Interval Partial Least Squares Research Articles

Research on the chemical oxygen demand spectral inversion model in water based on IPLS-GAN-SVM hybrid algorithm.

Spectral collinearity and limited spectral datasets are the problems influencing Chemical Oxygen Demand (COD) modeling. To address the first problem and obtain optimal modeling range, the spectra are preprocessed using six methods including Standard Normal Variate, Savitzky-Golay Smoothing Filtering (SG) etc. Subsequently, the 190-350 nm spectral range is divided into 10 subintervals, and Interval Partial Least Squares (IPLS) is used to perform PLS modeling on each interval. The results indicate that it is best modeled in the 7th range (238~253 nm). The values of Mean Square Error (MSE), Mean Absolute Error (MAE) and R2score of the model without pretreatment are 1.6489, 1.0661, and 0.9942. After pretreatment, the SG is better than others, with MSE and MAE decreasing to 1.4727, 1.0318 and R2score improving to 0.9944. Using the optimal model, the predicted COD for three samples are 10.87 mg/L, 14.88 mg/L, and 19.29 mg/L. To address the problem of the small dataset, using Generative Adversarial Networks for data augmentation, three datasets are obtained for Support Vector Machine (SVM) modeling. The results indicate that, compared to the original dataset, the SVM's MSE and MAE have decreased, while its accuracy has improved by 2.88%, 11.53%, and 11.53%, and the R2score has improved by 18.07%, 17.40%, and 18.74%.

Raman spectroscopy combined with partial least squares (PLS) based on hybrid spectral preprocessing and backward interval PLS (biPLS) for quantitative analysis of four PAHs in oil sludge

Polycyclic aromatic hydrocarbons (PAHs) contained in a large amount of oily sludge produced in petroleum and petrochemical production has become one of the main environmental protection concerns in the industry. The accurate determination of PAHs is of great significance in the field of petroleum geochemistry and environmental protection. In this study, Raman spectroscopy combined with partial least squares (PLS) based on different hybrid spectral preprocessing methods and variable selection strategies was proposed for quantitative analysis of phenanthrene, fluoranthrene, fluorene and naphthalene (Phe, Flt, Flu and Nap) in oil sludge. At first, PAHs in oily sludge was extracted by solid–liquid extraction with methanol as extractant, and Raman spectra of 21 oily sludge samples were collected by portable Raman spectrometer. And then, the influence of first derivative (D1st), wavelet transform (WT) and their hybrid spectral preprocessing on the predictive performance of the PLS calibration model was discussed. Thirdly, biPLS (backward interval partial least squares) was used to optimize the input variables before and after the hybrid spectral preprocessing methods, and the influence of biPLS and the hybrid spectral preprocessing sequence on the predictive performance of the PLS calibration model was discussed. Finally, the predictive performance of the PLS calibration model was optimized according to the results of leave-one-out cross-validation (LOOCV) method. The results show that the biPLS-D1st-WT-PLS calibration model established by using biPLS first to select the characteristic variables, followed by hybrid spectral preprocessing of the characteristic variables, has better prediction performance for Flt (determination coefficient of prediction (R2P) = 0.9987, and the mean relative error of prediction (MREP) = 0.0606). For Phe, Flu and Nap, the WT-biPLS-PLS calibration model has a better predictive effect (R2P are 0.9995, 0.9996 and 0.9983, and MREP are 0.0426, 0.0719 and 0.0497, respectively). In general, portable Raman spectroscopy combined with PLS calibration model based on different hybrid spectral preprocessing and variable selection strategies has achieved good prediction results for quantitative analysis of four PAHs in oily sludge. It is a new strategy to firstly select the characteristic variables of the original spectra, and secondly to preprocess the characteristic variables by the hybrid spectral preprocessing, which will provide a new idea for the establishment of quantitative analysis methods for PAHs in oily sludge.

Development of Prediction Models for the Pasting Parameters of Rice Based on Near-Infrared and Machine Learning Tools

Due to the importance of rice (Oryza sativa) in food products, developing strategies to evaluate its quality based on a fast and reliable methodology is fundamental. Herein, near-infrared (NIR) spectroscopy combined with machine learning algorithms, such as interval partial least squares (iPLS), synergy interval PLS (siPLS), and artificial neural networks (ANNs), allowed for the development of prediction models of pasting parameters, such as the breakdown (BD), final viscosity (FV), pasting viscosity (PV), setback (ST), and trough (TR), from 166 rice samples. The models developed using iPLS and siPLS were characterized, respectively, by the following regression values: BD (R = 0.84; R = 0.88); FV (R = 0.57; R = 0.64); PV (R = 0.85; R = 0.90); ST (R = 0.85; R = 0.88); and TR (R = 0.85; R = 0.84). Meanwhile, ANN was also tested and allowed for a significant improvement in the models, characterized by the following values corresponding to the calibration and testing procedures: BD (Rcal = 0.99; Rtest = 0.70), FV (Rcal = 0.99; Rtest = 0.85), PV (Rcal = 0.99; Rtest = 0.80), ST (Rcal = 0.99; Rtest = 0.76), and TR (Rcal = 0.99; Rtest = 0.72). Each model was characterized by a specific spectral region that presented significative influence in terms of the pasting parameters. The machine learning models developed for these pasting parameters represent a significant tool for rice quality evaluation and will have an important influence on the rice value chain, since breeding programs focus on the evaluation of rice quality.

A Novel Variable Selection Method Based on Binning-Normalized Mutual Information for Multivariate Calibration.

Variable (wavelength) selection is essential in the multivariate analysis of near-infrared spectra to improve model performance and provide a more straightforward interpretation. This paper proposed a new variable selection method named binning-normalized mutual information (B-NMI) based on information entropy theory. "Data binning" was applied to reduce the effects of minor measurement errors and increase the features of near-infrared spectra. "Normalized mutual information" was employed to calculate the correlation between each wavelength and the reference values. The performance of B-NMI was evaluated by two experimental datasets (ideal ternary solvent mixture dataset, fluidized bed granulation dataset) and two public datasets (gasoline octane dataset, corn protein dataset). Compared with classic methods of backward and interval PLS (BIPLS), variable importance projection (VIP), correlation coefficient (CC), uninformative variables elimination (UVE), and competitive adaptive reweighted sampling (CARS), B-NMI not only selected the most featured wavelengths from the spectra of complex real-world samples but also improved the stability and robustness of variable selection results.

A simple and green method for simultaneously determining the geographical origin and glycogen content of oysters using ATR–FTIR and chemometrics

Oysters are a marine bivalve extensively used as a food product and in medicinal drugs. However, the geographical origin of oysters greatly affects their economic value and quality. In this study, a simple and eco-friendly method is proposed for geographically tracing oysters and determining their bioactive glycogen content using attenuated total reflectance Fourier-transform infrared spectroscopy (ATR-FTIR). Three classification algorithms, including partial least squares-discriminant analysis (PLS-DA), orthogonal PLS-DA (OPLS-DA), and least squares support vector machine (LS-SVM), were applied to determine the geographical origin of oysters. Simultaneously, three types of PLS algorithms, backward interval PLS (BI-PLS), synergy interval PLS (SI-PLS), and competitive adaptive reweighted sampling PLS (CARS-PLS), were used to evaluate the feasibility of determining the glycogen content of oysters. In addition, five signal preprocessing methods were compared to enhance the prediction performance of the qualitative and quantitative models. For qualitative analysis, 100% classification accuracy was achieved using the PLS-DA, OPLS-DA, and LS-SVM. For quantitative analysis, the SI-PLS model showed the best predicted results (correlation coefficient of prediction (RP) = 0.96, relative analysis error of prediction (RPDP) = 3.38), indicating its stable and high predictive performance as a new analytical technique for the traceability supervision and quality evaluation of oysters.

Determination of corn protein content using near-infrared spectroscopy combined with A-CARS-PLS.

In order to quickly and accurately determine the protein content of corn, a new characteristic wavelength selection algorithm called anchor competitive adaptive reweighted sampling (A-CARS) was proposed in this paper. This method first lets Monte Carlo synergy interval PLS (MC-siPLS) to select the sub-intervals where the characteristic variables exist and then uses CARS to screen the variables further. A-CARS-PLS was compared with 6 methods, including 3 feature variable selection methods (GA-PLS, random frog PLS, and CARS-PLS) and 2 interval partial least squares methods (siPLS and MWPLS). The results showed that A-CARS-PLS was significantly better than other methods with the results: RMSECV=0.0336, R2 c=0.9951 in the calibration set; RMSEP=0.0688, R2 p=0.9820 in the prediction set. Furthermore, A-CARS reduced the original 700-dimensional variable to 23 variables. The results showed that A-CARS-PLS was better than some wavelength selection methods, and it has great application potential in the non-destructive detection of protein content in corn.

Wine age prediction using digital images and multivariate calibration

The prediction or confirmation of age is an important field in evaluation of wine’s value. Such type of studies commonly requires a number of data sets describing changes in chemical composition and/or related physical properties. Digital images of wines captured by a webcam represent an easy and low-cost approach to prevent frauds connected to the age of wines. In this work, a combination of frequency histograms including grey scale, red-green-blue (RGB) and hue-saturation-value (HSV) colour models extracted from digital images were used to evaluate the age of botrytized and related varietal wines produced during a 1989–2019 period at different countries. The main findings showed that digital images carry the appropriate chemical information for the age assignment and PLS-type models were able to estimate wine age only one latent variable. Grey levels enabled to find figure of merit values similar to the PLS model based on full histogram. An additional interval selection of the histograms with interval PLS allows improving accuracy of variable assessment and achieving lower error at a cross-validation step, RMSECV decreases from 3.6 years to 3.1 years. When models were employed to predict an external set of samples similar results were found, RMSEP equal to 2.8 years and 2.9 years for PLS and iPLS, respectively. However, a slight deterioration of the results was observed for the PLS model based on full grey levels (RMSEP 3.2). In general, these non-destructive measurements do not generate residuals and can be performed without sophisticated equipment with a reasonably accurate response.

Quantitative and qualitative prediction of sulfur content in diesel by near infrared spectroscopy

This study explored the application of near infrared spectroscopy for quantitative and qualitative prediction of sulfur content in diesel fuel in the range of 10.3–1038.0 mg kg−1. The original spectra were preprocessed through various methods such as decentralization, normalization, multivariate scattering correction, and a smoothing (15-point window with second order polynomial fit). The performances of models based on partial least squares (PLS) regression, the bootstrapping soft shrinkage (BOSS), competitive adaptive reweighted sampling and Monte Carlo uninformative variable elimination algorithms in quantitative analysis of diesel samples were compared. The model for quantitative prediction of sulfur content in diesel samples using the BOSS-PLS algorithm had the highest performance and accuracy with a RMSEP of 36.20 mg kg−1 and r2 of 0.98 using a Savitzky-Golay second derivative. Diesel fuel samples were classified into five groups according to the sulfur content for qualitative analysis. The interval PLS method was then used to determine the characteristic spectra of the diesel samples. The experimental results indicated that the discriminant partial least squares qualitative analysis model had the highest performance with the characteristic spectrum from 12,493 to 10,892 cm−1, with 92.04% accuracy.

Nondestructive Detection of Moisture Content in Palm Oil by Using Portable Vibrational Spectroscopy and Optimal Prediction Algorithms.

Rapid and nondestructive measurement of moisture content in crude palm oil is essential for promoting the shelf-stability and quality. In this research, micro NIR spectrometer coupled with a multivariate calibration model was used to collect and analyse fingerprinted information from palm oil samples at different moisture contents. Several preprocessing methods such as standard normal variant (SNV), multiplicative scatter correction (MSC), Savitzky-Golay first derivative (SGD1), Savitzky-Golay second derivative (SGD2) together with partial least square (PLS) regression techniques, full PLS, interval PLS (iPLS), synergy interval PLS (SiPLS), genetic algorithm PLS (GAPLS), and successive projection algorithm PLS (SPA-PLS) were comparatively employed to construct an optimum quantitative prediction model for moisture content in crude palm oil. The models were evaluated according to the coefficient of determination and root mean square error in calibration (Rc and RMSEC) and prediction (Rp and RMSEC) set, respectively. The model SGD1 + SiPLS was the optimal novel algorithm obtained among the others with the performance of Rc = 0.968 and RMSEC = 0.468 in the calibration set and Rp = 0.956 and RMSEP = 0.361 in the prediction set. The results showed that rapid and nondestructive determination of moisture content in palm oil is feasible and this would go a long way to facilitating quality control of crude palm oil.

Research on a nondestructive model for the detection of the nitrogen content of tomato.

The timely detection of information on crop nutrition is of great significance for improving the production efficiency of facility crops. In this study, the terahertz (THz) spectral information of tomato plant leaves with different nitrogen levels was obtained. The noise reduction of the THz spectral data was then carried out by using the Savitzky-Golay (S-G) smoothing algorithm. The sample sets were then analyzed by using Kennard-Stone (KS) and random sampling (RS) methods, respectively. The KS algorithm was optimized to divide the sample sets. The stability competitive adaptive reweighted sampling (SCARS), uninformative variable elimination (UVE), and interval partial least-squares (iPLS) algorithms were then used to screen the pre-processed THz spectral data. Based on the selected characteristic frequency bands, a model for the detection of the nitrogen content of tomato based on the THz spectrum was established by the radial basis function neural network (RBFNN) and backpropagation neural network (BPNN) algorithms, respectively. The results show that the root-mean-square error of correction (RMSEC) and root-mean-square error of prediction (RMSEP) of the BPNN model were respectively 0.1722% and 0.1843%, and the determination coefficients of the correction set (Rc 2) and prediction set (Rp 2) were respectively 0.8447 and 0.8375. The RMSEC and RMSEP values of the RBFNN model were respectively 0.1322% and 0.1855%, and the Rc 2 and Rp 2 values were respectively 0.8714 and 0.8463. Thus, the accuracy of the model established by the RBFNN algorithm was slightly higher. Therefore, the nitrogen content of tomato leaves can be detected by THz spectroscopy. The results of this study can provide a theoretical basis for the research and development of equipment for the detection of the nitrogen content of tomato leaves.

Rapid determination of cadmium residues in tomato leaves by Vis-NIR hyperspectral and Synergy interval PLS coupled Monte Carlo method

Excessive heavy metal cadmium in tomatoes is harmful to human health. The detection of heavy metals in tomato leaves can determine whether the heavy metals in tomatoes exceed the standard. In order to quickly, non-destructively and efficiently detect whether heavy metals on the surface of tomato leaves exceed the standard, a new wavelength interval selection method called Synergy interval PLS couple with Monte Carlo method (MC-siPLS) was proposed. From the seedling stage, concentration of 0, 0.05, 0.1, 0.2, 0.5, 1, 2, 5, 10 mg/L cadmium chloride (CdCl2) was used for irrigation under normal nutrient elements respectively. A total of 405 leaf samples were collected. Using the VIS-NIR hyperspectral instrument, the tomato leaves were set as the region of interest to obtain hyperspectral data, then used Atomic Absorption Spectrometry (AAS) method to detect heavy metals in tomato leaves. In addition, 5 different PLS algorithm were used to compare with MC-siPLS. Furthermore, the best model was given by MC-siPLS with RMSEP = 0.5378, R2 = 0.9870. The results show that MC-siPLS was better than similar wavelength interval selection methods, which had great application potential in the nondestructive detection of heavy metals in tomato leaves. This method maybe determines whether tomatoes contain excess cadmium early.

Spectral method for macro and micronutrient prediction in soybean leaves using interval partial least squares regression

Studies on the use of hyperspectral remote sensing for nutrient prediction in soybean (Glycine max L.) leaves are limited, especially regarding the selection of wavelengths. Therefore, the objective of this study was to estimate macro and micronutrients in soybean leaves by employing reflectance data modeled by Partial Least Squares Regression (PLSR) from bands selected by the iPLS (Interval PLS), method with a script developed for MATLAB R2018a. The experimental area was treated with different doses of limestone, with and without incorporation, also with phosphogypsum application in additional treatments. The soybean crops of 2018/2019 and 2019/2020 had the nutritional status evaluated by a random collection of the third fully developed trefoil in the R2 (full flowering) and R5.5 (76–100% grain filling) reproductive phenological stages. The leaf samples were submitted to conventional laboratory analyses. The Ca, Mg, K, P, S, Cu, Fe, Mn, and Zn elements in the leaves were quantified through spectrometry. A field spectroradiometer performed spectral data acquisition in the visible-near infrared, short-wave infrared spectral range of soybean leaves. The spectral curves were subjected to iPLS, and PLSR models were fitted. After iPLS selection, the coefficient of determination (R2) values of PLSR models were on average 15.3% and 16.6% higher in calibration and validation, respectively, compared to classical methods. The PLSR model for Mn, which obtained R2 above 0.90 in the calibration and validation phases, stood out. The Root Mean Square Error (RMSE) decreased, on average, more than 15.0%, both in calibration and validation, after applying the iPLS selection. The models for Ca and Mn stood out with over a 30.0% decrease in RMSE, in calibration and validation. The iPLS selection was efficient in improving the performance and accuracy of the PLSR models, increasing the R2 and decreasing the RMSE, opening new possibilities for the analysis and prediction of macro and micronutrients in plants.

Evaluation of near-infrared hyperspectral imaging for the assessment of potato processing aptitude.

The potato (Solanum tuberosum L.) is the world's fifth most important staple food with high socioeconomic relevance. Several potato cultivars obtained by selection and crossbreeding are currently on the market. This diversity causes tubers to exhibit different behaviors depending on the processing to which they are subjected. Therefore, it is interesting to identify cultivars with specific characteristics that best suit consumer preferences. In this work, we present a method to classify potatoes according to their cooking or frying as crisps aptitude using NIR hyperspectral imaging (HIS) combined with a Partial Least Squares Discriminant Analysis (PLS-DA). Two classification approaches were used in this study. First, a classification model using the mean spectra of a dataset composed of 80 tubers belonging to 10 different cultivars. Then, a pixel-wise classification using all the pixels of each sample of a small subset of samples comprised of 30 tubers. Hyperspectral images were acquired using fresh-cut potato slices as sample material placed on a mobile platform of a hyperspectral system in the NIR range from 900 to 1,700 nm. After image processing, PLS-DA models were built using different pre-processing combinations. Excellent accuracy rates were obtained for the models developed using the mean spectra of all samples with 90% of tubers correctly classified in the external dataset. Pixel-wise classification models achieved lower accuracy rates between 66.62 and 71.97% in the external validation datasets. Moreover, a forward interval PLS (iPLS) method was used to build pixel-wise PLS-DA models reaching accuracies above 80 and 71% in cross-validation and external validation datasets, respectively. Best classification result was obtained using a subset of 100 wavelengths (20 intervals) with 71.86% of pixels correctly classified in the validation dataset. Classification maps were generated showing that false negative pixels were mainly located at the edges of the fresh-cut slices while false positive were principally distributed at the central pith, which has singular characteristics.

Effect of variable selection and rapid determination of total tea polyphenols contents in Fuzhuan tea by near-infrared spectroscopy

ABSTRACT This study attempted to measure the total polyphenols contents in Fuzhuan tea by near-infrared (NIR) spectroscopy coupled with an appropriate multivariate calibration method. Partial least squares (PLS), synergy interval PLS (si-PLS), and genetic algorithm-based PLS (ga-PLS) were carried out comparatively to calibrate regression models. The root mean square error of prediction (RMSEP), determination coefficient (Rp2), and P-value between the true and predicted values of prediction set were used to evaluate the performance of the final model. The ga-PLS model showed the best performance compared with the PLS and si-PLS models. The optimal model obtained Rp2 = 0.9996 and RMSEP = 0.0488 for the prediction set using only 37 spectral data points. No significant difference was observed between the true and predicted tea polyphenol contents in the prediction set (P > 0.05). NIR spectroscopy together with the ga-PLS algorithm can be used to rapidly predict the total polyphenol contents in Fuzhuan tea.

Fast identification of soybean varieties using Raman spectroscopy

Fast and accurate identification of soybean varieties is important for determining seed quality, protecting the interests of soybean growers and ensuring food safety. A combination of Raman spectroscopy with chemometric methods has been widely applied in the identification of agricultural products such as grains, fruit, edible oils, and honey; however, the identification methods of soybean varieties mainly focuses on infrared spectroscopy and hyperspectral imagery. Therefore, a partial least squares (PLS) identification model was established by Raman spectroscopy combined with characteristic wavenumber extraction method to rapidly identify four high-protein soybean varieties (Heinong 88, Heinong 98, Suinong 71, and Suinong 76) that are extensively planted in Heilongjiang Province, China. Owing to the high-dimensional and high correlation data obtained from Raman spectroscopy, a full-spectrum prediction mode will lead to high complexity and poor stability. Therefore, first, the optimal combinations of spectral subintervals were selected by backward interval PLS (BIPLS) and synergy interval PLS (SIPLS); however, redundant variables still existed in the selected continuous band and strong collinearity was observed between adjacent wavenumbers. Consequently, ElasticNet was used to re-filter the characteristic spectral regions of BIPLS and SIPLS, which effectively reduced the collinearity between the selected wavenumbers. The performance of different algorithms, i.e., full-spectrum and five characteristic wavenumber selection algorithms—BIPLS, SIPLS, ElasticNet, BIPLS-ElasticNet, and SIPLS-ElasticNet —were compared. In the BIPLS-ElasticNet algorithm, 1113 effective wavenumbers were extracted, which accounted for approximately 35% of the total wavenumbers. Moreover, the values of root mean square error, determination coefficient, and identification accuracy of the prediction set were determined to be 0.2298,0.9568 and 100%, respectively. Therefore, the proposed BIPLS-ElasticNet demonstrated the best performance among the PLS models and can be used for the fast and accurate identification of soybean varieties; moreover, it can also provide a reference for the rapid identification of other crop seeds.

Measurement of nitrogen content in rice plant using near infrared spectroscopy combined with different PLS algorithms

Nitrogen plays an important role in rice growth, and determination of nitrogen content in rice plants is of great significance in assessing plant nutritional status and allowing precision cultivation. Traditional chemical methods for determining nitrogen content have the disadvantages of destructive sampling and lengthy analysis times. Here, the feasibility of rapid nitrogen content analysis by near-infrared (NIR) spectroscopy of rice plants was studied. Spectral data from 447 rice samples at several growth stages were used to establish a predictive model. Different spectral preprocessing methods and characteristic selection methods were compared, such as interval partial least-squares (iPLS), synergy interval partial least-squares (SiPLS), and moving-window partial least-squares (mwPLS). The SiPLS method exhibited better performance than mwPLS or iPLS. Specifically, the combination of four subintervals (7, 26, 27, and 28), with characteristic bands at 5299–4451 cm−1 and 10445–10423 cm−1, resulted in the best model. The optimal SiPLS model had a correlation coefficient of 0.9533 and a root mean square error of prediction (RMSEP) of 0.1952 on the prediction set. Compared to using the full spectra, using SiPLS reduced the number of characteristics by 87 % in the model, and RMSEP was reduced from 0.2284 to 0.1952. The results demonstrate that NIR spectroscopy combined with the SiPLS algorithm can be applied to quickly determine nitrogen content in rice plants. This study provides a technical framework to guide future precision agriculture efforts with respect to nitrogen application.

Determination of protein content in single black fly soldier (Hermetia illucens L.) larvae by near infrared hyperspectral imaging (NIR-HSI) and chemometrics

The production of alternative proteins to meet the demand of a growing population has accelerated the growth of the market for edible insects. Black fly soldier (BFS) larvae (Hermetia illucens L.) have been widely studied globally due to their high content of fat, protein, and minerals, being mainly used for animal feed. Chemical analysis for determination of its composition is time consuming and laborious. In this work, we have developed predictive models based on Near Infrared Hyperspectral Imaging (NIR-HSI), Partial Least Square Regression (PLSR) and Support Vector Machine Regression (SVMR) to estimate the total protein content in single and intact BFS larvae. A variable selection step by interval PLS (iPLS) and genetic algorithms (GA) was implemented to improve regression model performance. In addition, BFS larvae hyperspectral images were explored using Principal Component Analysis (PCA), whose results showed the distribution of the different chemical compounds in the larvae. The PLSR and SVMR models reached RMSEP values of 1.57–1.66% and RPD values of 2.0–2.5, indicating a good approximate prediction capacity (% protein range 25.5–43.5%). Variables selected by iPLS obtained better regression models than variables selected by GA, based on the lower absolute error. Chemical maps displayed the heterogeneous protein distribution in single larvae and a batch of larvae. This manuscript demonstrates that NIR-HSI and chemometrics can be implemented as a fast screening method to estimate protein content in single BFS larvae.

Exploring the potential of hyperspectral imaging to detect Esca disease complex in asymptomatic grapevine leaves

• A pixel-based classification of esca-affected grapevine leaves was achieved by HSI. • Multiple pre-processing and variable selection methods were tested using PLS-DA. • Feature wavelengths were identified using automatic and interval PLS methods. • Asymptomatic leaves belonging to esca-affected vines were successfully identified. • NIR-HSI could detect foliar symptoms of grapevine Esca disease complex. Precise and reliable identification of specific plant diseases is a challenge within precision agriculture nowadays. This is the case of esca, a complex grapevine trunk disease, that represents a major threat to modern viticulture as it is responsible for large economic losses annually. The lack of effective control strategies and the complexity of esca disease expression make essential the identification of affected plants, before symptoms become evident, for a better management of the vineyard. This study evaluated the suitability of a near-infrared hyperspectral imaging (HSI) system to detect esca disease in asymptomatic grapevine leaves of Tempranillo red-berried cultivar. For this, 72 leaves from an experimental vineyard, naturally infected with esca, were collected and scanned with a lab-scale HSI system in the 900-1700 nm spectral range. Then, effective image processing and multivariate analysis techniques were merged to develop pixel-based classification models for the distinction of healthy, asymptomatic and symptomatic leaves. Automatic and interval partial least squares variable selection methods were tested to identify the most relevant wavelengths for the detection of esca-affected vines using partial least squares discriminant analysis and different pre-processing techniques. Three-class and two-class classifiers were carried out to differentiate healthy, asymptomatic and symptomatic leaf pixels, and healthy from asymptomatic pixels, respectively. Both variable selection methods performed similarly, achieving good classification rates in the range of 82.77-97.17% in validation datasets for either three-class or two-class classifiers. The latter results demonstrated the capability of hyperspectral imaging to distinguish two groups of seemingly identical leaves (healthy and asymptomatic). These findings would ease the annual monitoring of disease incidence in the vineyard and, therefore, better crop management and decision making.

Spectral Method for Liming Recommendation in Oxisol Based on the Prediction of Chemical Characteristics Using Interval Partial Least Squares Regression

Thousands of chemical analyses are carried out annually with the aim of recommending soil correction; however, these analyses are expensive, destructive, time-consuming, and can be harmful to the environment. As an alternative to conventional analysis methods, diffuse reflectance spectroscopy has been proposed as an option for evaluating the chemical characteristics of soil. The selection of variables has also emerged as an alternative to improve the performance of PLSR (partial least squares regression), as it decreases the root mean square error (RMSE) and increases the accuracy of the models. However, few studies have used a previous selection of variables for the construction of PLSR models to estimate the chemical characteristics of soil. In this context, the hypothesis in this study was that it is possible to calculate the liming recommendation in Oxisol based on the chemical characteristics estimated by PLSR, with a previous selection of variables using iPLS (Interval PLS). The objective was to calculate the need for liming based on chemical characteristics estimated via iPLS selection and PLSR modeling of specific wavelengths of soil reflectance. The experimental area was treated with different application rates of limestone, with and without incorporation, and phosphogypsum was applied in additional treatments. Soil assessments were carried out 5, 12, 24, and 36 months after the application of the treatments, using six layers: 0.00–0.05, 0.05–0.10, 0.10–0.20, 0.20–0.30, 0.30–0.40 and 0.40–0.60 m. Samples were subjected to conventional laboratory analyses, and spectral readings (400–2500 nm) were obtained with a spectroradiometer. The spectral curves were subjected to the iPLS variable selection method to generate PLSR models of the chemical characteristics used to calculate the liming recommendation. The chemical characteristics of the soil, such as Ca2+, sum of bases (SB), effective cation exchange capacity (CTCe), cation exchange capacity (CTC), and base saturation (BS), could be estimated, with values of R2 ranging from 0.83 to 0.92 in the calibration and validation steps, and from 0.84 to 0.90 for the prediction step (in the fourth assessment). The liming recommendation calculated based on the chemical characteristics predicted from the PLSR models showed a strong correlation (r > 0.86) with the liming recommendation calculated by conventional laboratory techniques. The fourth soil assessment yielded the best correlation coefficient (r = 0.95).

Green Banana Maturity Classification and Quality Evaluation Using Hyperspectral Imaging

Physiological maturity of bananas is of vital importance in determination of their quality and marketability. This study assessed, with the use of a Vis/NIR hyperspectral imaging (400–1000 nm), the feasibility in differentiating six maturity levels (maturity level 2, 4, and 6 to 9) of green dwarf banana and characterizing their quality changes during maturation. Spectra were extracted from three zones (pedicel, middle and apex zone) of each banana finger, respectively. Based on spectra of each zone, maturity identification models with high accuracy (all over 91.53% in validation set) were established by partial least squares discrimination analysis (PLSDA) method with raw spectra. A further generic PLSDA model with an accuracy of 94.35% for validation was created by the three zones’ spectra pooled to omit the effect of spectra acquisition position. Additionally, a spectral interval was selected to simplify the generic PLSDA model, and an interval PLSDA model was built with an accuracy of 85.31% in the validation set. For characterizing some main quality parameters (soluble solid content, SSC; total acid content, TA; chlorophyll content and total chromatism, ΔE*) of banana, full-spectra partial least squares (PLS) models and interval PLS models were, respectively, developed to correlate those parameters with spectral data. In full-spectra PLS models, high coefficients of determination (R2) were 0.74 for SSC, 0.68 for TA, and fair of 0.42 as well as 0.44 for chlorophyll and ΔE*. The performance of interval PLS models was slightly inferior to that of the full-spectra PLS models. Results suggested that models for SSC and TA had an acceptable predictive ability (R2 = 0.64 and 0.59); and models for chlorophyll and ΔE* (R2 = 0.34 and 0.30) could just be used for sample screening. Visualization maps of those quality parameters were also created by applying the interval PLS models on each pixel of the hyperspectral image, the distribution of quality parameters in which were basically consistent with the actual measurement. This study proved that the hyperspectral imaging is a useful tool to assess the maturity level and quality of dwarf bananas.