Potential of Fluorescence Index Derived from the Slope Characteristics of Laser-Induced Chlorophyll Fluorescence Spectrum for Rice Leaf Nitrogen Concentration Estimation

Yang, Jian; Du, Lina; Shi, Shuo; Gong, Wei; Sun, Jiayue; Chen, Biwu

doi:10.3390/app9050916

Cited by 7 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LIF was also successfully applied to study the effects of dimethoate on physiological and growth responses of pigeon pea plants and to measure out its application (Pandey et al, 2015 ). A fluorescent index was also proposed to estimate leaf nitrogen concentration in rice (Yang et al, 2019 ). In particular, differently to reflectance measurements (see sections 2.2 and 2.5), the signal is not affected by soil properties; so, ChlF sensors can be applied to estimate Chl content (linked to nitrogen availability) even in the early crop stages (after plant emergence or transplant) or in sparse soil coverage conditions (Casa et al, 2016 ).…”

Section: Remote Sensing Qualitative Methods For Stress Assessmentmentioning

confidence: 99%

Past and Future of Plant Stress Detection: An Overview From Remote Sensing to Positron Emission Tomography

Galieni¹,

D’Ascenzo

Stagnari

et al. 2021

Front. Plant Sci.

View full text Add to dashboard Cite

Plant stress detection is considered one of the most critical areas for the improvement of crop yield in the compelling worldwide scenario, dictated by both the climate change and the geopolitical consequences of the Covid-19 epidemics. A complicated interconnection of biotic and abiotic stressors affect plant growth, including water, salt, temperature, light exposure, nutrients availability, agrochemicals, air and soil pollutants, pests and diseases. In facing this extended panorama, the technology choice is manifold. On the one hand, quantitative methods, such as metabolomics, provide very sensitive indicators of most of the stressors, with the drawback of a disruptive approach, which prevents follow up and dynamical studies. On the other hand qualitative methods, such as fluorescence, thermography and VIS/NIR reflectance, provide a non-disruptive view of the action of the stressors in plants, even across large fields, with the drawback of a poor accuracy. When looking at the spatial scale, the effect of stress may imply modifications from DNA level (nanometers) up to cell (micrometers), full plant (millimeters to meters), and entire field (kilometers). While quantitative techniques are sensitive to the smallest scales, only qualitative approaches can be used for the larger ones. Emerging technologies from nuclear and medical physics, such as computed tomography, magnetic resonance imaging and positron emission tomography, are expected to bridge the gap of quantitative non-disruptive morphologic and functional measurements at larger scale. In this review we analyze the landscape of the different technologies nowadays available, showing the benefits of each approach in plant stress detection, with a particular focus on the gaps, which will be filled in the nearby future by the emerging nuclear physics approaches to agriculture.

show abstract

Section: Remote Sensing Qualitative Methods For Stress Assessmentmentioning

confidence: 99%

Past and Future of Plant Stress Detection: An Overview From Remote Sensing to Positron Emission Tomography

Galieni¹,

D’Ascenzo

Stagnari

et al. 2021

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…In this study, a three-layer neural network was selected to analyse the LNC based on the built inverse model. According to previous research [11], the 'trainbr' was used to serve as the training function. In addition, the size of hidden layer was set as four in this model.…”

Section: Methodsmentioning

confidence: 99%

“…Based on the passive hyperspectral remote sensing technology, studies have been conducted by some scholars to build different models to obtain more accurate biochemical parameter estimation. They proposed different vegetation indices based on statistical analysis models for estimating biochemical parameters or crops yields [10][11][12][13]. However, passive hyperspectral technology is difficult to acquire the spatial information.…”

Section: Introductionmentioning

confidence: 99%

Estimating leaf nitrogen concentration based on the combination with fluorescence spectrum and first-derivative

Yang

Gong

et al. 2020

R. Soc. open sci.

Self Cite

View full text Add to dashboard Cite

Leaf nitrogen concentration (LNC) is a major indicator in the estimation of the crop growth status which has been diffusely applied in remote sensing. Thus, it is important to accurately obtain LNC by using passive or active technology. Laser-induced fluorescence can be applied to monitor LNC in crops through analysing the changing of fluorescence spectral information. Thus, the performance of fluorescence spectrum (FS) and first-derivative fluorescence spectrum (FDFS) for paddy rice (Yangliangyou 6 and Manly Indica) LNC estimation was discussed, and then the proposed FS + FDFS was used to monitor LNC by multivariate analysis. The results showed that the difference between FS ( R 2 = 0.781, s.d. = 0.078) and FDFS ( R 2 = 0.779, s.d. = 0.097) for LNC estimation by using the artificial neural network is not obvious. The proposed FS + FDFS can improved the accuracy of LNC estimation to some extent ( R 2 = 0.813, s.d. = 0.051). Then, principal component analysis was used in FS and FDFS, and extracted the main fluorescence characteristics. The results indicated that the proposed FS + FDFS exhibited higher robustness and stability for LNC estimation ( R 2 = 0.851, s.d. = 0.032) than that only using FS ( R 2 = 0.815, s.d. = 0.059) or FDFS ( R 2 = 0.801, s.d. = 0.065).

show abstract

“…On the other hand, Kuruvilla and Gunavathi [29] classified cancer using ANN-BP and obtained information that traingdx provided higher performance than traingda and traingdm functions. Then, Yang et al [30] studied leaf nitrogen concentration (LNC) estimates with trials of activation functions "trainrp," "trainbr," and "trainlm". The results demonstrated that trainrp provided optimal results and was more accurate than trainbr and trainlm.…”

Section: Introductionmentioning

confidence: 99%

Experimental Analysis of Training Parameters Combination of ANN Backpropagation for Climate Classification

Syaharuddin¹,

Fatmawati²,

Suprajitno³

2022

MMEP

View full text Add to dashboard Cite

Artificial Neural Networks are widely used in prediction activities and classification processes. However, the implementation on average only uses a network architecture with one hidden layer, while the development of architectures with two or three hidden layers has not been done much. This article discusses the process of developing ANN Backpropagation using a Matlab-based graphical user interface with three hidden layers combined with non-linear activation functions (logsig, tansig, tanh) and training functions (trainrp and trainlm) based on learning rate and momentum. Architecture was created to study climate change in the area around Lombok International Airport station by training on hydrological data (rainfall) from January 2012 to December 2021 with a data type of 10-day interval (36 data every year). The number of neurons in the first hidden layer was determined using the Hecht-Nielsen model, while the second and third hidden layers used the Lawrence-Fredrickson model. Simulation results with architecture 36-73-37-19-1, a learning rate of 0.1, and momentum of 0.9 showed that variations in the activation function logsig-logsig-logsig-purelin and trainlm function demonstrated the best result with epoch of 7, MSE of 0.00090, and RMSE of 0.03011 in the training process and epoch of 5, MSE of 0.003758, and RMSE of 0.0613 in the data testing process. Furthermore, the prediction results demonstrated that a Q-value of 0.222 based on the Schmidt-Ferguson criteria obtained higher rainfall intensity information than previous years with climate category B (wet). Therefore, the government must be careful in determining policies related to field activities especially in agriculture because of climatic conditions with high rainfall.

show abstract

Potential of Fluorescence Index Derived from the Slope Characteristics of Laser-Induced Chlorophyll Fluorescence Spectrum for Rice Leaf Nitrogen Concentration Estimation

Cited by 7 publications

References 37 publications

Past and Future of Plant Stress Detection: An Overview From Remote Sensing to Positron Emission Tomography

Past and Future of Plant Stress Detection: An Overview From Remote Sensing to Positron Emission Tomography

Estimating leaf nitrogen concentration based on the combination with fluorescence spectrum and first-derivative

Experimental Analysis of Training Parameters Combination of ANN Backpropagation for Climate Classification

Contact Info

Product

Resources

About