Rapid and large area acquisition of nitrogen(N)deficiency status is important for achieving the optimal fertilization of rice.Most existing studies,however,focus on the use of unmanned aerial vehicle(UAV)remote sensin...Rapid and large area acquisition of nitrogen(N)deficiency status is important for achieving the optimal fertilization of rice.Most existing studies,however,focus on the use of unmanned aerial vehicle(UAV)remote sensing to diagnose N nutrition in rice,while there are fewer studies on the quantitative description of the degree of N deficiency in rice,and the effects of the critical N concentration on the spectral changes in rice have rarely been explored.Therefore,based on the canopy spectral data obtained by remotely-sensed UAV hyperspectral images,the N content in rice was obtained through field sampling.The construction method of the rice curve for the northeastern critical N concentration was studied,and on this basis,N deficiency was determined.Taking the spectrum of the critical N concentration state as the standard spectrum,the spectral reflectivity data were transformed by the ratios and differences,and the feature extraction of the spectral data was carried out by the successive projections algorithm(SPA).Finally,by taking the characteristic band as the input variable and N deficiency as the output variable,a set of multivariate linear regression(MLR),long short-term memory(LSTM)inversion models based on extreme learning machine(ELM),and the nondominated sorting genetic algorithmⅢextreme learning machine(NSGA-Ⅲ-ELM)were constructed.The results showed two key aspects of this system:1)The correlation between the N deficiency data and original spectrum was poor,but the correlation between the N deficiency data and N deficiency could be improved by a difference change and ratio transformation;2)The inversion results based on the ratio spectrum and NSGA-Ⅲ-ELM algorithm were the best,as the R2values of the training set and validation set were 0.852 and 0.810,and the root mean square error(RMSE)values were 0.291 and 0.308,respectively.From the perspective of the spectral data,the inversion accuracy of the ratio spectrum was better than the accuracy of the original spectrum or difference spectrum.At the algorithm level,the model inversion results based on LSTM algorithms showed a serious overfitting phenomenon and poor inversion effect.The inversion accuracy based on the NSGA-Ⅲ-ELM algorithm was better than the accuracy of the MLR algorithm or the ELM algorithm.Therefore,the inversion model based on the ratio spectrum and NSGA-Ⅲ-ELM algorithm could effectively invert the N deficiency in rice and provide critical technical support for accurate topdressing based on the N status in the rice.展开更多
Field experiments of nitrogen(N)treatment at five different application rates(0,75,150,225,and 300 kg ha^(-1))were conducted under pot-seedling mechanical transplanting(PMT)in 2018 and 2019.Two high-quality and high-y...Field experiments of nitrogen(N)treatment at five different application rates(0,75,150,225,and 300 kg ha^(-1))were conducted under pot-seedling mechanical transplanting(PMT)in 2018 and 2019.Two high-quality and high-yielding hybrids of indica rice,Huiliangyou 898 and Y Liangyou 900,were used in this study.The N nutrition index(NNI)and accumulated N deficit(N_(and)),used to assess the N nutrition status in real-time,were calculated for the indica cultivars under PMT with a critical nitrogen concentration(N_(c))dilution model based on shoot dry matter(DM)during the whole rice growth stage.The relationships between NNI and N_(and) with relative yield(RY)were determined,and accurate N application schemes were developed for hybrids indica rice under PMT.The results indicated that high application rate of N-fertilizer significantly increased the concentrations of shoot DM and N in aboveground organs during the observed stages in the two cultivars for two years(P<0.05).The N_(c) dilution model of hybrid indica cultivars was N_(c)=4.02 DM^(-0.42)(R^(2)=0.97)combining the two cultivars under PMT.Root-mean-square error and normalized root-mean-square error of the curve verification were 0.23 and 10.61%,respectively.The NNI and Nand ranged from 0.58 to 1.31 and 109 to–55 kg ha^(-1),respectively,in the two cultivars for all N treatments.NNI showed a linear relationship with Nand during the entire growth stage(0.53<R^(2)<0.99,P<0.01).In addition,NNI showed a linear-plateau relationship with RY(0.73<R<0.92,P<0.01)throughout the observed stages.These results suggest that the models can accurately diagnose the N-nutrition status and support effective N-fertilizer management in real-time for hybrid indica rice under PMT.展开更多
The nitrogen nutrition index(NNI)is a reliable indicator for diagnosing crop nitrogen(N)status.However,there is currently no specific vegetation index for the NNI inversion across multiple growth periods.To overcome t...The nitrogen nutrition index(NNI)is a reliable indicator for diagnosing crop nitrogen(N)status.However,there is currently no specific vegetation index for the NNI inversion across multiple growth periods.To overcome the limitations of the traditional direct NNI inversion method(NNI_(T1))of the vegetation index and traditional indirect NNI inversion method(NNI_(T2))by inverting intermediate variables including the aboveground dry biomass(AGB)and plant N concentration(PNC),this study proposed a new NNI remote sensing index(NNI_(RS)).A remote-sensing-based critical N dilution curve(Nc_(_RS))was set up directly from two vegetation indices and then used to calculate NNI_(RS).Field data including AGB,PNC,and canopy hyperspectral data were collected over four growing seasons(2012–2013(Exp.1),2013–2014(Exp.2),2014–2015(Exp.3),2015–2016(Exp.4))in Beijing,China.All experimental datasets were cross-validated to each of the NNI models(NNI_(T1),NNI_(T2)and NNI_(RS)).The results showed that:(1)the NNI_(RS)models were represented by the standardized leaf area index determining index(sLAIDI)and the red-edge chlorophyll index(CI_(red edge))in the form of NNI_(RS)=CI_(red edge)/(a×sLAIDI~b),where"a"equals 2.06,2.10,2.08 and 2.02 and"b"equals 0.66,0.73,0.67 and 0.62 when the modeling set data came from Exp.1/2/4,Exp.1/2/3,Exp.1/3/4,and Exp.2/3/4,respectively;(2)the NNI_(RS)models achieved better performance than the other two NNI revised methods,and the ranges of R2 and RMSE were 0.50–0.82 and 0.12–0.14,respectively;(3)when the remaining data were used for verification,the NNI_(RS)models also showed good stability,with RMSE values of 0.09,0.18,0.13 and 0.10,respectively.Therefore,it is concluded that the NNI_(RS)method is promising for the remote assessment of crop N status.展开更多
基金supported by grants from the Key Project of Liaoning Provincial Department of Education,China(LSNZD202005)。
文摘Rapid and large area acquisition of nitrogen(N)deficiency status is important for achieving the optimal fertilization of rice.Most existing studies,however,focus on the use of unmanned aerial vehicle(UAV)remote sensing to diagnose N nutrition in rice,while there are fewer studies on the quantitative description of the degree of N deficiency in rice,and the effects of the critical N concentration on the spectral changes in rice have rarely been explored.Therefore,based on the canopy spectral data obtained by remotely-sensed UAV hyperspectral images,the N content in rice was obtained through field sampling.The construction method of the rice curve for the northeastern critical N concentration was studied,and on this basis,N deficiency was determined.Taking the spectrum of the critical N concentration state as the standard spectrum,the spectral reflectivity data were transformed by the ratios and differences,and the feature extraction of the spectral data was carried out by the successive projections algorithm(SPA).Finally,by taking the characteristic band as the input variable and N deficiency as the output variable,a set of multivariate linear regression(MLR),long short-term memory(LSTM)inversion models based on extreme learning machine(ELM),and the nondominated sorting genetic algorithmⅢextreme learning machine(NSGA-Ⅲ-ELM)were constructed.The results showed two key aspects of this system:1)The correlation between the N deficiency data and original spectrum was poor,but the correlation between the N deficiency data and N deficiency could be improved by a difference change and ratio transformation;2)The inversion results based on the ratio spectrum and NSGA-Ⅲ-ELM algorithm were the best,as the R2values of the training set and validation set were 0.852 and 0.810,and the root mean square error(RMSE)values were 0.291 and 0.308,respectively.From the perspective of the spectral data,the inversion accuracy of the ratio spectrum was better than the accuracy of the original spectrum or difference spectrum.At the algorithm level,the model inversion results based on LSTM algorithms showed a serious overfitting phenomenon and poor inversion effect.The inversion accuracy based on the NSGA-Ⅲ-ELM algorithm was better than the accuracy of the MLR algorithm or the ELM algorithm.Therefore,the inversion model based on the ratio spectrum and NSGA-Ⅲ-ELM algorithm could effectively invert the N deficiency in rice and provide critical technical support for accurate topdressing based on the N status in the rice.
基金the National Key R&D Program of China(2016YFD0300608,2016YFD0300505 and 2017YFD0301305)the Key Research and Development Program of Anhui Province,China(1804h07020150)。
文摘Field experiments of nitrogen(N)treatment at five different application rates(0,75,150,225,and 300 kg ha^(-1))were conducted under pot-seedling mechanical transplanting(PMT)in 2018 and 2019.Two high-quality and high-yielding hybrids of indica rice,Huiliangyou 898 and Y Liangyou 900,were used in this study.The N nutrition index(NNI)and accumulated N deficit(N_(and)),used to assess the N nutrition status in real-time,were calculated for the indica cultivars under PMT with a critical nitrogen concentration(N_(c))dilution model based on shoot dry matter(DM)during the whole rice growth stage.The relationships between NNI and N_(and) with relative yield(RY)were determined,and accurate N application schemes were developed for hybrids indica rice under PMT.The results indicated that high application rate of N-fertilizer significantly increased the concentrations of shoot DM and N in aboveground organs during the observed stages in the two cultivars for two years(P<0.05).The N_(c) dilution model of hybrid indica cultivars was N_(c)=4.02 DM^(-0.42)(R^(2)=0.97)combining the two cultivars under PMT.Root-mean-square error and normalized root-mean-square error of the curve verification were 0.23 and 10.61%,respectively.The NNI and Nand ranged from 0.58 to 1.31 and 109 to–55 kg ha^(-1),respectively,in the two cultivars for all N treatments.NNI showed a linear relationship with Nand during the entire growth stage(0.53<R^(2)<0.99,P<0.01).In addition,NNI showed a linear-plateau relationship with RY(0.73<R<0.92,P<0.01)throughout the observed stages.These results suggest that the models can accurately diagnose the N-nutrition status and support effective N-fertilizer management in real-time for hybrid indica rice under PMT.
基金supported by the earmarked fund for China Agriculture Research System(CARS-03)the National Key Research and Development Program of China(2017YFD0201501 and 2016YFD020060306)the National Natural Science Foundation of China(41701375 and 61661136003)。
文摘The nitrogen nutrition index(NNI)is a reliable indicator for diagnosing crop nitrogen(N)status.However,there is currently no specific vegetation index for the NNI inversion across multiple growth periods.To overcome the limitations of the traditional direct NNI inversion method(NNI_(T1))of the vegetation index and traditional indirect NNI inversion method(NNI_(T2))by inverting intermediate variables including the aboveground dry biomass(AGB)and plant N concentration(PNC),this study proposed a new NNI remote sensing index(NNI_(RS)).A remote-sensing-based critical N dilution curve(Nc_(_RS))was set up directly from two vegetation indices and then used to calculate NNI_(RS).Field data including AGB,PNC,and canopy hyperspectral data were collected over four growing seasons(2012–2013(Exp.1),2013–2014(Exp.2),2014–2015(Exp.3),2015–2016(Exp.4))in Beijing,China.All experimental datasets were cross-validated to each of the NNI models(NNI_(T1),NNI_(T2)and NNI_(RS)).The results showed that:(1)the NNI_(RS)models were represented by the standardized leaf area index determining index(sLAIDI)and the red-edge chlorophyll index(CI_(red edge))in the form of NNI_(RS)=CI_(red edge)/(a×sLAIDI~b),where"a"equals 2.06,2.10,2.08 and 2.02 and"b"equals 0.66,0.73,0.67 and 0.62 when the modeling set data came from Exp.1/2/4,Exp.1/2/3,Exp.1/3/4,and Exp.2/3/4,respectively;(2)the NNI_(RS)models achieved better performance than the other two NNI revised methods,and the ranges of R2 and RMSE were 0.50–0.82 and 0.12–0.14,respectively;(3)when the remaining data were used for verification,the NNI_(RS)models also showed good stability,with RMSE values of 0.09,0.18,0.13 and 0.10,respectively.Therefore,it is concluded that the NNI_(RS)method is promising for the remote assessment of crop N status.