First Derivative Spectra Research Articles

Experimental Observation of a Peculiar Effect in Electron Paramagnetic Resonance Spectra for Nitroxides Undergoing Fast Spin Exchange: Emission.

We report the experimental observation of an EPR spectral manifestation of spin exchange frequencies, ωex, larger than the 15N hyperfine separation, A0, predicted 50 years ago but previously not observed. For spectra with ωex/γA0 < 1, where γ is the gyromagnetic ratio of the electron, the spectrum consists of two "normal" spin modes each with one absorption and one dispersion component separated by Aabs < A0. Aabs decreases with ωex. In stark contrast, when ωex/γA0 > 1, the spectrum consists of two absorption spin modes, one of which is negative (emissive). We show that the experimental behavior of the spin modes agrees with theory: (a) the doubly integrated intensity of the first-derivative spectra remains constant because the increased intensity of the positive spin mode minus the negative emissive mode remains constant; (b) the value of the spin exchange rate constant Kex = ωex/C, where C is the molar concentration, is continuous through ωex/γA0 = 1.

Predicting leaf nitrogen content in wolfberry trees by hyperspectral transformation and machine learning for precision agriculture.

Leaf nitrogen content (LNC) is an important indicator for scientific diagnosis of the nutrition status of crops. It plays an important role in the growth, yield and quality of wolfberry. This study aimed to develop new spectral indices (NSIs) and constructed machine learning regression (MLR) models for predicting wolfberry tree LNC. By utilizing four smoothing methods and five mathematic transformation methods, we obtained the original spectral dataset and five spectral transformation datasets for quantitative analysis and model establishment. Subsequently, published vegetation indices (PVIs) were acquired, sensitive wavelengths (SWs) were screened and NSIs were calculated based on SWs. Then MLR models were constructed by combining NSIs from six spectral datasets with three machine learning algorithms. Finally, a comparison was made among the MLR models. The study indicated that the application of mathematical transformation highlighted the differences in spectra, the square root, first-derivative and second-derivative transformation improved the prediction accuracy of MLR models constructed based on NSIs (MLR-NSIs models). However, these transformations had little impact on improving the prediction ability of MLR models constructed based on PVIs (MLR-PVIs models). Additionally, The optimal model for predicting the LNC of wolfberry tree was obtained by using the Random Forest (RF) algorithm combined with NSIs developed by first-derivative transformation spectra. The determination coefficient of validation (Rv2) and ratio of percentage deviation (RPD) was 0.71 and 1.90, respectively. In conclusion, this study has demonstrated that the combination of hyperspectral transformation and machine learning is useful for improving the accuracy of LNC estimation in wolfberry trees.

Electron Paramagnetic Resonance, Electronic Ground State, and Electron Spin Relaxation of Seven Lanthanide Ions Bound to Lanmodulin and the Bioinspired Chelator, 3,4,3-LI(1,2-HOPO).

The electron paramagnetic resonance (EPR) spectra of lanthanide(III) ions besides Gd3+ , bound to small-molecule and protein chelators, are uncharacterized. Here, the EPR properties of 7 lanthanide(III) ions bound to the natural lanthanide-binding protein, lanmodulin (LanM), and the synthetic small-molecule chelator, 3,4,3-LI(1,2-HOPO) ("HOPO"), were systematically investigated. Echo-detected pulsed EPR spectra reveal intense signals from ions for which the normal continuous-wave first-derivative spectra are negligibly different from zero. Spectra of Kramers lanthanide ions Ce3+ , Nd3+ , Sm3+ , Er3+ , and Yb3+ , and non-Kramers Tb3+ and Tm3+ , bound to LanM are more similar to the ions in dilute aqueous:ethanol solution than to those coordinated with HOPO. Lanmodulins from two bacteria, with distinct metal-binding sites, had similar spectra for Tb3+ but different spectra for Nd3+ . Spin echo dephasing rates (1/Tm ) are faster for lanthanides than for most transition metals and limited detection of echoes to temperatures below ~6 to 12 K. Dephasing rates were environment dependent and decreased in the order water:ethanol>LanM>HOPO, which is attributed to decreasing librational motion. These results demonstrate that the EPR spectra and relaxation times of lanthanide(III) ions are sensitive to coordination environment, motivating wider application of these methods for characterization of both small-molecule and biomolecule interactions with lanthanides.

Characterization and classification of urban weed species in northeast China using terrestrial hyperspectral images

AbstractWeeds contribute to biodiversity and a wide range of ecosystem functions. It is crucial to map different weed species and analyze their physiological activities. Remote sensing techniques for plant identification, especially hyperspectral imaging, are being developed using spectral response patterns to vegetation for detection and species identification. A library of hyperspectral images of 40 urban weed species in northeast China was established in this study. A terrestrial hyperspectral camera was used to acquire 435 hyperspectral images. The hyperspectral information for each weed species was extracted and analyzed. The spectral characteristics and vegetation indices of different weeds revealed the differences between weed species in the cities of northeast China and indirectly characterized the growth and physiological activity levels of different species, but could not effectively distinguish different species. Five methods—first derivative spectrum (FDS), second derivative spectrum (SDS), standard normal variate (SNV), moving averages (MA), and Savitzky-Golay (SG) smoothing—were used to pretreat the spectral curves to maximize the retention of spectral characteristics while removing the influence of noise. We investigated the application of a convolutional neural network (CNN) with terrestrial hyperspectral remote sensing to identify urban weeds in northeast China. A CNN classification model was established to distinguish weeds from the hyperspectral images and demonstrated a test accuracy of 95.32% to 98.15%. The accuracy of the original spectrum was 97.45%; SNV had the best accuracy (98.15%) and SG was the least accurate (95.32%). This provides a baseline for understanding the hyperspectral characteristics of urban weed species and monitoring their growth. It also contributes to the development of a hyperspectral imaging database with global applicability.

Estimation of Winter Wheat Canopy Chlorophyll Content Based on Canopy Spectral Transformation and Machine Learning Method

Canopy chlorophyll content (CCC) is closely related to crop nitrogen status, crop growth and productivity, detection of diseases and pests, and final yield. Thus, accurate monitoring of chlorophyll content in crops is of great significance for decision support in precision agriculture. In this study, winter wheat in the Guanzhong Plain area of the Shaanxi Province, China, was selected as the research subject to explore the feasibility of canopy spectral transformation (CST) combined with a machine learning method to estimate CCC. A hyperspectral canopy ground dataset in situ was measured to construct CCC prediction models for winter wheat over three growth seasons from 2014 to 2017. Sensitive-band reflectance (SR) and narrow-band spectral index (NSI) were established based on the original spectrum (OS) and CSTs, including the first derivative spectrum (FDS) and continuum removal spectrum (CRS). Winter wheat CCC estimation models were constructed using univariate regression, partial least squares (PLS) regression, and random forest (RF) regression based on SR and NSI. The results demonstrated the reliability of CST combined with the machine learning method to estimate winter wheat CCC. First, compared with OS-SR (683 nm), FDS-SR (630 nm) and CRS-SR (699 nm) had a larger correlation coefficient between canopy reflectance and CCC; secondly, among the parametric regression methods, the univariate regression method with CRS-NDSI as the independent variable achieved satisfactory results in estimating the CCC of winter wheat; thirdly, as a machine learning regression method, RF regression combined with multiple independent variables had the best winter wheat CCC estimation accuracy (the determination coefficient of the validation set (Rv2) was 0.88, the RMSE of the validation set (RMSEv) was 3.35 and relative prediction deviation (RPD) was 2.88). Thus, this modeling method could be used as a basic method to predict the CCC of winter wheat in the Guanzhong Plain area.

Hyperspectral imaging with a band matrix reduction method to detect early drought stress in tomato

Drought stress is one of the key abiotic stresses affecting plant growth, crop yield and food quality. The main objective of this study is to investigate the potential effectiveness of hyperspectral imaging with band selection method for the rapid detection of the early drought stress of tomatoes. First, the unsupervised algorithm - K-means and statistical histogram are used to extract samples representing each experimental treatment group. Then, to solve problems related to the high redundancy and correlation of hyperspectral data, band matrix reduction method (BMRM) based on recursive feature elimination theory is proposed to determine the optimal band subset. The band matrix is constructed according to the band ranking obtained by the discrimination coefficient -Coefi, which is calculated from the average spectral curve and the first-derivative spectrum. Finally, the effectiveness of waveband selection algorithms was validated by comparison with successive projections algorithm, competitive adaptive reweighted sampling, recursive feature elimination with cross-validation and full spectrum. The results demonstrated that BMRM achieved higher classification accuracy with fewer bands selected, and the amount of calculation is not greatly improved. The proposed method provides a more accurate, and effective way of detecting early drought stress.

Estimation of Potato Above-Ground Biomass Using UAV-Based Hyperspectral images and Machine-Learning Regression

Above-ground biomass (AGB) is an important indicator for monitoring crop growth and plays a vital role in guiding agricultural management, so it must be determined rapidly and nondestructively. The present study investigated the extraction from UAV hyperspectral images of multiple variables, including canopy original spectra (COS), first-derivative spectra (FDS), vegetation indices (VIs), and crop height (CH) to estimate the potato AGB via the machine-learning methods of support vector machine (SVM), random forest (RF), and Gaussian process regression (GPR). High-density point clouds were combined with three-dimensional spatial information from ground control points by using structures from motion technology to generate a digital surface model (DSM) of the test field, following which CH was extracted based on the DSM. Feature bands in sensitive spectral regions of COS and FDS were automatically identified by using a Gaussian process regression-band analysis tool that analyzed the correlation of the COS and FDS with the AGB in each growth period. In addition, the 16 Vis were separately analyzed for correlation with the AGB of each growth period to identify highly correlated Vis and excluded highly autocorrelated variables. The three machine-learning methods were used to estimate the potato AGB at each growth period and their results were compared separately based on the COS, FDS, VIs, and combinations thereof with CH. The results showed that (i) the correlations of COS, FDS, and VIs with AGB all gradually improved when going from the tuber-formation stage to the tuber-growth stage and thereafter deteriorated. The VIs were most strongly correlated with the AGB, followed by FDS, and then by COS. (ii) The CH extracted from the DSM was consistent with the measured CH. (iii) For each growth stage, the accuracy of the AGB estimates produced by a given machine-learning method depended on the combination of model variables used (VIs, FDS, COS, and CH). (iv) For any given set of model variables, GPR produced the best AGB estimates in each growth period, followed by RF, and finally by SVM. (v) The most accurate AGB estimate was achieved in the tuber-growth stage and was produced by combining spectral information and CH and applying the GPR method. The results of this study thus reveal that UAV hyperspectral images can be used to extract CH and crop-canopy spectral information, which can be used with GPR to accurately estimate potato AGB and thereby accurately monitor crop growth.

Simultaneous analysis of patin fish oil (Pangasius micronemus) and bandeng (Chanos chanos) fish oil using FTIR spectroscopy and chemometrics

Patin fish (Pangasius micronemus) and bandeng fish (Chanos chanos) has high levels of oils containing essential fatty acids which are necessary for the human body. Therefore, quantitative analysis of fish oils extracted from patin fish and bandeng fish was very important. This research aimed to combine Fourier transform infrared (FTIR) spectroscopy with partial least square (PLS) and principal component regression (PCR) for simultaneous analysis of the binary mixture of patin fish oil (PFO) and bandeng fish oil (BFO). The method has consisted of extraction of both oils, preparation of calibration and validation samples, scanning of samples using FTIR spectrophotometer, and developing the calibration and validation models using PLS and PCR. The simultaneous analysis of PFO in a binary mixture with BFO was performed based on first derivative spectra at combined wavenumbers of 3050-2800, 1800-1700, and 1500-650 cm-1 assisted with PLS. In addition, BFO in binary mixtures with PFO was determined using the first derivative spectra using the same wavenumbers. The coefficient of determination for calibration (Rcal 2 ) and validation (Rval 2 ) were 0.9998 and 0.9994, with low errors (RMSEC = 0.0072 and RMSEP = 0.0121). The combination of FTIR spectroscopy with PLS using suitable wavenumbers can be potential tools for the simultaneous analysis of PFO and BFO.

Predicting the true density of commercial biomass pellets using near-infrared hyperspectral imaging

The use of biomass is increasing because it is a form of renewable energy that provides high heating value. Rapid measurements could be used to check the quality of biomass pellets during production. This research aims to apply a near-infrared (NIR) hyperspectral imaging system for the evaluation of the true density of individual biomass pellets during the production process. Real-time measurement of the true density could be beneficial for the operation settings, such as the ratio of the binding agent to the raw material, the temperature of operation, the production rate, and the mixing ratio. The true density could also be used for rough measurement of the bulk density, which is a necessary parameter in commercial production. Therefore, knowledge of the true density is required during production in order to maintain the pellet quality as well as operation conditions. A prediction model was developed using partial least squares (PLS) regression across different wavelengths selected using different spectral pre-treatment methods and variable selection methods. After model development, the performance of the models was compared. The best model for predicting the true density of individual pellets was developed with first-derivative spectra (D1) and variables selected by the genetic algorithm (GA) method, and the number of variables was reduced from 256 to 53 wavelengths. The model gave R2cal, R2val, SEC, SEP, and RPD values of 0.88, 0.89, 0.08 g/cm3, 0.07 g/cm3, and 3.04, respectively. The optimal prediction model was applied to construct distribution maps of the true density of individual biomass pellets, with the level of the predicted values displayed in colour bars. This imaging technique could be used to check visually the true density of biomass pellets during the production process for warnings to quality control equipment.

Prediction of soil organic matter using VNIR spectral parameters extracted from shape characteristics

Whether spectral feature parameters (SFPs) can be effectively used to predict soil organic matter (SOM), and its spatial transferability was tested for different regions. In this study, a hybrid model was proposed based on SFPs and local regression method. The topsoil spectra of 221 soil samples from Sanjiang Plain and 187 soil samples from Nong’an county in Northeast China were re-sampled (at 0.01 µm intervals) and converted to the first-derivative curves and CR curves. Two SFPs were extracted on reflectance curves (RSFPs), which were defined as curve length (Lc) and area (Ac) between two absorption positions. Local random forest models with k-means clustering were built using the RSFPs and first-derivative spectra for evaluating the feasibility of RSFPs in these two study areas. After analyzing the results of Chinese soil samples, this method was also applied to Land Use/Land Cover Area Frame Survey (LUCAS) topsoil database in order to evaluate the feasibility of RSFPs outside China. Our results revealed these: (1) high correlation between the RSFPs of soil samples with spectral characteristics of sandy soils and SOM; (2) the importance of Lc relative to Ac in SOM prediction is higher; and (3) SOM prediction using RSFPs is comparable to the first-derivative spectra, and the best result has an R2 of 0.76 and an RMSE of 7.43 g kg−1. Our results suggest that RSFPs can be used to predict SOM and have good spatial transferability after applying in two study areas. RSFPs with specific geometric meaning have high potential to predict other soil properties in Northeast China. Our results also provide a reference for SOM mapping using hyper-spectral satellites.

Airborne hyperspectral AVIRIS-NG data for vegetation carbon stock mapping based on red edge position parameter and narrowband vegetation indices in Sholayar reserve forest, Kerala

The biophysical and biochemical spectral responses in the form of red-edge position (REP) and narrowband indices for carbon stock mapping have been evaluated in this study using AVIRIS-NG data in Sholayar reserve forest, Kerala. Maximum first-derivative spectrum, linear four-point interpolation technique, and adjusted linear-extrapolation techniques were employed for REP estimation. Results exhibited a maximum peak of REP at 717 nm and two extreme dips at 677 nm and 772 nm. Regression analysis between field-based AGB with REP (R2 = 0.6537) and narrowband indices; EVI, ARVI, VRI, and RNDVI was adopted exhibiting significant correlations (R2=0.5100, R2=0.5106, R2=0.5220, and R2=0.5507, respectively) (P-value < 0.001). Results show that dry-deciduous plantations (mainly Tectona grandis) have the lowest AGB values of 25-100tons/hectare, whereas, Wet-evergreen forest exhibited the highest values (300-350tons/hectare). Correlation between plot-level AGB and predicted AGB being 0.7065. Conclusively, the retrieval of structural measures like biomass can be achieved through these methods using AVIRIS-NG data.

FT-MIR Analysis of Water-Soluble Extracts during the Ripening of Sheep Milk Cheese with Different Phospholipid Content

The purpose of this work was to study the suitability of the water-soluble extracts (WSE) of semi-hard sheep milk cheese for analysis by diffuse reflectance Fourier transform mid-infrared spectroscopy (FT-MIR) and the development of classification models using discriminant analysis and based on cheese age or phospholipid content. WSE was extracted from three types of sheep milk cheeses (full-fat, reduced-fat and reduced-fat fortified with lyophilized sweet sheep buttermilk) at various stages of ripening from six to 168 days and lyophilized. The first model used 1854–1381 and 1192–760 cm−1 regions of the first-derivative spectra and successfully differentiated samples of different age, based on changes in the water-soluble products of ripening biochemical events. The second model used the phospholipid absorbance spectral regions (3012–2851, 1854–1611 and 1192–909 cm−1) to successfully discriminate cheeses of markedly different phospholipid content. Cheese WSE was found suitable for FT-MIR analysis. According to the results, a fast and simple method to monitor cheese ripening based on water-soluble substances has been developed. Additionally, the results indicated that a considerable amount of phospholipids migrates to the cheese WSE and that FT-MIR can be a useful tool for their assessment.

Simulating Heat Stress of Coal Gangue Spontaneous Combustion on Vegetation Using Alfalfa Leaf Water Content Spectral Features as Indicators

Vegetation heat-stress assessment in the reclamation areas of coal gangue dumps is of great significance in controlling spontaneous combustion; through a temperature gradient experiment, we collected leaf spectra and water content data on alfalfa. We then obtained the optimal spectral features of appropriate leaf water content indicators through time series analysis, correlation analysis, and Lasso regression analysis. A spectral feature-based long short-term memory (SF-LSTM) model is proposed to estimate alfalfa’s heat stress level; the live fuel moisture content (LFMC) varies significantly with time and has high regularity. Correlation analysis of the raw spectrum, first-derivative spectrum, spectral reflectance indices, and leaf water content data shows that LFMC and spectral data were the most strongly correlated. Combined with Lasso regression analysis, the optimal spectral features were the first-derivative spectral value at 1661 nm (abbreviated as FDS (1661)), RVI (1525,1771), DVI (1412,740), and NDVI (1447,1803). When the classification strategies were divided into three categories and the time sequence length of the spectral features was set to five consecutive monitoring dates, the SF-LSTM model had the highest accuracy in estimating the heat stress level in alfalfa; the results provide an important theoretical basis and technical support for vegetation heat-stress assessment in coal gangue dump reclamation areas.

Development of derivative spectrophotometric method for simultaneous determination of pyrazinamide and rifampicin in cubosome formulation

The ultraviolet spectrophotometry analysis for quantitative assay of drugs is a method accurate, sensitive, selective and reproductive with the advantage of being a simple and less expensive method. In this study, a derivative ultraviolet spectrophotometric method was developed for simultaneous determination of pyrazinamide (PYZ) and rifampicin (RIF). The spectrophotometric method was evaluated according to validation guidelines for specificity, linearity, limits of detection and quantification, precision, accuracy and robustness. The first-derivative spectra were obtained and by the zerocrossing point, the wavelength 247 nm and 365 nm were selected for PYZ and RIF quantification, respectively. No interference from cubosome excipients was detected in the proposed method. The results demonstrated linearity in a range of 4.0 – 12.0 µg/mL with an adequate correlation coefficient for both drugs. The intra and inter-day precision results (RSD &lt; 5%) indicated the reproducibility of the method. The accuracy data showed satisfactory results (RSD &lt; 5%) from recovery test. In addition, the robustness results showed that the PYZ and RIF content were unaffected by the solvent alteration of methanol to methanol:water (99:1, v/v). The derivative ultraviolet spectrophotometric method proved to be an excellent strategy for simultaneous determination of PYZ and RIF.

A cloud computing-based approach using the visible near-infrared spectrum to classify greenhouse tomato plants under water stress

The objective of this study was to evaluate the potential of cloud computing technology for classifying protected tomato plants under different watering treatments. Two tomato varieties, HeZuo 903 and WanShiRuYi, were used in protected cultivation for two seasons. Three water treatments were conducted (normal watering, no watering during the first fruit-swelling period, and no watering during the both fruit-swelling periods). The visible near-infrared reflection spectra of the tomato canopies were collected during the fruiting period. Three spectral datasets were used, including the original reflection spectra, the first derivative of the reflection spectra, and the absorbance spectra. The successive projections algorithm(SPA) was used to select data from six wavebands (483, 557, 674, 783, 869, and 964 nm) as optimal wavebands. The cloud computing platform was built using the Hadoop and Spark frameworks. The MLlib machine-learning library from the Spark framework was used to build a multilayer perceptron classifier (MLPC) and one-vs.-rest classifier (ORC). These multi-class classifiers were applied to the spectral datasets (original, first derivative, and absorbance) for the two tomato varieties under different water treatments. For each classifier, 70% of the data was randomly selected for training and the remaining 30% was used for prediction. Training and prediction were conducted on the cloud computing platform. The MLPC had better classification accuracy than the ORC. Among the three spectral datasets, the first derivative of the spectra had the best classification performance, while the reflection and absorbance spectra had similar performances. Using the full waveband spectrum provided higher classification accuracy than using only the optimal wavebands. Furthermore, the tomato canopy spectrum classification performance was better for the WanShiRuYi plants than the HeZuo 903 plants. Moreover, the collected spectral dataset was increased in size to evaluate the operating efficiency of the cloud computing platform when processing ‘big data.’ The operating efficiency was significantly improved by increasing the size of the spectral dataset or the number of nodes in the platform. Finally, the python and TensorFlow were used to implement the CNN algorithm, and conducted classification and analysis of the spectral datasets. The results showed that the MLPC and ORC algorithm had better classification performance than the CNN algorithm in classification of spectral data.

Application of the radial basis function neural networks to improve the nondestructive Vis/NIR spectrophotometric analysis of potassium in fresh lettuces

Abstract This study was carried out to evaluate the feasibility of using Vis/near-infrared (Vis/NIR) spectroscopy for determining the potassium concentration in fresh lettuce leaves and petioles of single-variety lettuce and mixed lettuce leaves of two varieties. Partial least squares (PLS) and radial basis function (RBF) neural network were systemically studied and compared as regressions tools in developing the prediction models. Competitive adaptive reweighted sampling (CARS) variable selection and spectral preprocessing (first- and second-order derivatives) were applied to optimize the performance of predictions. On the basis of these selected optimum wavelengths, the established PLS prediction models provided the coefficients of determination (R2) of 0.83 and 0.71, residual predictive deviations (RPD) were 1.95 and 1.80, and root mean square errors of prediction (RMSEP) were 39.07 and 38.06 mg/100 g for green leaves and petioles, respectively. By comparison, the RBF approach with first-derivative preprocessing spectra was found to provide the best performance of mixed samples, yielding R2 of 0.86 and 0.88, RMSEP of 31.20 and 27.63 mg/100 g, and RPD of 2.44 and 2.47 for green leaves and petioles, respectively. The overall results of this study revealed the potential for use of Vis/NIR spectroscopy as an objective and non-destructive method to inspect the potassium concentration of fresh lettuces.

An innovative spectrophotometric method for determination of uranium and thorium using 3-aminomethylalizarn-N-N diacetic acid in some geological samples

3-aminomethylalizarn-N-N diacetic acid chromogenic dye (AMADA) was used for the first time in uranium and thorium spectrophotometric estimation with accurate and sensitive result, their complexes having a maximum absorbance at 575 nm for U and at 510 nm for Th. This system allows uranium and thorium content to be calculated with a detection limit (LOD) of 0.16 µg L−1 and 0.14 µg L−1, respectively. The first-derivative spectra and EDTA were investigated to eliminate interference and provide selective estimation of uranium and thorium in presence of each other. This new spectrophotometric method was applied for the determination of U(VI) and Th(IV) in the standard reference materials (granite and Syenite) and some cataclastic rock samples with accurate results.

Estimating leaf chlorophyll content by laser-induced fluorescence technology at different viewing zenith angles.

Leaf chlorophyll content (LCC) is a key indicator of a plant's physiological status. Fast and non-destructive monitoring of chlorophyll content in plants through remote sensing is very important for accurate diagnosis and assessment of plant growth. Through the use of laser-induced fluorescence (LIF) technology, this study aims to compare the predictive ability of different single fluorescence characteristic and fluorescence characteristic combinations at various viewing zenith angles (VZAs) combined with multivariate analysis algorithms, such as principal component analysis (PCA) and support vector machine (SVM), for estimating the LCC of plants. The SVM models of LCC estimation were proposed, and fluorescence characteristics-fluorescence peak (FP), fluorescence ratio (FR), PCA, and first-derivative (FD) parameter-and fluorescence characteristic combinations (FP+FR, FP+FD, FR+FD, FP+FR+FD) were used as input variables for the models. Experimental results demonstrated that the effect of single fluorescence characteristics on the predictive performance of SVM models was: FR>FD>FP>PCA. Compared with other models, 0° SVM was the optimal model for estimating LCC by higher R2. The fluorescence spectra and FD spectra observed at 0° and 30° were superior to those observed at 15°, 45°, and 60°. Thus, appropriate VZA must also be considered, as it can improve the accuracy of LCC monitoring. In addition, compared with single fluorescence characteristic, the FP+FR+FD was the optimal combination of fluorescence characteristics to estimate the LCC for the SVM model by higher R2, indicating better predictive performance. The experimental results show that the combination of LIF technology and multivariate analysis can be effectively used for LCC monitoring and has broad development prospects.

Assessing different regression algorithms for paddy rice leaf nitrogen concentration estimations from the first-derivative fluorescence spectrum.

The non-destructive and rapid estimation of the crop's leaf nitrogen concentration (LNC) is significant for the quality evaluation and precise management of nitrogen (N) fertilizer. First derivative can be applied to reduce the noise in the spectral analysis, which is suited to estimate leaf N and chlorophyll concentration with different fertilization levels. In this study, the first-derivative fluorescence spectrum (FDFS) was calculated in terms of the laser-induced fluorescence (LIF) spectra and was combined with different regression algorithms, including principal component analysis (PCA), partial least-square regression (PLSR), random forest (RF), radial basic function neural network (RBF-NN), and back-propagation neural network (BPNN) for paddy rice LNC estimation. Then, the effect of diverse inner parameters on regression algorithm for LNC estimation based on the calculated FDFS served as input variables were discussed, and the optimal parameters of each model were acquired. Subsequently, the performance of different models (PLSR, RF, BPNN, RBF-NN, PCA-RF, PCA-BPNN, and PCA-RBFNN) with the optimal parameter for LNC estimation based on FDFS was discussed. Results demonstrated that PCA can efficiently extract major spectral information without obviously losing, which can improve the stability and robustness of model (PLSR, PCA-RF, PCA-BNN, and PCA-RBFNN) for LNC estimation. Then, PCA-RBFNN model exhibited better potential for LNC estimation with higher average R2 (R2=0.8743) and lower SD values (SD=0.0256) than that the other regression models in this study. And, PLSR also exhibited promising potential for LNC estimation in which the R2 values (average R2=0.8412) are higher than that the other models except for PCA-RBFNN.

A Machine Learning Framework to Predict Nutrient Content in Valencia-Orange Leaf Hyperspectral Measurements

This paper presents a framework based on machine learning algorithms to predict nutrient content in leaf hyperspectral measurements. This is the first approach to evaluate macro- and micronutrient content with both machine learning and reflectance/first-derivative data. For this, citrus-leaves collected at a Valencia-orange orchard were used. Their spectral data was measured with a Fieldspec ASD FieldSpec® HandHeld 2 spectroradiometer and the surface reflectance and first-derivative spectra from the spectral range of 380 to 1020 nm (640 spectral bands) was evaluated. A total of 320 spectral signatures were collected, and the leaf-nutrient content (N, P, K, Mg, S, Cu, Fe, Mn, and Zn) was associated with them. For this, 204,800 (320 × 640) combinations were used. The following machine learning algorithms were used in this framework: k-Nearest Neighbor (kNN), Lasso Regression, Ridge Regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision Tree (DT), and Random Forest (RF). The training methods were assessed based on Cross-Validation and Leave-One-Out. The Relief-F metric of the algorithms’ prediction was used to determine the most contributive wavelength or spectral region associated with each nutrient. This approach was able to return, with high predictions (R2), nutrients like N (0.912), Mg (0.832), Cu (0.861), Mn (0.898), and Zn (0.855), and, to a lesser extent, P (0.771), K (0.763), and S (0.727). These accuracies were obtained with different algorithms, but RF was the most suitable to model most of them. The results indicate that, for the Valencia-orange leaves, surface reflectance data is more suitable to predict macronutrients, while first-derivative spectra is better linked to micronutrients. A final contribution of this study is the identification of the wavelengths responsible for contributing to these predictions.