基于冠层光谱和BP神经网络的水稻叶片氮素浓度估算模型
|
摘要
[目的]快速、准确地诊断水稻叶片氮素营养状况,为水稻氮肥精准管理提供依据。[方法]以江西省农科院8种不同施肥处理的晚稻为研究对象,于主要生育期同步测定了水稻冠层光谱反射率及叶片全氮浓度(Leaf Nitrogen Concentration,LNC),系统分析了原始光谱反射率、一阶微分光谱、"三边"参数以及由350～1 350nm两两波段组合的差值(SD (Rλ1,Rλ2))、比值(SR (Rλ1,Rλ2))及归一化(ND(Rλ1,Rλ2))光谱指数与水稻LNC的相关关系,筛选出敏感参数,并以之为自变量构建了水稻LNC的传统预测模型,另外构建不同指标个数的多元线性与BP神经网络模型,并对模型进行验证。[结果](1)水稻LNC与一阶微分光谱在751nm处的相关性最高(r=0. 822);(2)"三边"参数中的红边面积SDr与LNC的相关性较高(r=0. 687);(3) 750nm附近的红边波段与近红外波段差值组合、550nm附近的绿光波段与近红外波段的比值及归一化差值组合与水稻LNC的相关性较高,以SD (R752,R751)、SR (R534,R1 350)和ND (R534,R1 349)表现最好,相关系数分别为0. 827、-0. 790和0. 788;(4)传统回归模型中以SD(R752,R751)构建的一元线性模型最佳(RC2=0. 665、RV2=0. 750、RMSEV=0. 4%、RPD=2. 034);(5)利用5个指标((R'751、SDr、SD (R752,R751)、SR (R534,R1 350)、ND (R534,R1 349))经逐步回归筛选出的2个指标SD ((R752,R751)和SR (R534,R1 350))构建预测水稻氮素的BP神经网络模型,预测效果最佳,其验证参数值分别为R2=0. 859、RMSEV=0. 302%和RPD=2. 669。[结论]基于单指标构建的传统线性模型计算过程简单但精度略低,而基于2个指标(SD (R752,R751)、SR (R534,R1 350))构建的BP神经网络模型预测精度高于该2指标构建的多元线性模型,表明在指标适合的情况下,BP神经网络对氮素具有较好的预测能力,是一种快速准确估算水稻叶片全氮浓度的方法。
The objective of the study is to analyze the relationships between canopy spectral reflectance characteristics and leaf nitrogen concentration( LNC),and establish the rapid and accurate method to diagnose the rice leaf nitrogen nutrition by spectrum,so as to provide the basis of rice precision fertilization. An experiment of eight different fertilization treatments on the late rice was carried out in the Jiangxi Academy of Agricultural Sciences. The canopy spectral reflectance and leaf nitrogen concentration( LNC) were measured simultaneously in the main growth stages which were stages of tillering,booting,heading,maturity. The original spectral reflectance,the first derivative spectrum,the 'three edge' parameter and the spectral index including difference( SD( Rλ1,Rλ2)),the ratio( SR( Rλ1,Rλ2)) and the normalized( ND( Rλ1,Rλ2)) between 2 bands from spectral range in 350-1350 nm and their relationship with rice LNC were systematically analyzed to selected the sensitive parameters,and constructed the traditional prediction model of rice LNC with the sensitive parameters as the independent variables. In addition,the multiple linear model and BP neural network model of different index number were established,and the models were verified. The results were showed as follows. Firstly,the maximum correlation coefficient was between the rice LNC and the first order differential spectrum at 751 nm( r = 0. 822). Secondly,the correlation coefficient between the " red-edge" area( SDr) in the " three edge" parameters and the LNC was high( 0. 687). Thirdly,the correlation coefficients between the rice LNC and the difference spectral index of red edge band near 750 nm with Infrared band,between the rice LNC and the ratio of green band near 550 nm with Infrared band,and between the rice LNC and the normalized difference spectral index were high,with SD( R752,R751),SR( R534,R1 350),and ND( R534,R1 349) were best,and the correlation coefficients were 0. 872,-0. 790 and 0. 788,respectively. Fourthly,in the traditional regression models,the linear model of SD( 752,751) was the best( Rc2= 0. 665,Rv2= 0. 750,RMSE= 0. 4%,RPD = 2. 034). Finally,using 2 indicators(( R752,R751),SR( R534,R1 350)),which were selected from5 indicators(( R'751,SDr,SD( R752,R751),SR( R534,R1 350),ND( R534,R1 349)) through stepwise regression,a BP neural network model to predict rice nitrogen was built. The model had the best prediction effect,with the accuracy of the model were R2= 0. 859,RMSEv = 0. 302% and RPD = 2. 669,respectively. Comparing with the single index traditional regression models,mult-index models has higher accuracy,especially two index-BP neural network model which has the highest accuracy. The result show that BP neural network model is a quick and accurate method to estimate the rice LNC in the case of suitable index.
The objective of the study is to analyze the relationships between canopy spectral reflectance characteristics and leaf nitrogen concentration( LNC),and establish the rapid and accurate method to diagnose the rice leaf nitrogen nutrition by spectrum,so as to provide the basis of rice precision fertilization. An experiment of eight different fertilization treatments on the late rice was carried out in the Jiangxi Academy of Agricultural Sciences. The canopy spectral reflectance and leaf nitrogen concentration( LNC) were measured simultaneously in the main growth stages which were stages of tillering,booting,heading,maturity. The original spectral reflectance,the first derivative spectrum,the 'three edge' parameter and the spectral index including difference( SD( Rλ1,Rλ2)),the ratio( SR( Rλ1,Rλ2)) and the normalized( ND( Rλ1,Rλ2)) between 2 bands from spectral range in 350-1350 nm and their relationship with rice LNC were systematically analyzed to selected the sensitive parameters,and constructed the traditional prediction model of rice LNC with the sensitive parameters as the independent variables. In addition,the multiple linear model and BP neural network model of different index number were established,and the models were verified. The results were showed as follows. Firstly,the maximum correlation coefficient was between the rice LNC and the first order differential spectrum at 751 nm( r = 0. 822). Secondly,the correlation coefficient between the " red-edge" area( SDr) in the " three edge" parameters and the LNC was high( 0. 687). Thirdly,the correlation coefficients between the rice LNC and the difference spectral index of red edge band near 750 nm with Infrared band,between the rice LNC and the ratio of green band near 550 nm with Infrared band,and between the rice LNC and the normalized difference spectral index were high,with SD( R752,R751),SR( R534,R1 350),and ND( R534,R1 349) were best,and the correlation coefficients were 0. 872,-0. 790 and 0. 788,respectively. Fourthly,in the traditional regression models,the linear model of SD( 752,751) was the best( Rc2= 0. 665,Rv2= 0. 750,RMSE= 0. 4%,RPD = 2. 034). Finally,using 2 indicators(( R752,R751),SR( R534,R1 350)),which were selected from5 indicators(( R'751,SDr,SD( R752,R751),SR( R534,R1 350),ND( R534,R1 349)) through stepwise regression,a BP neural network model to predict rice nitrogen was built. The model had the best prediction effect,with the accuracy of the model were R2= 0. 859,RMSEv = 0. 302% and RPD = 2. 669,respectively. Comparing with the single index traditional regression models,mult-index models has higher accuracy,especially two index-BP neural network model which has the highest accuracy. The result show that BP neural network model is a quick and accurate method to estimate the rice LNC in the case of suitable index.
引文
[1]王莉雯,卫亚星.植被氮素浓度高光谱遥感反演研究进展.光谱学与光谱分析,2013,33(10):2823-2827.
[2]周冬琴,田永超,姚霞,等.水稻叶片全氮浓度与冠层反射光谱的定量关系.应用生态学报,2008,19(2):337-344.
[3] Ju X T,Xing G X,Chen X P,et al. Reducing Environmental Risk by Improving N Management in Intensive Chinese Agricultural Systems.Proceedings of the National Academy of Sciences of the United States of America,2009,106(9):3041.
[4]郭腾飞,梁国庆,周卫,等.施肥对稻田温室气体排放及土壤养分的影响.植物营养与肥料学报,2016,22(2):337-345.
[5]谢芳,韩晓日,杨劲峰,等.不同施氮处理对水稻氮素吸收及产量的影响.中国土壤与肥料,2010(4):24-26.
[6]田永超,杨杰,姚霞,等.水稻高光谱红边位置与叶层氮浓度的关系.作物学报,2009,35(9):1681-1690.
[7]冯伟,朱艳,姚霞,等.利用红边特征参数监测小麦叶片氮素积累状况.农业工程学报,2009,25(11):194-201.
[8] Richardson A J,Gausman H W,Cardenas R,et al. Relation of Light Reflectance to Histological and Physical Evaluations of Cotton Leaf Maturity. Applied Optics,1970,9(3):545-52.
[9]田永超,杨杰,姚霞,等.利用红边面积形状参数估测水稻叶层氮浓度.植物生态学报,2009,33(4):791-801.
[10] Sims D A,Gamon J A. Relationships between leaf pigment content and spectral reflectance across a wide range of species,leaf structures and developmental stages. Remote Sensing of Environment,2002,81(2~3):337-354.
[11]唐延林,王人潮,黄敬峰,等.不同供氮水平下水稻高光谱及其红边特征研究.遥感学报,2004,8(2):185-192.
[12]夏天,吴文斌,周清波,等.不同地域冬小麦叶片SPAD高光谱估算研究.中国农业资源与区划,2014,35(4):49-57.
[13] Horler D N H,Dockray M,Barber J. The red edge of plant leaf reflectance. International Journal of Remote Sensing,1983,4(2):273-288.
[14]王人潮,陈铭臻,蒋亨显.水稻遥感估产的农学机理研究———Ⅰ.不同氮素水平的水稻光谱特征及其敏感波段的选择.浙江大学学报,1993(s1):9-16.
[15]谭昌伟,周清波,齐腊,等.水稻氮素营养高光谱遥感诊断模型.应用生态学报,2008,19(6):1261-1268.
[16]薛利红,曹卫星,罗卫红,等.基于冠层反射光谱的水稻群体叶片氮素状况监测.中国农业科学,2003,36(7):807-812.
[17] Tian Y C,Gu K J,Chu X,et al. comparison of different hyperspectral vegetation indices for canopy leaf nitrogen concentration estimation in rice. Plant&Soil,2014,376(1~2):193-209.
[18]郑立华,李民赞,潘娈,等.基于近红外光谱技术的土壤参数BP神经网络预测.光谱学与光谱分析,2008,28(5):1160-1164.
[19]林洁,陈效民,张勇,等.基于BP神经网络的太湖典型农田土壤水分动态模拟.南京农业大学学报,2012,35(4):140-144.
[20]徐小逊,张萍,徐精文,等.基于被动微波遥感和BP神经网络的土壤水分反演研究———以川中丘陵区为例.西南农业学报,2014,27(6):2478-2484.
[21]张娟娟,田永超,姚霞,等.基于高光谱的土壤全氮含量估测.自然资源学报,2011,26(5):881-890.
[22]李媛媛,常庆瑞,刘秀英,等.基于高光谱和BP神经网络的玉米叶片SPAD值遥感估算.农业工程学报,2016,32(16):135-142.
[23] L. Chen,J. F. Huang,F. M. Wang,et al. comparison between back propagation neural network and regression models for the estimation of pigment content in rice leaves and panicles using hyperspectral data. International Journal of Remote Sensing,2007,28(16):3457-3478.
[24] Kira O,Linker R,Gitelson A. Non-destructive estimation of foliar chlorophyll and carotenoid contents:Focus on informative spectral bands.International Journal of Applied Earth Observations&Geoinformation,2015,38:251-260.
[25]周冬琴,朱艳,田永超,等.以冠层反射光谱监测水稻叶片氮积累量的研究.作物学报,2006,32(9):1316-1322.
[26]史冰全,张晓丽,白雪琪,等.基于“三边”参数的油松林叶绿素估算模型.东北林业大学学报,2015(5):80-83.
[27]秦占飞,常庆瑞,申健,等.引黄灌区水稻红边特征及SPAD高光谱预测模型.武汉大学学报,2016,41(9):1168-1175.
[28]田永超,杨杰,姚霞,等.利用叶片高光谱指数预测水稻群体叶层全氮含量.作物学报,2010,36(9):1529-1537.
[2]周冬琴,田永超,姚霞,等.水稻叶片全氮浓度与冠层反射光谱的定量关系.应用生态学报,2008,19(2):337-344.
[3] Ju X T,Xing G X,Chen X P,et al. Reducing Environmental Risk by Improving N Management in Intensive Chinese Agricultural Systems.Proceedings of the National Academy of Sciences of the United States of America,2009,106(9):3041.
[4]郭腾飞,梁国庆,周卫,等.施肥对稻田温室气体排放及土壤养分的影响.植物营养与肥料学报,2016,22(2):337-345.
[5]谢芳,韩晓日,杨劲峰,等.不同施氮处理对水稻氮素吸收及产量的影响.中国土壤与肥料,2010(4):24-26.
[6]田永超,杨杰,姚霞,等.水稻高光谱红边位置与叶层氮浓度的关系.作物学报,2009,35(9):1681-1690.
[7]冯伟,朱艳,姚霞,等.利用红边特征参数监测小麦叶片氮素积累状况.农业工程学报,2009,25(11):194-201.
[8] Richardson A J,Gausman H W,Cardenas R,et al. Relation of Light Reflectance to Histological and Physical Evaluations of Cotton Leaf Maturity. Applied Optics,1970,9(3):545-52.
[9]田永超,杨杰,姚霞,等.利用红边面积形状参数估测水稻叶层氮浓度.植物生态学报,2009,33(4):791-801.
[10] Sims D A,Gamon J A. Relationships between leaf pigment content and spectral reflectance across a wide range of species,leaf structures and developmental stages. Remote Sensing of Environment,2002,81(2~3):337-354.
[11]唐延林,王人潮,黄敬峰,等.不同供氮水平下水稻高光谱及其红边特征研究.遥感学报,2004,8(2):185-192.
[12]夏天,吴文斌,周清波,等.不同地域冬小麦叶片SPAD高光谱估算研究.中国农业资源与区划,2014,35(4):49-57.
[13] Horler D N H,Dockray M,Barber J. The red edge of plant leaf reflectance. International Journal of Remote Sensing,1983,4(2):273-288.
[14]王人潮,陈铭臻,蒋亨显.水稻遥感估产的农学机理研究———Ⅰ.不同氮素水平的水稻光谱特征及其敏感波段的选择.浙江大学学报,1993(s1):9-16.
[15]谭昌伟,周清波,齐腊,等.水稻氮素营养高光谱遥感诊断模型.应用生态学报,2008,19(6):1261-1268.
[16]薛利红,曹卫星,罗卫红,等.基于冠层反射光谱的水稻群体叶片氮素状况监测.中国农业科学,2003,36(7):807-812.
[17] Tian Y C,Gu K J,Chu X,et al. comparison of different hyperspectral vegetation indices for canopy leaf nitrogen concentration estimation in rice. Plant&Soil,2014,376(1~2):193-209.
[18]郑立华,李民赞,潘娈,等.基于近红外光谱技术的土壤参数BP神经网络预测.光谱学与光谱分析,2008,28(5):1160-1164.
[19]林洁,陈效民,张勇,等.基于BP神经网络的太湖典型农田土壤水分动态模拟.南京农业大学学报,2012,35(4):140-144.
[20]徐小逊,张萍,徐精文,等.基于被动微波遥感和BP神经网络的土壤水分反演研究———以川中丘陵区为例.西南农业学报,2014,27(6):2478-2484.
[21]张娟娟,田永超,姚霞,等.基于高光谱的土壤全氮含量估测.自然资源学报,2011,26(5):881-890.
[22]李媛媛,常庆瑞,刘秀英,等.基于高光谱和BP神经网络的玉米叶片SPAD值遥感估算.农业工程学报,2016,32(16):135-142.
[23] L. Chen,J. F. Huang,F. M. Wang,et al. comparison between back propagation neural network and regression models for the estimation of pigment content in rice leaves and panicles using hyperspectral data. International Journal of Remote Sensing,2007,28(16):3457-3478.
[24] Kira O,Linker R,Gitelson A. Non-destructive estimation of foliar chlorophyll and carotenoid contents:Focus on informative spectral bands.International Journal of Applied Earth Observations&Geoinformation,2015,38:251-260.
[25]周冬琴,朱艳,田永超,等.以冠层反射光谱监测水稻叶片氮积累量的研究.作物学报,2006,32(9):1316-1322.
[26]史冰全,张晓丽,白雪琪,等.基于“三边”参数的油松林叶绿素估算模型.东北林业大学学报,2015(5):80-83.
[27]秦占飞,常庆瑞,申健,等.引黄灌区水稻红边特征及SPAD高光谱预测模型.武汉大学学报,2016,41(9):1168-1175.
[28]田永超,杨杰,姚霞,等.利用叶片高光谱指数预测水稻群体叶层全氮含量.作物学报,2010,36(9):1529-1537.