基于基质含水率的作物蒸腾量估算与预测模型研究
|
摘要
作物蒸腾作用是基质水分传输的主要驱动力,建立了基于基质含水率变化量的温室番茄作物蒸腾量估算模型和预测模型,并进行对比分析。使用校准后的EC5基质含水率传感器,记录第1次灌溉后与第2次灌溉前基质实时含水率变化量,使用称量法测量作物实时蒸腾量。通过基质含水率变化量与基质栽培槽体积的多元线性回归运算,建立番茄单株日蒸腾量估算模型;将基质含水率变化量、空气温度、空气湿度和光照强度作为输入,利用GABP神经网络算法,建立番茄单株日蒸腾量预测模型。将试验所得温室作物日蒸腾量估算模型和预测模型分别与温室作物实际日蒸腾量进行线性回归分析,结果表明,基于基质含水率变化量建立的估算模型在苗期、花期的预测精度分别为0. 972 9、0. 979 6,预测模型的预测精度分别为0. 991 5、0. 989 0,两者之间差异不大,但估算模型运算速度远高于预测模型的运算速度,估算模型对于温室灌溉管理具有推广应用价值。
Crop transpiration was the main driving force of substrate water transfer. Aiming to establish a greenhouse tomato crop transpiration estimation model and prediction model based on the change of substrate water content,and make a comparative analysis. The calibrated EC5 matrix moisture content sensor was used to record the real-time change of matrix moisture content after the first irrigation and before the second irrigation. Real-time crop transpiration was measured by weighing method. The estimation model of daily transpiration per plant of tomato was established by multiple linear regression calculation of variation of substrate moisture content and volume of substrate cultivation tank. Taking the variation of substrate moisture content,air temperature,air humidity and illuminate intensity as input,the prediction model of daily transpiration per plant of tomato was established by GABP neural network algorithm. The greenhouse crop transpiration estimation model and predictive model were tested respectively with the greenhouse crop's daily transpiration by linear regression analysis,the results showed that the prediction accuracy of the estimation model based on the variation of water content in the matrix was 0. 972 9 and 0. 979 6,respectively,in the seedling stage and florescence,and the prediction accuracy of the prediction model was 0. 991 5 and 0. 989 0,respectively. The differences between the two was not big,but the estimate model operation speed was much higher than predictionmodel of operation speed. In practical application,the estimation model had good robustness to environmental changes,and the relative error was less than 5% at seedling stage and flowering stage. The estimation model had the value of popularization and application for greenhouse irrigation management.
Crop transpiration was the main driving force of substrate water transfer. Aiming to establish a greenhouse tomato crop transpiration estimation model and prediction model based on the change of substrate water content,and make a comparative analysis. The calibrated EC5 matrix moisture content sensor was used to record the real-time change of matrix moisture content after the first irrigation and before the second irrigation. Real-time crop transpiration was measured by weighing method. The estimation model of daily transpiration per plant of tomato was established by multiple linear regression calculation of variation of substrate moisture content and volume of substrate cultivation tank. Taking the variation of substrate moisture content,air temperature,air humidity and illuminate intensity as input,the prediction model of daily transpiration per plant of tomato was established by GABP neural network algorithm. The greenhouse crop transpiration estimation model and predictive model were tested respectively with the greenhouse crop's daily transpiration by linear regression analysis,the results showed that the prediction accuracy of the estimation model based on the variation of water content in the matrix was 0. 972 9 and 0. 979 6,respectively,in the seedling stage and florescence,and the prediction accuracy of the prediction model was 0. 991 5 and 0. 989 0,respectively. The differences between the two was not big,but the estimate model operation speed was much higher than predictionmodel of operation speed. In practical application,the estimation model had good robustness to environmental changes,and the relative error was less than 5% at seedling stage and flowering stage. The estimation model had the value of popularization and application for greenhouse irrigation management.
引文
[1]李惠,梁杏,刘延锋.干旱区膜下滴灌棉田SPAC系统水分通量模拟[J].水文地质工程地质,2018,45(2):21-28.LI Hui,LIANG Xing,LIU Yanfeng.Simulation of water flux in subfilm drip irrigation cotton field SPAC system in arid area[J].Journal of Hydrogeology and Engineering Geology,2018,45(2):21-28.(in Chinese)
[2]DIAZ-PEREZ J C,YAHIA E M.Transpiration,postharvest physiology and biochemistry of fruits and vegetables[M].Woodhead Publishing,2019:157-173.
[3]李建明,樊翔宇,闫芳芳,等.基于蒸腾模型决策的灌溉量对甜瓜产量及品质的影响[J].农业工程学报,2017,33(21):156-162.LI Jianming,FAN Xiangyu,YAN Fangfang,et al.Effects of irrigation amount on yield and quality of muskmelon based on transpiration model decision[J].Transactions of the CSAE,2017,33(21):156-162.(in Chinese)
[4]GOSWAMI T K,MANGARA J.Advances in polymeric materials for modified atmosphere packaging(MAP)[M].Woodhead Publishing,2011:163-242.
[5]WANG H,SANCHEZ-MOLINA J A,LI M,et al.Leaf area index estimation for a greenhouse transpiration model using external climate conditions based on genetics algorithms,back-propagation neural networks and nonlinear autoregressive exogenous models[J].Agricultural Water Management,2017,183:107-115.
[6]VADEZ V,KHOLOVA J,HUMMEL G,et al.Leasy Scan:a novel concept combining 3D imaging and lysimetry for highthroughput phenotyping of traits controlling plant water budget[J].Journal of Experimental Botany,2015,66(18):5581-5593.
[7]KIRKHAM M B.Sap flow principles of soil and plant water relations[M].Academic Press,2014:375-390.
[8]李永秀,番聪聪,宋文怀.不同方法测定设施番茄蒸腾的结果比较及相关性分析[J].江苏农业科学,2017,45(3):98-101.LI Yongxiu,FAN Congcong,SONG Wenhuai.Comparison and correlation analysis of different methods for determination of transpiration of tomato in facilities[J].Jiangsu Agricultural Science,2017,45(3):98-101.(in Chinese)
[9]WIDMOSER P.A discussion on and alternative to the Penman-Monteith equation[J].Agricultural Water Management,2009,96(4):711-721.
[10]伍德林,毛罕平,曹成茂.温室设施作物蒸腾量计算方法及模型[C]∥全国农业水土工程学术研讨会,2010.
[11]PEREA R G,POYATO E C,MONTESIONS P,et al.Irrigation demand forecasting using artificial neuro-genetic networks[J].Water Resources Management,2015,29(15):5551-5567.
[12]卢佳骏,王纪章,刘继展,等.草莓高架栽培中混合基质水分分布[J].排灌机械工程学报,2017,35(6):535-540.LU Jiajun,WANG Jizhang,LIU Jizhan,et al.Mixed matrix water distribution in strawberry viaduct cultivation[J].Journal of Drainage and Irrigation Mechanical Engineering,2017,35(6):535-540.(in Chinese)
[13]BAR-TAL A,SAHA U K,RAVIA M,et al.Inorganic and synthetic organic components of soilless culture and potting mixtures[M].Elsevier,2019:259-301.
[14]MARGENOT A J,GRIFFIN D E,ALVES B S Q,et al.Substitution of peat moss with softwood biochar for soil-free marigold growth[J].Industrial Crops and Products,2018,112:160-169.
[15]徐丽萍,张朝晖.基于Hydrus-1D的滴灌土壤水分运移数值模拟[J].节水灌溉,2019(2):64-67.XU Liping,ZHANG Zhaohui.Numerical simulation of soil water transport by drip irrigation based on Hydrus-1D[J].Watersaving Irrigation,2019(2):64-67.(in Chinese)
[16]BAYAT H,EBRAHIM Z G.Estimation of the soil water retention curve using penetration resistance curve models[J].Computers and Electronics in Agriculture,2018,144:329-343.
[17]PATRICIO D I,RIEDER R.Computer vision and artificial intelligence in precision agriculture for grain crops:a systematic review[J].Computers and Electronics in Agriculture,2018,153:69-81.
[18]曲春阳,刘亿军.基于改进BP神经网络模型的区域农业灌溉用水预测研究[J].吉林水利,2016(10):1-3,6.QU Chunyang,LIU Yijun.Prediction of regional agricultural irrigation water based on improved BP neural network model[J].Jilin Water Conservancy,2016(10):1-3,6.(in Chinese)
[19]LI H,HU C X,LI Y.Application of the purification of materials based on GA-BP[J].Energy Procedia,2012,17:762-769.
[20]魏云云.基于遗传算法的BP神经网络对农业产业的分析预测[J].高师理科学刊,2018,38(9):15-19.WEI Yunyun.Analysis and prediction of agricultural industry by BP neural network based on genetic algorithm[J].Science Journal of Normal University,2018,38(9):15-19.(in Chinese)
[21]LI Y,ZOU C,BERECIBAR M,et al.Random forest regression for online capacity estimation of lithium-ion batteries[J].Applied Energy,2018,232:197-210.
[2]DIAZ-PEREZ J C,YAHIA E M.Transpiration,postharvest physiology and biochemistry of fruits and vegetables[M].Woodhead Publishing,2019:157-173.
[3]李建明,樊翔宇,闫芳芳,等.基于蒸腾模型决策的灌溉量对甜瓜产量及品质的影响[J].农业工程学报,2017,33(21):156-162.LI Jianming,FAN Xiangyu,YAN Fangfang,et al.Effects of irrigation amount on yield and quality of muskmelon based on transpiration model decision[J].Transactions of the CSAE,2017,33(21):156-162.(in Chinese)
[4]GOSWAMI T K,MANGARA J.Advances in polymeric materials for modified atmosphere packaging(MAP)[M].Woodhead Publishing,2011:163-242.
[5]WANG H,SANCHEZ-MOLINA J A,LI M,et al.Leaf area index estimation for a greenhouse transpiration model using external climate conditions based on genetics algorithms,back-propagation neural networks and nonlinear autoregressive exogenous models[J].Agricultural Water Management,2017,183:107-115.
[6]VADEZ V,KHOLOVA J,HUMMEL G,et al.Leasy Scan:a novel concept combining 3D imaging and lysimetry for highthroughput phenotyping of traits controlling plant water budget[J].Journal of Experimental Botany,2015,66(18):5581-5593.
[7]KIRKHAM M B.Sap flow principles of soil and plant water relations[M].Academic Press,2014:375-390.
[8]李永秀,番聪聪,宋文怀.不同方法测定设施番茄蒸腾的结果比较及相关性分析[J].江苏农业科学,2017,45(3):98-101.LI Yongxiu,FAN Congcong,SONG Wenhuai.Comparison and correlation analysis of different methods for determination of transpiration of tomato in facilities[J].Jiangsu Agricultural Science,2017,45(3):98-101.(in Chinese)
[9]WIDMOSER P.A discussion on and alternative to the Penman-Monteith equation[J].Agricultural Water Management,2009,96(4):711-721.
[10]伍德林,毛罕平,曹成茂.温室设施作物蒸腾量计算方法及模型[C]∥全国农业水土工程学术研讨会,2010.
[11]PEREA R G,POYATO E C,MONTESIONS P,et al.Irrigation demand forecasting using artificial neuro-genetic networks[J].Water Resources Management,2015,29(15):5551-5567.
[12]卢佳骏,王纪章,刘继展,等.草莓高架栽培中混合基质水分分布[J].排灌机械工程学报,2017,35(6):535-540.LU Jiajun,WANG Jizhang,LIU Jizhan,et al.Mixed matrix water distribution in strawberry viaduct cultivation[J].Journal of Drainage and Irrigation Mechanical Engineering,2017,35(6):535-540.(in Chinese)
[13]BAR-TAL A,SAHA U K,RAVIA M,et al.Inorganic and synthetic organic components of soilless culture and potting mixtures[M].Elsevier,2019:259-301.
[14]MARGENOT A J,GRIFFIN D E,ALVES B S Q,et al.Substitution of peat moss with softwood biochar for soil-free marigold growth[J].Industrial Crops and Products,2018,112:160-169.
[15]徐丽萍,张朝晖.基于Hydrus-1D的滴灌土壤水分运移数值模拟[J].节水灌溉,2019(2):64-67.XU Liping,ZHANG Zhaohui.Numerical simulation of soil water transport by drip irrigation based on Hydrus-1D[J].Watersaving Irrigation,2019(2):64-67.(in Chinese)
[16]BAYAT H,EBRAHIM Z G.Estimation of the soil water retention curve using penetration resistance curve models[J].Computers and Electronics in Agriculture,2018,144:329-343.
[17]PATRICIO D I,RIEDER R.Computer vision and artificial intelligence in precision agriculture for grain crops:a systematic review[J].Computers and Electronics in Agriculture,2018,153:69-81.
[18]曲春阳,刘亿军.基于改进BP神经网络模型的区域农业灌溉用水预测研究[J].吉林水利,2016(10):1-3,6.QU Chunyang,LIU Yijun.Prediction of regional agricultural irrigation water based on improved BP neural network model[J].Jilin Water Conservancy,2016(10):1-3,6.(in Chinese)
[19]LI H,HU C X,LI Y.Application of the purification of materials based on GA-BP[J].Energy Procedia,2012,17:762-769.
[20]魏云云.基于遗传算法的BP神经网络对农业产业的分析预测[J].高师理科学刊,2018,38(9):15-19.WEI Yunyun.Analysis and prediction of agricultural industry by BP neural network based on genetic algorithm[J].Science Journal of Normal University,2018,38(9):15-19.(in Chinese)
[21]LI Y,ZOU C,BERECIBAR M,et al.Random forest regression for online capacity estimation of lithium-ion batteries[J].Applied Energy,2018,232:197-210.