Analysis of the perpendicular structure of vegetation by spectral reflectance in the visible and near Infrared

The purpose of this study is to determine a method for quickly and accurately estimating the chlorophyll content of peanut plants at different plant densities. This was explored using leaf spectral reflectance to monitor peanut chlorophyll content to detect sensitive spectral bands and the optimum spectral indicators to establish a quantitative model. Peanut plants under different plant density conditions were monitored during three consecutive growth periods; single-photon avalanche diode (SPAD) and hyperspectral data derived from the leaves under the different plant density conditions were recorded. By combining arbitrary bands, indices were constructed across the full spectral range (350–2500 nm) based on blade spectra: the normalized difference spectral index (NDSI), ratio spectral index (RSI), difference spectral index (DSI) and soil-adjusted spectral index (SASI). This enabled the best vegetation index reflecting peanut-leaf SPAD values to be screened out by quantifying correlations with chlorophyll content, and the peanut leaf SPAD estimation models established by regression analysis to be compared and analyzed. The results showed that the chlorophyll content of peanut leaves decreased when plant density was either too high or too low, and that it reached its maximum at the appropriate plant density. In addition, differences in the spectral reflectance of peanut leaves under different chlorophyll content levels were highly obvious. Without considering the influence of cell structure as chlorophyll content increased, leaf spectral reflectance in the visible (350–700 nm): near-infrared (700–1300 nm) ranges also increased. The spectral bands sensitive to chlorophyll content were mainly observed in the visible and near-infrared ranges. The study results showed that the best spectral indicators for determining peanut chlorophyll content were NDSI (R520, R528), RSI (R748, R561), DSI (R758, R602) and SASI (R753, R624). Testing of these regression models showed that coefficient of determination values based on the NDSI, RSI, DSI and SASI estimation models were all greater than 0.65, while root mean square error values were all lower than 2.04. Therefore, the regression model established according to the above spectral indicators was a valid predictor of the chlorophyll content of peanut leaves.

Download Full-text

Deep Learning Application for Predicting Soil Organic Matter Content by VIS-NIR Spectroscopy

Computational Intelligence and Neuroscience ◽

10.1155/2019/3563761 ◽

2019 ◽

Vol 2019 ◽

pp. 1-11 ◽

Cited By ~ 1

Author(s):

Zhe Xu ◽

Xiaomin Zhao ◽

Xi Guo ◽

Jiaxin Guo

Keyword(s):

Organic Matter ◽

Deep Learning ◽

Infrared Spectroscopy ◽

Soil Organic Matter ◽

Near Infrared Spectroscopy ◽

Spectral Reflectance ◽

Near Infrared ◽

Spectral Variation ◽

Full Spectrum ◽

Reflectance Data

Deep learning is characterized by its strong ability of data feature extraction. This method can provide unique advantages when applying it to visible and near-infrared spectroscopy for predicting soil organic matter (SOM) content in those cases where the SOM content is negatively correlated with the spectral reflectance of soil. This study relied on the SOM content data of 248 red soil samples and their spectral reflectance data of 400–2450 nm in Fengxin County, Jiangxi Province (China) to meet three objectives. First, a multilayer perceptron and two convolutional neural networks (LeNet5 and DenseNet10) were used to predict the SOM content based on spectral variation and variable selection, and the outcomes were compared with that from the traditional back-propagation neural network (BPN). Second, the four methods were applied to full-spectrum modeling to test the difference to selected feature variables. Finally, the potential of direct modeling was evaluated using spectral reflectance data without any spectral variation. The results of prediction accuracy showed that deep learning performed better at predicting the SOM content than did the traditional BPN. Based on full-spectrum data, deep learning was able to obtain more feature information, thus achieving better and more stable results (i.e., similar average accuracy and far lower standard deviation) than those obtained through variable selection. DenseNet achieved the best prediction result, with a coefficient of determination (R2) = 0.892 ± 0.004 and a ratio of performance to deviation (RPD) = 3.053 ± 0.056 in validation. Based on DenseNet, the application of spectral reflectance data (without spectral variation) produced robust results for application-level purposes (validation R2 = 0.853 ± 0.007 and validation RPD = 2.639 ± 0.056). In conclusion, deep learning provides an effective approach to predict the SOM content by visible and near-infrared spectroscopy and DenseNet is a promising method for reducing the amount of data preprocessing.

Download Full-text

Spectral signature of brown rust and orange rust in sugarcane

Revista Facultad de Ingeniería Universidad de Antioquia ◽

10.17533/udea.redin.20191042 ◽

2020 ◽

pp. 9-20

Author(s):

Eniel Rodríguez-Machado ◽

Osmany Aday-Díaz ◽

Luis Hernández-Santana ◽

Jorge Luís Soca-Muñoz ◽

Rubén Orozco-Morales

Keyword(s):

Precision Agriculture ◽

Spectral Reflectance ◽

Vegetation Index ◽

Near Infrared ◽

Normalized Difference Vegetation Index ◽

Brown Rust ◽

Spectral Signature ◽

Spatial And Temporal Variability ◽

Mean Values ◽

Index Value

Precision agriculture, making use of the spatial and temporal variability of cultivable land, allows farmers to refine fertilization, control field irrigation, estimate planting productivity, and detect pests and disease in crops. To that end, this paper identifies the spectral reflectance signature of brown rust (Puccinia melanocephala) and orange rust (Puccinia kuehnii), which contaminate sugar cane leaves (Saccharum spp.). By means of spectrometry, the mean values and standard deviations of the spectral reflectance signature are obtained for five levels of contamination of the leaves in each type of rust, observing the greatest differences between healthy and diseased leaves in the red (R) and near infrared (NIR) bands. With the results obtained, a multispectral camera was used to obtain images of the leaves and calculate the Normalized Difference Vegetation Index (NDVI). The results identified the presence of both plagues by differentiating healthy from contaminated leaves through the index value with an average difference of 11.9% for brown rust and 9.9% for orange rust.

Download Full-text

Spectral reflectance characteristics of eucalypt foliage damaged by insects

Australian Journal of Botany ◽

10.1071/bt00091 ◽

2001 ◽

Vol 49 (6) ◽

pp. 687 ◽

Cited By ~ 55

Author(s):

C. Stone ◽

L. Chisholm ◽

N. Coops

Keyword(s):

Spectral Reflectance ◽

Near Infrared ◽

Leaf Age ◽

Electromagnetic Spectrum ◽

Similar Response ◽

Leaf Ontogeny ◽

Maximum Slope ◽

Mature Leaves ◽

Eucalypt Species ◽

Red Coloration

Variables related to foliar damage, leaf morphology, spectral reflectance, chlorophyll fluorescence and chlorophyll content were measured from leaves sampled from mature eucalypts exhibiting symptoms of crown dieback associated with bell miner colonisation located in Olney State Forest, near Wyong, New South Wales. Insect-damaged mature leaves and healthy young expanding leaves of some species exhibited a conspicuous red coloration caused by the presence of anthocyanin pigmentation. For the mature leaves, the level of red coloration was significantly correlated with insect herbivory and leaf necrosis. Significant correlations were also found between the level of red pigmentation and the following four spectral features: maximum reflectance at the green peak (550 nm); the wavelength position and maximum slope of the red edge (690–740 nm) and the maximum reflectance at 750 nm in the near-infrared portion of the electromagnetic spectrum. While it has been shown that anthocyanin pigments are synthesised in some eucalypt species in response to certain abiotic stresses causing photoinhibition and activation of photoprotective mechanisms, this work proposes that biotic agents such as leaf damaging insects and fungal pathogens may induce a similar response in eucalypt foliage resulting in increased levels of anthocyanins. The potential of anthocyanin levels to be related to leaf ontogeny for some eucalypt species was also illustrated in the reflectance spectra. Thus, it is essential that leaf age be considered. This work demonstrates that the identification of a number of key features of leaf spectra can provide a basis for the development of a robust forest health indicator that may be obtained from airborne or spaceborne hyperspectral sensors.

Download Full-text