基于田间环境及气象数据的甘蔗产量预测方法
|
摘要
对2008—2017年间广西某甘蔗地装设的田间物联网获取的田间环境及气象数据进行了分析,研究通过这些数据预测甘蔗产量的可行性。对田间的环境数据(土壤含水率和土壤温度)和气象数据(降水量和空气温度)进行预处理,分别运用BP神经网络及遗传算法优化初始阈值的BP神经网络(GA-BP)对所选地块的甘蔗产量进行预测。结果表明,GA-BP神经网络模型的预测精度明显高于BP神经网络模型,R~2达到0. 989 4,平均相对误差仅为0. 64%。说明用GA-BP神经网络预测甘蔗产量是有效、可行的。
The agricultural internet of things has been gradually popularized in agricultural planting management,but most of the application scenarios are mainly focusing on guiding growers to fertilize and irrigate crops from its acquired field data. Environmental and meteorological data of the crop's entire growth season can also reflect the microscopic and macroscopic environment of crop growth,and hence influencing the final yield. Therefore, the environmental data( soil moisture content and soil temperature) and meteorological data( precipitation and air temperature) of a sugarcane field collected from a field IoTs system were used to build up yield predict models. The collected data was ranged from the year of 2008 to 2017,and the original BP neural network and an improved BP neural network based on genetic algorithm( GA-BP) were adopted to predict the yield. Comparing the prediction results of these two models,it was found that the prediction accuracy of the GA-BP neural network model was significantly higher than that of the BP neural network model,with its R~2 reaching 0. 989 4,and its average relative prediction error was only 0. 64%,which was also obviously lower than that of BP neural network model( 5. 66%). The result indicated that the GA-BP neural network was effective and feasible in predicting sugarcane production.
The agricultural internet of things has been gradually popularized in agricultural planting management,but most of the application scenarios are mainly focusing on guiding growers to fertilize and irrigate crops from its acquired field data. Environmental and meteorological data of the crop's entire growth season can also reflect the microscopic and macroscopic environment of crop growth,and hence influencing the final yield. Therefore, the environmental data( soil moisture content and soil temperature) and meteorological data( precipitation and air temperature) of a sugarcane field collected from a field IoTs system were used to build up yield predict models. The collected data was ranged from the year of 2008 to 2017,and the original BP neural network and an improved BP neural network based on genetic algorithm( GA-BP) were adopted to predict the yield. Comparing the prediction results of these two models,it was found that the prediction accuracy of the GA-BP neural network model was significantly higher than that of the BP neural network model,with its R~2 reaching 0. 989 4,and its average relative prediction error was only 0. 64%,which was also obviously lower than that of BP neural network model( 5. 66%). The result indicated that the GA-BP neural network was effective and feasible in predicting sugarcane production.
引文
[1]李炳杨.广西甘蔗种植现状、问题及对策[J].热带农业科学,2018,38(4):119-127.LI Bingyang.The present situation,problems and countermeasures of sugarcane cultivation in Guangxi[J].Chinese Journal of Tropical Agriculture,2018,38(4):119-127.(in Chinese)
[2]肖凌,梁玉莲,杨宇红,等.南宁市甘蔗气候产量预测模型[J].广东农业科学,2013,40(4):174-176,238.XIAO Ling,LIANG Yulian,YANG Yuhong,et al.Sugarcane climatic yield predicting model of Nanning[J].Guangdong Agricultural Sciences,2013,40(4):174-176,238.(in Chinese)
[3]何燕,谭宗琨,丁美花,等.制约广西甘蔗产量及蔗糖分含量的关键气象条件研究[J].安徽农业科学,2008,36(8):3181-3184.
[4]付建涛,孙东磊,陈立君,等.温度和降水变化与甘蔗产量的关系分析[J].热带农业科学,2018,38(6):13-17.FU Jiantao,SUN Donglei,CHEN Lijun,et al.Relationship analysis of the temperature and precipitation with the yield of sugarcane[J].Chinese Journal of Tropical Agriculture,2018,38(6):13-17.(in Chinese)
[5]李奇伟.现代甘蔗改良技术[M].广州:华南理工大学出版社,2000.
[6]阮红燕.气候变化对广西甘蔗生产潜力影响的模拟研究[D].南宁:广西大学,2018.RUAN Hongyan.Climate change projects impacts on sugarcane productivity in Guangxi[D].Nanning:Guangxi University,2018.(in Chinese)
[7]欧钊荣,谭宗琨,何燕,等.BP神经网络模型在广西原料蔗产量预报中的应用[J].中国农业气象,2008,29(2):213-216.OU Zhaorong,TAN Zongkun,HE Yan,et al.Application of BP neural network in yield predication of sugarcane(Saccharum officinarum L.)in Guangxi Province[J].Chinese Journal of Agrometeorology,2008,29(2):213-216.(in Chinese)
[8]EZRIN M H,AMIN M S M,ANUAR A R,et al.Relationship between rice yield and apparent electrical conductivity of paddy soils[J].American Journal of Applied Sciences,2010,7(1):63.
[9]MEENA P K,HARDAHA M K,KHARE D,et al.Neural method for site-specific yield prediction[C]∥Proceedings of the Third International Conference on Soft Computing for Problem Solving.Springer India,2014:237-246.
[10]FORTIN J G,ANCTIL F,PARENT L,et al.Site-specific early season potato yield forecast by neural network in eastern Canada[J].Precision Agriculture,2011,12(6):905-923.
[11]徐永春,张森文.改进遗传神经网络在甘蔗产量预测中的应用[J].华南农业大学学报,2010,31(3):102-104.XU Yongchun,ZHANG Senwen.The Application on the sugar cane forecast with the neural networks using improved genetic algorithms[J].Journal of South China Agricultural University,2010,31(3):102-104.(in Chinese)
[12]姜新.河南省粮食产量影响因素和预测方法研究[J].中国农学通报,2019,35(1):154-158.JIANG Xin.Influencing factors and forecasting methods of grain yield in Henan Province[J].Chinese Agricultural Science Bulletin,2019,35(1):154-158.(in Chinese)
[13]黄健熙,罗倩,刘晓暄,等.基于时间序列MODIS NDVI的冬小麦产量预测方法[J].农业机械学报,2016,47(2):295-301.HUANG Jianxi,LUO Qian,LIU Xiaoxuan,et al.Winter wheat yield forecasting based on time series of MODIS NDVI[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(2):295-301.(in Chinese)
[14]和文超,师学义,邓青云,等.土地利用规划修编中粮食产量预测方法比较[J].农业工程学报,2011,27(12):348-352.HE Wenchao,SHI Xueyi,DENG Qingyun,et al.Comparison of grain yield prediction methods in land use planning[J].Transactions of the CSAE,2011,27(12):348-352.(in Chinese)
[15]马晓敏,王新.基于遗传算法的BP神经网络改进[J].云南大学学报(自然科学版),2013,35(增刊2):34-38.MA Xiaomin,WANG Xin.An improved BP neural network algorithm based on genetic algorithm[J].Journal of Yunnan University(Natural Sciences Edition),2013,35(Supp.2):34-38.(in Chinese)
[16]李海青,赵又群,闫茜,等.基于遗传神经网络的车轮匹配整车逆动力学[J].华中科技大学学报(自然科学版),2019,47(5):27-32.LI Haiqing,ZHAO Youqun,YAN Xi,et al.Inverse dynamics of vehicle matching with mechanical elastic wheels based on genetic neural network[J].Journal of Huazhong University of Science and Technology(Natural Science Edition),2019,47(5):27-32.(in Chinese)
[17]陈英义,程倩倩,成艳君,等.基于GA-BP神经网络的池塘养殖水温短期预测系统[J].农业机械学报,2017,48(8):172-178.CHEN Yingyi,CHENG Qianqian,CHENG Yanjun,et al.Short-term prediction system of water temperature in pond aquaculture based on GA-BP neural network[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(8):172-178.(in Chinese)
[18]张漫,李婷,季宇寒,等.基于BP神经网络算法的温室番茄CO2增施策略优化[J].农业机械学报,2015,46(8):239-245.ZHANG Man,LI Ting,JI Yuhan,et al.Optimization of CO2enrichment strategy based on BPNN for tomato plants in greenhouse[J].Transactions of the Chinese Society for Agricultural Machinery,2015,46(8):239-245.(in Chinese)
[19]刘雪,李亚妹,刘娇,等.基于BP神经网络的鲜鸡蛋货架期预测模型[J].农业机械学报,2015,46(10):328-334.LIU Xue,LI Yamei,LIU Jiao,et al.BP neural network based prediction model for fresh egg’s shelf life[J].Transactions of the Chinese Society for Agricultural Machinery,2015,46(10):328-334.(in Chinese)
[20]郁磊,史峰,王辉,等.MATLAB智能算法30个案例分析[M].北京:北京航空航天大学出版社,2011.
[2]肖凌,梁玉莲,杨宇红,等.南宁市甘蔗气候产量预测模型[J].广东农业科学,2013,40(4):174-176,238.XIAO Ling,LIANG Yulian,YANG Yuhong,et al.Sugarcane climatic yield predicting model of Nanning[J].Guangdong Agricultural Sciences,2013,40(4):174-176,238.(in Chinese)
[3]何燕,谭宗琨,丁美花,等.制约广西甘蔗产量及蔗糖分含量的关键气象条件研究[J].安徽农业科学,2008,36(8):3181-3184.
[4]付建涛,孙东磊,陈立君,等.温度和降水变化与甘蔗产量的关系分析[J].热带农业科学,2018,38(6):13-17.FU Jiantao,SUN Donglei,CHEN Lijun,et al.Relationship analysis of the temperature and precipitation with the yield of sugarcane[J].Chinese Journal of Tropical Agriculture,2018,38(6):13-17.(in Chinese)
[5]李奇伟.现代甘蔗改良技术[M].广州:华南理工大学出版社,2000.
[6]阮红燕.气候变化对广西甘蔗生产潜力影响的模拟研究[D].南宁:广西大学,2018.RUAN Hongyan.Climate change projects impacts on sugarcane productivity in Guangxi[D].Nanning:Guangxi University,2018.(in Chinese)
[7]欧钊荣,谭宗琨,何燕,等.BP神经网络模型在广西原料蔗产量预报中的应用[J].中国农业气象,2008,29(2):213-216.OU Zhaorong,TAN Zongkun,HE Yan,et al.Application of BP neural network in yield predication of sugarcane(Saccharum officinarum L.)in Guangxi Province[J].Chinese Journal of Agrometeorology,2008,29(2):213-216.(in Chinese)
[8]EZRIN M H,AMIN M S M,ANUAR A R,et al.Relationship between rice yield and apparent electrical conductivity of paddy soils[J].American Journal of Applied Sciences,2010,7(1):63.
[9]MEENA P K,HARDAHA M K,KHARE D,et al.Neural method for site-specific yield prediction[C]∥Proceedings of the Third International Conference on Soft Computing for Problem Solving.Springer India,2014:237-246.
[10]FORTIN J G,ANCTIL F,PARENT L,et al.Site-specific early season potato yield forecast by neural network in eastern Canada[J].Precision Agriculture,2011,12(6):905-923.
[11]徐永春,张森文.改进遗传神经网络在甘蔗产量预测中的应用[J].华南农业大学学报,2010,31(3):102-104.XU Yongchun,ZHANG Senwen.The Application on the sugar cane forecast with the neural networks using improved genetic algorithms[J].Journal of South China Agricultural University,2010,31(3):102-104.(in Chinese)
[12]姜新.河南省粮食产量影响因素和预测方法研究[J].中国农学通报,2019,35(1):154-158.JIANG Xin.Influencing factors and forecasting methods of grain yield in Henan Province[J].Chinese Agricultural Science Bulletin,2019,35(1):154-158.(in Chinese)
[13]黄健熙,罗倩,刘晓暄,等.基于时间序列MODIS NDVI的冬小麦产量预测方法[J].农业机械学报,2016,47(2):295-301.HUANG Jianxi,LUO Qian,LIU Xiaoxuan,et al.Winter wheat yield forecasting based on time series of MODIS NDVI[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(2):295-301.(in Chinese)
[14]和文超,师学义,邓青云,等.土地利用规划修编中粮食产量预测方法比较[J].农业工程学报,2011,27(12):348-352.HE Wenchao,SHI Xueyi,DENG Qingyun,et al.Comparison of grain yield prediction methods in land use planning[J].Transactions of the CSAE,2011,27(12):348-352.(in Chinese)
[15]马晓敏,王新.基于遗传算法的BP神经网络改进[J].云南大学学报(自然科学版),2013,35(增刊2):34-38.MA Xiaomin,WANG Xin.An improved BP neural network algorithm based on genetic algorithm[J].Journal of Yunnan University(Natural Sciences Edition),2013,35(Supp.2):34-38.(in Chinese)
[16]李海青,赵又群,闫茜,等.基于遗传神经网络的车轮匹配整车逆动力学[J].华中科技大学学报(自然科学版),2019,47(5):27-32.LI Haiqing,ZHAO Youqun,YAN Xi,et al.Inverse dynamics of vehicle matching with mechanical elastic wheels based on genetic neural network[J].Journal of Huazhong University of Science and Technology(Natural Science Edition),2019,47(5):27-32.(in Chinese)
[17]陈英义,程倩倩,成艳君,等.基于GA-BP神经网络的池塘养殖水温短期预测系统[J].农业机械学报,2017,48(8):172-178.CHEN Yingyi,CHENG Qianqian,CHENG Yanjun,et al.Short-term prediction system of water temperature in pond aquaculture based on GA-BP neural network[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(8):172-178.(in Chinese)
[18]张漫,李婷,季宇寒,等.基于BP神经网络算法的温室番茄CO2增施策略优化[J].农业机械学报,2015,46(8):239-245.ZHANG Man,LI Ting,JI Yuhan,et al.Optimization of CO2enrichment strategy based on BPNN for tomato plants in greenhouse[J].Transactions of the Chinese Society for Agricultural Machinery,2015,46(8):239-245.(in Chinese)
[19]刘雪,李亚妹,刘娇,等.基于BP神经网络的鲜鸡蛋货架期预测模型[J].农业机械学报,2015,46(10):328-334.LIU Xue,LI Yamei,LIU Jiao,et al.BP neural network based prediction model for fresh egg’s shelf life[J].Transactions of the Chinese Society for Agricultural Machinery,2015,46(10):328-334.(in Chinese)
[20]郁磊,史峰,王辉,等.MATLAB智能算法30个案例分析[M].北京:北京航空航天大学出版社,2011.