58-66]
Li L,Mou SM,Lin ZQ.2017.Application of random forest in forecasting cotton aphid pest grade.Anhui Agricultural Science Bulletin,23(1):18-20(in Chinese)[李磊,牟少敏,林中琦.2017.随机森林在棉蚜虫害等级预测中的应用.安徽农学通报,23(1):18-20]
Li XH.2013.Using“random forest”for classification and regression.Chinese Journal of Applied Entomology,50(4):1190-1197(in Chinese)[李欣海.2013.随机森林模型在分类与回归分析中的应用.应用昆虫学报,50(4):1190-1197]
Liu MC,Jiang JF,Shi ZJ,Tang JL,Xu SH.2009.Analysis of meteorological factors and forecast of population dynamic changes of wheat aphid.Chinese Journal of Agrometeorology,30(3):440-444(in Chinese)[刘明春,蒋菊芳,史志娟,唐峻岭,徐生海.2009.小麦蚜虫种群消长气象影响成因及预测.中国农业气象,30(3):440-444]
Peng H.2014.Study on growth development and control of a wheat pest:Agriphila aeneociliella.Master Thesis.Beijing:Chinese Academy of Agricultural Sciences(in Chinese)[彭赫.2014.小麦害虫白眉野草螟的生长发育与防治研究.硕士学位论文.北京:中国农业科学院]
Qu XF.2005.Grading the occurrences of meadow moth(Loxostege sticticalis L.).China Plant Protection,25(8):8-11(in Chinese)[屈西峰.2005.草地螟发生程度的划分.中国植保导刊,25(8):8-11]
Shi LJ,Lu J.2017.Automatic measurement method for maize ear development degree based on random forest.Transactions of the Chinese Society for Agricultural Machinery,48(1):169-174(in Chinese)[石礼娟,卢军.2017.基于随机森林的玉米发育程度自动测量方法.农业机械学报,48(1):169-174]
Si LL,Cao KQ,Liu JP,Yang JY,Zhen WC.2006.Establishment of a real-time monitoring and forecasting system on main crop diseases and pests of China based on GIS.Journal of Plant Protection,33(3):282-286(in Chinese)[司丽丽,曹克强,刘佳鹏,杨军玉,甄文超.2006.基于地理信息系统的全国主要粮食作物病虫害实时监测预警系统的研制.植物保护学报,33(3):282-286]
Tang CC,Huang WJ,Luo JH,Liang D,Zhao JL,Huang LS.2015.Forecasting wheat aphid with remote sensing based on relevance vector machine.Transactions of the Chinese Society of Agricultural Engineering,31(6):201-207(in Chinese)[唐翠翠,黄文江,罗菊花,梁栋,赵晋陵,黄林生.2015.基于相关向量机的冬小麦蚜虫遥感预测.农业工程学报,31(6):201-207]
Wang LA,Ma C,Zhou XD,Zi Y,Zhu XK,Guo WS.2015.Estimation of wheat leaf SPAD value using RF algorithmic model and remote sensing data.Transactions of the Chinese Society for Agricultural Machinery,46(1):259-265(in Chinese)[王丽爱,马昌,周旭东,訾妍,朱新开,郭文善.2015.基于随机森林回归算法的小麦叶片SPAD值遥感估算.农业机械学报,46(1):259-265]
Wang XG.2013.A fast random forest algorithm based on K means clustering and its application on intrusion detection.Bulletin of Science and Technology,29(8):76-78(in Chinese)[王象刚.2013.基于K均值随机森林快速算法及入侵检测中的应用.科技通报,29(8):76-78]
Wang XY,Wen HJ,Li XX,Fu ZT,LüXJ,Zhang LX.2016.Research progress analysis of mainly agricultural diseases detection and early warning technologies.Transactions of the Chinese Society for Agricultural Machinery,47(9):266-277(in Chinese)[王翔宇,温皓杰,李鑫星,傅泽田,吕雄杰,张领先.2016.农业主要病害检测与预警技术研究进展分析.农业机械学报,47(9):266-277]
Wei ZT,Yang YL,Bai J.2018.An improved random forest algorithm based on unbalanced data.Journal of Chongqing University,41(4):54-62(in Chinese)[魏正韬,杨有龙,白婧.2018.基于非平衡数据的随机森林分类算法改进.重庆大学学报,41(4):54-62]
Yang B,Liu Y,Mou SM,Wen FJ.2014.Based on big data:the establishment of meteorological forecast model for the occurrence degree of the second generation of corn borer in Shandong.Journal of Computer Research and Development,51(S):160-165(in Chinese)[杨波,刘勇,牟少敏,温孚江.2014.大数据背景下山东省二代玉米螟发生程度预测模型的构建.计算机研究与发展,51(S):160-165]
Zeng J,Jiang YY,Wang HY,Yuan GH,Dong BX,Qin YX.2014.The biological characteristics of Agriphila aeneociliella and methods for monitoring and managing this pest.Chinese Journal of Applied Entomology,51(3):814-818(in Chinese)[曾娟,姜玉英,王海英,原国辉,董保信,秦引雪.2014.白眉野草螟的生物学特性和监测防控对策.应用昆虫学报,51(3):814-818]
Zeng J,Qin YX,Chen HG,Wu XY,Zhang YF.2015.Field efficacy of soil treatment with mixture of phoxim and phorate on Agriphila aeneociliella during autumn wheat sowing.Plant Protection,41(6):217-220(in Chinese)[曾娟,秦引雪,陈会刚,吴晓燕,张跃芳.2015.秋播辛硫·甲拌磷土壤处理对麦田白眉野草螟的防治效果.植物保护,41(6):217-220]
Zhang L,Wang LL,Zhang XD,Liu SR,Sun PS,Wang TL.2014.The basic principle of random forest and its applications in ecology:a case study of Pinus yunnanensis.Acta Ecologica Sinica,34(3):650-659(in Chinese)[张雷,王琳琳,张旭东,刘世荣,孙鹏森,王同立.2014.随机森林算法基本思想及其在生态学中的应用:以云南松分布模拟为例.生态学报,34(3):650-659]
Zhang QQ,Liu Y,Mou SM,Wen FJ.2016.Decision tree predictive classification model on the occurrence degree of wheat aphids based on big data.Big Data Research,2(1):59-67(in Chinese)[张晴晴,刘勇,牟少敏,温孚江.2016.基于大数据的小麦蚜虫发生程度决策树预测分类模型.大数据,2(1):59-67]
Zhang YH,Peng H,Zhang Z,Li XR,Liu Y,Yuan GH,Zou MJ,Cheng DF.2015.Effects of high temperature stress on the survival characteristics of the diapause larvae of Agriphila aeneociliella(Lepidoptera:Pyralidae).Acta Entomologica Sinica,58(8):887-892(in Chinese)[张云慧,彭赫,张智,李祥瑞,刘勇,原国辉,邹明江,程登发.2015.高温胁迫对白眉野草螟滞育幼虫存活特性的影响.昆虫学报,58(8):887-892]
Dong SS,Huang ZX.2013.A brief theoretical overview of random forests.Journal of Integration Technology,2(1):1-7(in Chinese)[董师师,黄哲学.2013.随机森林理论浅析.集成技术,2(1):1-7]
Fang KN,Wu JB,Zhu JP,Xie BC.2011.A review of random forest methods.Statistics&Information Forum,26(3):32-38(in Chinese)[方匡南,吴见彬,朱建平,谢邦昌.2011.随机森林方法研究综述.统计与信息论坛,26(3):32-38]
Genuer R,Poggi JM,Tuleau-Malot C,Villa-Vialaneix N.2017.Random forests for big data.Big Data Research,9:28-46
Iverson LR,Prasad AM,Matthews SN,Peters M.2008.Estimating potential habitat for 134 eastern US tree species under six climate scenarios.Forest Ecology and Manage,254:390-406
Ji YC,Qin M,Wu LF,Chen XL,Zhang RZ.2014.Potential distribution of two wheat pests,Agriphila aeneociliella and A.vulgivagella,in China.Chinese Journal of Applied Entomology,51(1):271-277(in Chinese)[季英超,秦萌,吴立峰,陈小龙,张润志.2014.二种危害小麦的草螟在中国的适生区.应用昆虫学报,51(1):271-277]
Lai CG,Chen XH,Zhao SW,Wang ZL,Wu SX.2015.A flood risk assessment model based on random forest and its application.Journal of Hydraulic Engineering,46(1):58-66(in Chinese)[赖成光,陈晓宏,赵仕威,王兆礼,吴旭树.2015.基于随机森林的洪灾风险评价模型及其应用.水利学报,46(1):58-66]
Li L,Mou SM,Lin ZQ.2017.Application of random forest in forecasting cotton aphid pest grade.Anhui Agricultural Science Bulletin,23(1):18-20(in Chinese)[李磊,牟少敏,林中琦.2017.随机森林在棉蚜虫害等级预测中的应用.安徽农学通报,23(1):18-20]
Li XH.2013.Using“random forest”for classification and regression.Chinese Journal of Applied Entomology,50(4):1190-1197(in Chinese)[李欣海.2013.随机森林模型在分类与回归分析中的应用.应用昆虫学报,50(4):1190-1197]
Liu MC,Jiang JF,Shi ZJ,Tang JL,Xu SH.2009.Analysis of meteorological factors and forecast of population dynamic changes of wheat aphid.Chinese Journal of Agrometeorology,30(3):440-444(in Chinese)[刘明春,蒋菊芳,史志娟,唐峻岭,徐生海.2009.小麦蚜虫种群消长气象影响成因及预测.中国农业气象,30(3):440-444]
Peng H.2014.Study on growth development and control of a wheat pest:Agriphila aeneociliella.Master Thesis.Beijing:Chinese Academy of Agricultural Sciences(in Chinese)[彭赫.2014.小麦害虫白眉野草螟的生长发育与防治研究.硕士学位论文.北京:中国农业科学院]
Qu XF.2005.Grading the occurrences of meadow moth(Loxostege sticticalis L.).China Plant Protection,25(8):8-11(in Chinese)[屈西峰.2005.草地螟发生程度的划分.中国植保导刊,25(8):8-11]
Shi LJ,Lu J.2017.Automatic measurement method for maize ear development degree based on random forest.Transactions of the Chinese Society for Agricultural Machinery,48(1):169-174(in Chinese)[石礼娟,卢军.2017.基于随机森林的玉米发育程度自动测量方法.农业机械学报,48(1):169-174]
Si LL,Cao KQ,Liu JP,Yang JY,Zhen WC.2006.Establishment of a real-time monitoring and forecasting system on main crop diseases and pests of China based on GIS.Journal of Plant Protection,33(3):282-286(in Chinese)[司丽丽,曹克强,刘佳鹏,杨军玉,甄文超.2006.基于地理信息系统的全国主要粮食作物病虫害实时监测预警系统的研制.植物保护学报,33(3):282-286]
Tang CC,Huang WJ,Luo JH,Liang D,Zhao JL,Huang LS.2015.Forecasting wheat aphid with remote sensing based on relevance vector machine.Transactions of the Chinese Society of Agricultural Engineering,31(6):201-207(in Chinese)[唐翠翠,黄文江,罗菊花,梁栋,赵晋陵,黄林生.2015.基于相关向量机的冬小麦蚜虫遥感预测.农业工程学报,31(6):201-207]
Wang LA,Ma C,Zhou XD,Zi Y,Zhu XK,Guo WS.2015.Estimation of wheat leaf SPAD value using RF algorithmic model and remote sensing data.Transactions of the Chinese Society for Agricultural Machinery,46(1):259-265(in Chinese)[王丽爱,马昌,周旭东,訾妍,朱新开,郭文善.2015.基于随机森林回归算法的小麦叶片SPAD值遥感估算.农业机械学报,46(1):259-265]
Wang XG.2013.A fast random forest algorithm based on K means clustering and its application on intrusion detection.Bulletin of Science and Technology,29(8):76-78(in Chinese)[王象刚.2013.基于K均值随机森林快速算法及入侵检测中的应用.科技通报,29(8):76-78]
Wang XY,Wen HJ,Li XX,Fu ZT,LüXJ,Zhang LX.2016.Research progress analysis of mainly agricultural diseases detection and early warning technologies.Transactions of the Chinese Society for Agricultural Machinery,47(9):266-277(in Chinese)[王翔宇,温皓杰,李鑫星,傅泽田,吕雄杰,张领先.2016.农业主要病害检测与预警技术研究进展分析.农业机械学报,47(9):266-277]
Wei ZT,Yang YL,Bai J.2018.An improved random forest algorithm based on unbalanced data.Journal of Chongqing University,41(4):54-62(in Chinese)[魏正韬,杨有龙,白婧.2018.基于非平衡数据的随机森林分类算法改进.重庆大学学报,41(4):54-62]
Yang B,Liu Y,Mou SM,Wen FJ.2014.Based on big data:the establishment of meteorological forecast model for the occurrence degree of the second generation of corn borer in Shandong.Journal of Computer Research and Development,51(S):160-165(in Chinese)[杨波,刘勇,牟少敏,温孚江.2014.大数据背景下山东省二代玉米螟发生程度预测模型的构建.计算机研究与发展,51(S):160-165]
Zeng J,Jiang YY,Wang HY,Yuan GH,Dong BX,Qin YX.2014.The biological characteristics of Agriphila aeneociliella and methods for monitoring and managing this pest.Chinese Journal of Applied Entomology,51(3):814-818(in Chinese)[曾娟,姜玉英,王海英,原国辉,董保信,秦引雪.2014.白眉野草螟的生物学特性和监测防控对策.应用昆虫学报,51(3):814-818]
Zeng J,Qin YX,Chen HG,Wu XY,Zhang YF.2015.Field efficacy of soil treatment with mixture of phoxim and phorate on Agriphila aeneociliella during autumn wheat sowing.Plant Protection,41(6):217-220(in Chinese)[曾娟,秦引雪,陈会刚,吴晓燕,张跃芳.2015.秋播辛硫·甲拌磷土壤处理对麦田白眉野草螟的防治效果.植物保护,41(6):217-220]
Zhang L,Wang LL,Zhang XD,Liu SR,Sun PS,Wang TL.2014.The basic principle of random forest and its applications in ecology:a case study of Pinus yunnanensis.Acta Ecologica Sinica,34(3):650-659(in Chinese)[张雷,王琳琳,张旭东,刘世荣,孙鹏森,王同立.2014.随机森林算法基本思想及其在生态学中的应用:以云南松分布模拟为例.生态学报,34(3):650-659]
Zhang QQ,Liu Y,Mou SM,Wen FJ.2016.Decision tree predictive classification model on the occurrence degree of wheat aphids based on big data.Big Data Research,2(1):59-67(in Chinese)[张晴晴,刘勇,牟少敏,温孚江.2016.基于大数据的小麦蚜虫发生程度决策树预测分类模型.大数据,2(1):59-67]
Zhang YH,Peng H,Zhang Z,Li XR,Liu Y,Yuan GH,Zou MJ,Cheng DF.2015.Effects of high temperature stress on the survival characteristics of the diapause larvae of Agriphila aeneociliella(Lepidoptera:Pyralidae).Acta Entomologica Sinica,58(8):887-892(in Chinese)[张云慧,彭赫,张智,李祥瑞,刘勇,原国辉,邹明江,程登发.2015.高温胁迫对白眉野草螟滞育幼虫存活特性的影响.昆虫学报,58(8):887-892]