A Neural Network Model of Maize Crop Nitrogen Stress Assessment for a Multi-spectral Imaging Sensor

Noh, Hyun Ho; Zhang, Q.; Shin, Beom Soo; Han, Song; Liu, Feng

doi:10.1016/j.biosystemseng.2006.04.009

Cited by 61 publications

(29 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Por outro lado, o medidor de clorofila utilizado no trabalho exige contato físico com as folhas, o que, muitas vezes, leva à coleta de dados em poucos pontos no campo, o que pode acarretar indicação inadequada da distribuição espacial do estado nutricional da cultura (NOH et al, 2006). Ressalta-se, entretanto, que já se encontram disponíveis no mercado medidores de clorofila capazes de coletar os dados sem necessidade de contato físico.…”

Section: Resultsunclassified

“…A principal desvantagem das câmeras digitais é a menor resolução espectral em relação aos radiômetros, mas é uma limitação que pode ser contornada pela utilização de filtros específicos na câmera. Dados coletados com câmeras digitais podem ser utilizados para detectar níveis de estresse nutricional por nitrogênio, em tempo real, para a adubação em cobertura (NOH et al, 2006). Com o objetivo de minimizar variações causadas por fatores externos e promover o realce dos objetos de interesse, podem ser utilizados índices espectrais (HABOUDANE et al, 2002), que são combinações entre bandas espectrais.…”

Section: Introductionunclassified

See 1 more Smart Citation

Discriminação entre estágios nutricionais na cultura do trigo com técnicas de visão artificial e medidor portátil de clorofila

et al. 2008

View full text Add to dashboard Cite

RESUMO:O ajuste da adubação nitrogenada é um tema que suscita preocupações econômicas e ambientais em todo o mundo. Isso decorre da elevada resposta das culturas, especialmente gramíneas, ao nitrogênio e da falta de métodos adequados de quantificação de sua disponibilidade no solo. Com o objetivo de avaliar a discriminação de três estágios nutricionais na cultura do trigo, foram utilizadas imagens digitais e um medidor portátil de clorofila (SPAD -502). Os dados foram coletados em três épocas (8; 14 e 20 dias após a adubação nitrogenada em cobertura -DAA), em parcelas de trigo submetidas a três doses de N (0; 30 e 60 kg ha -1 ). As imagens foram processadas para desenvolvimento dos classificadores multivariados, utilizando-se de nove índices espectrais com as combinações dos valores médios dos "pixels". Os dados de clorofila e N foliar foram utilizados para desenvolver classificadores univariados. Verificou-se que o sistema de visão artificial foi mais eficiente que o SPAD aos 8 DAA. Aos 14 e 20 DAA, a classificação univariada com os dados SPAD foi equivalente aos classificadores com dados de imagens. Com a utilização das imagens digitais, foi possível discriminar os estágios nutricionais oito dias após a primeira adubação nitrogenada em cobertura.PALAVRAS-CHAVE: agricultura de precisão, taxas variáveis, processamento de imagens. MACHINE VISION TECHNIQUES AND MULTIVARIATE CLASSIFIERS FOR NITROGEN FERTILIZATION DOSES DISCRIMINATION IN WHEATABSTRACT: Sidedress nitrogen fertilization is currently discussed throughout the world due to its economical and environmental implications. The cereal crops strongly respond to N application and there is a lack of current methods to determine N availability on the soil. The aim of this work was to evaluate the discrimination among three nutritional levels in wheat crop using digital images and a portable chlorophyll meter. Data were collected in plots with three levels of N (0; 30 and 60 kha -1 ) in three dates (8; 14 and 20 days after sidedress fertilization). The images were processed using nine spectral indices and elaborated multivariate classifiers based on the mean pixel values. The chlorophyll data and leaf nitrogen concentration were used in univariate classifiers. The classification using the machine vision techniques were better than the chlorophyll meter (SPAD) at 8 DAF, since the Kappa coefficient was better than a random classification. At 14 and 20 DAF there were no statistical differences between this type of data and the data from images. Using digital images it was possible discriminate the nutritional levels eight days after sidedress fertilization.

show abstract

Section: Resultsunclassified

Section: Introductionunclassified

Discriminação entre estágios nutricionais na cultura do trigo com técnicas de visão artificial e medidor portátil de clorofila

et al. 2008

View full text Add to dashboard Cite

show abstract

“…The accuracy of such a technique appeared to be easily affected by the low resolution and obvious soil background noises (Broge and Leblanc 2001). Noh et al (2006) adopted multispectral images to increase the sensitivity and improve the testing precision of nitrogen status in the crop. Visible and near-infrared spectroscopy was also used for a nondestructive detection of nitrogen in Chinese cabbage leaves, the stepwise multiple linear regression (SMLR) showed the highest determination coefficient (r 2 ) of 0.846 (Min et al 2006).…”

Section: Introductionmentioning

confidence: 99%

Quantification of Nitrogen Status in Rice by Least Squares Support Vector Machines and Reflectance Spectroscopy

Shao

Zhao

Bao

et al. 2009

Food Bioprocess Technol

View full text Add to dashboard Cite

The estimation of nitrogen status non-destructively in rice was performed using canopy spectral reflectance with visible and near-infrared reflectance (Vis/NIR) spectroscopy. The canopy spectral reflectance of rice grown with different levels of nitrogen inputs was determined at several important growth stages. This study was conducted at the experiment farm of Zhejiang University, Hangzhou, China. The soil plant analysis development (SPAD) value was used as a reference data that indirectly reflects nitrogen status in rice. A total of 64 rice samples were used for Vis/NIR spectroscopy at 325-1075 nm using a field spectroradiometer, and chemometrics of partial least square (PLS) was used for regression. The correlation coefficient (r), root mean square error of prediction, and bias in prediction set by PLS were, respectively, 0.8545, 0.7628, and 0.0521 for SPAD value prediction in tillering stage, 0.9082, 0.4452, and −0.0109 in booting stage, and 0.8632, 0.7469, and 0.0324 in heading stage. Least squares support vector machine (LS-SVM) model was compared with PLS and back propagation neural network methods. The results showed that LS-SVM was superior to the conventional linear and non-linear methods in predicting SPAD values of rice. Independent component analysis was executed to select several sensitive wavelengths (SWs) based on loading weights; the optimal LS-SVM model was achieved with SWs of 560, 575-580, 700, 730, and 740 nm for SPAD value prediction in booting stage. It is concluded that Vis/NIR spectroscopy combined with LS-SVM regression method is a promising technique to monitor nitrogen status in rice.

show abstract

“…Anna Chlingaryan et al conducted a survey of machine learning approaches for crop yield with respect to estimation of nitrogen status in precision agriculture, which included various technologies and ML techniques, such as back-propagation Neural Network, combination of CNN or LSTM with Gaussian Processes, M5-Prime Regression Trees, and Least Squares Vector Machine [17]. H. Noh et al estimated crop nitrogen status during side-dressing operations [18]. The authors used a neural network model to evaluate maize leaf based on the sensed reflectance of the maize canopy in three channels, including green and red colors and the near-infrared (NIR) range of a multi-spectral charge-coupled device camera.…”

Section: Introduction and Related Workmentioning

confidence: 99%

A Comparative Study of Deep CNN in Forecasting and Classifying the Macronutrient Deficiencies on Development of Tomato Plant

Tran

Choi

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

During the process of plant growth, such as during the flowering stages and fruit development, the plants need to be provided with the various minerals and nutrients to grow. Nutrient deficiency is the cause of serious diseases in plant growth, affecting crop yield. In this article, we employed artificial neural network models to recognize, classify, and predict the nutritional deficiencies occurring in tomato plants (Solanum lycopersicum L.). To classify and predict the different macronutrient deficiencies in the cropping process, this paper handles the captured images of the macronutrient deficiency. This deficiency during the fruiting and leafing phases of tomato plant are based on a deep convolutional neural network (CNN). A total of 571 images were captured with tomato leaves and fruits containing the crop species at the growth stage. Among all images, 80% (461 captured images) were used for the training dataset and 20% (110 captured images) were applied for the validation dataset. In this study, we provide an analysis of two different model architectures based on convolutional neural network for classifying and predicting the nutrient deficiency symptoms. For instance, Inception-ResNet v2 and Autoencoder with the captured images of tomato plant growth under the greenhouse conditions. Moreover, a major type of statistical structure, namely Ensemble Averaging, was applied with two aforementioned predictive models to increase the accuracy of predictive validation. Three mineral nutrients, i.e., Calcium/Ca2+, Potassium/K+, and Nitrogen/N, are considered for use in evaluating the nutrient status in the development of tomato plant with these models. The aim of this study is to predict the nutrient deficiency accurately in order to increase crop production and prevent the emergence of tomato pathology caused by lack of nutrients. The predictive performance of the three models in this paper are validated, with the accuracy rates of 87.273% and 79.091% for Inception-ResNet v2 and Autoencoder, respectively, and with 91% validity using Ensemble Averaging.

show abstract

A Neural Network Model of Maize Crop Nitrogen Stress Assessment for a Multi-spectral Imaging Sensor

Cited by 61 publications

References 13 publications

Discriminação entre estágios nutricionais na cultura do trigo com técnicas de visão artificial e medidor portátil de clorofila

Discriminação entre estágios nutricionais na cultura do trigo com técnicas de visão artificial e medidor portátil de clorofila

Quantification of Nitrogen Status in Rice by Least Squares Support Vector Machines and Reflectance Spectroscopy

A Comparative Study of Deep CNN in Forecasting and Classifying the Macronutrient Deficiencies on Development of Tomato Plant

Contact Info

Product

Resources

About