RPD Values Research Articles

Examining the Potential Environmental Controls of Underground CO2 Concentration in Arid Regions by an SVD-PCA-ANN Preview Model

This study attempts to examine environmental controls of the underground CO2 concentration, taking the CO2 concentration 4 m beneath the soil as an example. An SVD-PCA-ANN (singular value decomposition-principal component analysis-artificial neural network) preview model is proposed with the data of underground CO2 concentration and 12 environmental variables (the soil and meteorological data). The R2, RMSE, and RPD values of the proposed model are, respectively, 0.8874, 0.3351, and 2.7929, performing better than the popular preview models like SAE (stacked autoencoders), SVM (support vector machine), and LSTM (long short-term memory). It is proved that the underground CO2 concentration can be approximated by a nonlinear function of the considered variables. Soil temperature, salinity, and wind speed are the leading environmental controls, which explain 32.04%, 13.68%, and 11.21% in the variability of the underground CO2 concentration, respectively. Possible mechanisms associated with the environmental controls are also preliminarily discussed.

Study on hyperspectral estimation model of soil organic carbon content in the wheat field under different water treatments

Hyperspectral remote sensing technology can be used to monitor the soil nutrient changes in a rapid, real-time, and non-destructive manner, which is of great significance to promote the development of precision agriculture. In this paper, 225 soil samples were studied. The effects of different water treatments on soil organic carbon (SOC) content, and the relationship between SOC content and spectral reflectance (350–2500 nm) were studied. 17 kinds of preprocessing algorithm were performed on the original spectral (R), and the five allocation ratios of calibration to verification sets were set. Finally, the model was constructed by partial least squares regression (PLSR). The results showed that the effects of water treatment on SOC content were different in different growth stages of winter wheat. Results of correlation analysis showed that the differential transformation can refine the spectral characteristics, and improve the correlation between SOC content and spectral reflectance. Results of model construction showed that the models constructed by second-order differential transformation were not good. But the ratio of standard deviation to the standard prediction error (RPD) values of the models were constructed by simple mathematical transformation (T0–T5) and first-order differential transformation (T6–T11) can reach more than 1.4. The simple mathematical transformation (T0–T2, T4–T5) and the first-order differential transformation (T6–T10) resulted in the highest RPD in mode 5 and mode 2, respectively. Among all the models, the model of T7 in mode 2 reach the highest accuracy with a RPD value of 1.9861. Therefore, it is necessary to consider the data preprocessing algorithm and allocation ratio in the process of constructing the hyperspectral monitoring model of SOC.

Comparison of Machine-Learning and CASA Models for Predicting Apple Fruit Yields from Time-Series Planet Imageries

Apple (Malus domestica Borkh. cv. “Fuji”), an important cash crop, is widely consumed around the world. Accurately predicting preharvest apple fruit yields is critical for planting policy making and agricultural management. This study attempted to explore an effective approach for predicting apple fruit yields based on time-series remote sensing data. In this study, time-series vegetation indices (VIs) were derived from Planet images and analyzed to further construct an accumulated VI (∑VIs)-based random forest (RF∑VI) model and a Carnegie–Ames–Stanford approach (CASA) model for predicting apple fruit yields. The results showed that (1) ∑NDVI was the optimal predictor to construct an RF model for apple fruit yield, and the R2, RMSE, and RPD values of the RF∑NDVI model reached 0.71, 16.40 kg/tree, and 1.83, respectively. (2) The maximum light use efficiency was determined to be 0.499 g C/MJ, and the CASASR model (R2 = 0.57, RMSE = 19.61 kg/tree, and RPD = 1.53) performed better than the CASANDVI model and the CASAAverage model (R2, RMSE, and RPD = 0.56, 24.47 kg/tree, 1.22 and 0.57, 20.82 kg/tree, 1.44, respectively). (3) This study compared the yield prediction accuracies obtained by the models using the same dataset, and the RF∑NDVI model (RPD = 1.83) showed a better performance in predicting apple fruit yields than the CASASR model (RPD = 1.53). The results obtained from this study indicated the potential of the RF∑NDVI model based on time-series Planet images to accurately predict apple fruit yields. The models could provide spatial and quantitative information of apple fruit yield, which would be valuable for agronomists to predict regional apple production to inform and develop national planting policies, agricultural management, and export strategies.

Rapid spectroscopic method for quantifying gluten concentration as a potential biomarker to test adulteration of green banana flour

The demand for gluten-free banana flour has led manufactures to enforce strict measures for quality control. A need has arisen for the development of more sensitive and reliable methods to test the quality of green banana flour (GBF). The objective of this study was to develop rapid visible to near-infrared (Vis-NIR) based spectroscopic models to detect gluten concentration, as a biomarker to detect wheat flour adulteration in green banana flour (GBF). Spectroscopic data were acquired using a desktop (FOSS®) Vis-NIR spectroscopy ranging from 400 to 2500 nm of the electromagnetic spectrum. The spectral and reference data were submitted to principal component analysis (PCA) and partial least squares regression (PLSR) for the development of gluten adulteration detection models. Calibration models were constructed based on a full cross-validation approach, consisting of 51 samples for the calibration set and 21 samples for the test set. PCA scores plot discriminated gluten adulterated and unadulterated GBF samples with 100% accuracy for the first two principal components (PCs). The optimal prediction model was obtained after a combination of baseline (offset and baseline linear correlation) and standard normal variate (SNV) pre-processing technique. This model showed a 94% coefficient of determination of cross-validation (R2cv) and prediction (R2p); root mean square error of cross-validation (RMSECV) of 3.7 mg/kg, root mean square error of prediction (RMSEP) of 3.9 mg/kg; and RPD value of 4. This work has demonstrated that Vis-NIRS method is a robust and feasible technology that may be used to ensure the safety of banana flour and that this product stays gluten-free by providing good and reliable gluten detection and quantification prediction models.

Rapid and nondestructive prediction of amylose and amylopectin contents in sorghum based on hyperspectral imaging

The contents of amylose and amylopectin in sorghum directly affects the quality and yield of liquor. Hyperspectral imaging (HSI) is an emerging technology widely applied in the content analysis of food ingredients. In this study, the effects of different preprocessing methods on visible-light and near-infrared spectral data were analyzed, and the prediction accuracies of these spectral data were compared. Principal components analysis (PCA) and successive projections algorithm (SPA) were combined to extract the characteristic wavelengths. Using both the full and characteristic wavelengths, partial least square regression (PLSR) and cascade forest (CF) models were developed to predict the contents of amylose and amylopectin in different varieties of sorghum. The average RPD values of the CF models established by the characteristic wavelengths were 4.7622 and 5.5889, respectively. These results corroborated the utility of HSI in achieving the rapid and nondestructive prediction of amylose and amylopectin contents in different varieties of sorghum.

Measurement of total soluble solids and moisture in puree and dry powder of Kakadu plum (Terminalia ferdinandiana) samples using hand-held near infrared spectroscopy

Recent research has shown the potential of portable and handheld NIR instruments to monitor and measure the composition of fruits and vegetables. Current research has also shown the possibility of using portable instruments as tools to monitor composition along the entire food value chain. The objective of this study was to evaluate two sample presentation methods (dry powder and fruit puree) to measure total soluble solids (TSS) and moisture (M) in wild harvested Kakadu plum (KP) ( Terminalia ferdinandiana, Combretaceae). Kakadu plum is an endemic plant of Australia that contains high concentrations of vitamin C, ellagic acid as well as other bioactive compounds. These properties make this plant of high economic and social importance for the Aboriginal communities of Australia. Fruit samples were wild harvested in January 2020 from locations in the Kimberley region (Western Australia, Australia) and analysed using both reference and NIR spectroscopic methods. The SECV and RPD values in cross validation were 0.65% (RPD: 2.2) and 0.22% (RPD: 4.2) to predict M and TSS in the KP dry powder samples. The SECV and RPD values obtained in cross validation for the KP fruit puree samples were 0.56% (RPD: 2.8) and 0.24% (RPD: 3.8) for M and TSS, respectively. The results of this study demonstrated the ability of NIR spectroscopy to measure M and TSS in wild harvest fruit. These findings can be also utilised by the Aboriginal communities to develop a grading/sorting system to rapidly screen and evaluate relevant chemical parameters associated with fruit quality and safety.

Estimation of soil organic matter content based on CARS algorithm coupled with random forest

Soil organic matter (SOM) is an important index used to evaluate soil fertility and nutrient availability, and it is also an important component of precision agriculture. In this study, in order to quickly and efficiently estimate the SOM content of farmland soil, we took 190 farmland soil samples in Jingbian County and measureed the SOM content of the samples in the lab and collected the corresponding Vis-NIR spectroscopy data. Based on the six pretreatment methods, a competitive adaptive weighting algorithm (CARS) is used for characteristic wavelength selection. Random forest (RF) regression is used to establish the predictive SOM model. The results indicate that after the CARS algorithm screens the different spectral variables, the optimal variable sets of the seven spectral variables are 15, 40, 30, 23, 20, 26, and 23, respectively. The accuracy of the model is improved after the CARS algorithm screens the different spectral variables. A total of 15 characteristic variables from the 2151 spectral wavelengths were used as the optimal spectral variable subset; RF shortened the training time required during the SOM modeling process and dramatically improved the model’s accuracy and predictive ability, and the R2 of the validation set increased from 0.21 to 0.96, and the RPD increased from 0.46 to 3.02. The RPIQ increased from 1.25 to 4.41. Among the tested models, the CR-RF model produced the best results. The R2 and RMSE values of the calibration set are 0.91 and 0.49, and the R2, RMSE, RPD, and RPIQ values of the validation set are 0.96, 0.51, 3.02, and 4.41, respectively. Accurate prediction of the SOM of the cultivated layer in the study area was realized.

Nondestructive freshness evaluation of intact prawns (Fenneropenaeus chinensis) using line-scan spatially offset Raman spectroscopy

Prawns are highly popular with consumers but present many technical difficulties for the evaluation of their internal quality when intact (in-shell prawns). This study proposed a nondestructive method to assess the internal quality of intact prawns (Fenneropenaeus chinensis) using spatially offset Raman spectroscopy (SORS) technique combined with data modeling analysis. This technique holds promise due to the capability of SORS to obtain chemical information nondestructively from below the surface of a sample material. Raman scattering image data for 100 fresh prawns (approximately 15 g each) were collected using a line-scan Raman imaging system over the course of seven days with 24 h measurement intervals. Measurement anomalies due to physical prawn irregularities were eliminated using a peak identification method. Twenty feature bands selected by Random Forest (RF) method were input to Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), and Extremely Randomized Tree (ET) models to predict the freshness of prawns during the storage time. The prediction model based on SORS enhanced data and combining RF feature band selection with SVR demonstrated the best performance, with RMSEP, R2, and RPD values of 0.71, 0.88, and 2.63, respectively. This rapid and nondestructive method for quality evaluation may be feasible as a practical means of assessing internal quality of materials that demonstrate surface interference, such as in-shell prawns.

Non-targeted fingerprinting approach for rapid quantification of mustard oil adulteration with linseed oil: An economically motivated adulteration

Mustard oil (MO) is a popular edible oil and an essential component of the Indian diet due to its characteristic flavor and pungency. Recently, “Economically motivated adulteration (EMA),” a type of oil fraud, becomes an evolving threat to consumers. In the present work, MO adulteration with Linseed oil (LSO) was analyzed using attenuated total reflectance Fourier-transform infrared (ATR-FTIR) spectroscopy. Based on spectral information of adulterated samples, exploratory method such as Principal component analysis (PCA) and classification method like Linear discriminant analysis (LDA) were employed that correctly classified adulterated samples, providing an accurate classification of 100 %. Furthermore, quantitative methods like Principal component regression (PCR) and partial least square regression (PLSR) were used to compare raw, first, and second derivatives of three selected optimized spectral regions to obtain the best model. The PLSR model for the first derivative of optimized spectral region II (1800 to 600 cm−1) showed excellent precision and accuracy ability in predicting adulterated samples with high R2 (0.999), RPD (63.42) and low standard error values (RMSECV; 0.216 v/v, RMSEP; 0.167 v/v and RE%; 3.45). Therefore, our results showed that the optimized statistical model has the potential to rapidly detect LSO adulteration in MO as low as 0.5 % v/v.

Near infrared reflectance spectroscopy: classification and rapid prediction of patchouli oil content

Patchouli is a fragrant oil that produces essential oils known as patchouli oil. The main content of patchouli oil is Patchouli alcohol (PA), generally to determine the PA content of patchouli oil uses chemicals and the waste is not good for the environment. Therefore, there is another alternative method to address these problem, one of the alternative technologies to determine the content of patchouli oil is to use Near Infrared Spectroscopy (NIRS). NIRS can be used to analyze samples rapidly, easily, non-destructive and does not require any chemicals. In this study, the PA content and patchouli oil refractive index were obtained through the acquisition of NIRS spectrum in patchouli oil samples from several different regions with different fractions. Patchouli oil classification is carried out by the Principal Component Analysis (PCA) method. The content of PA content and refractive index is carried out by verifying the factual results of laboratory tests using the Principal Component Regression (PCR) method. Patchouli alcohol spectrum data is found in the wavelength range of 1350-1450 nm and 1950-2100 nm. Predicted results with PCR for PA content and refractive index show values R2 = 0.95 and 0.99 respectively with RPD values of 5.07 and 0.0011.

Quantitative prediction and visualization of key physical and chemical components in black tea fermentation using hyperspectral imaging

Fermentation is a key process that affects the quality of black tea. In this study, we discussed the changes and influencing factors of key endoplasmic components at different positions of stacked fermented leaves, and the effects of different preprocessing, variable selection and intelligent algorithm on the model performance are compared, the quantitative prediction model of main endoplasmic components of Congou black tea under different fermentation time series was established, finally, the content distribution is depicted in different colors. The results show that the RPD values of the random forest (RF) prediction model constructed using the optimal variables of theafuscin, thearubigin, catechin, caffeine, and soluble sugar were 3.40, 2.21, 5.71, 1.46, and 2.89, respectively. The RPD values of the support vector machine (SVR) prediction model constructed using the optimal variables of theaflavin and the phenol ammonia ratio were 3.78 and 2.91, respectively. Furthermore, the visualization process successfully displayed the distribution of various quality indicators of the samples at different time periods. These research results lay a theoretical foundation for advancing the judicious processing of black tea.

Development of NIR-HSI and chemometrics process analytical technology for drying of beef jerky

Beef jerky samples immersed in brine or water, both with and without ultrasound treatment were dried at 60 °C for 30, 60, 90, 120, 150, 180, 210 and 240 min. Drying behaviour was evaluated using ten drying kinetic models and hyperspectral imaging. All samples reached water activity values (Aw) < 0.85 during the first 90 min of drying. Moisture content (MC) of beef jerky was predicted using near infrared hyperspectral imaging and chemometrics. Partial least squares regression, band selection and spectral pre-treatments were applied to develop MC prediction models using beef jerky spectra. Most of the MC prediction models developed in this work had RPD values >4, indicating their suitability for process control applications. The best performing MC prediction models for the non-ultrasound and ultrasound treated samples were developed using the ensemble Monte Carlo variable selection (EMCVS) on second derivative of log(1/R) spectra and EMCVS-selectivity ratio on linear detrended log (1/R) spectra, respectively. This study demonstrated the potential of NIR-HSI and chemometrics as a PAT tool for drying of beef jerky.

Prediction of Moisture and Caffeine Contents of the Roasted Coffee Beans (Coffea liberica Hiern) using NIRS and PLSR-MLR Models

Near-infrared spectroscopy was assessed for the prediction of moisture content (MC) and caffeine content (CC) of ground “Barako” roasted coffee. Individual models were developed using a chemometric analysis of the NIR spectra (900-1700 nm). Partial least squares regression (PLSR) cross-validation and validation results showed that the MC models could be used for at least quality assurance applications. However, the CC model for PLSR cross validation can only be used for rough screening and approximate calibration applications due to low RPD (2.000) and R2 (0.755) values. The results for the validation models of CC obtained lower RPD (0.220) and R2(0.136) that it did not pass for any use or application. The results of the PLSR modeling identified significant wavelengths based on the regression coefficient and variable importance of projection. These wavelengths were used to develop multiple linear regression (MLR) models. MC model, with 3 wavelengths, was suitable for most research applications with an RPD = 2.600 and R2 = 0.851. CC model, with 8 wavelengths, did not pass for any use or application due to poor predictive performance (RPD = 1.378, R2 = 0.471). The results showed that only the MC models can be used for quality assessment of roasted coffee.

Non-invasive spectroscopic and imaging systems for prediction of beef quality in a meat processing pilot plant

This study evaluated a range of diffuse reflectance spectroscopic (Vis-NIR spectrophotometers) and imaging (Hyperspectral imaging cameras) instruments for predicting pH, IMF and shear force values of beef in a meat processing pilot plant. A total of 364 beef striploin samples were evaluated and prediction models were developed using PLSR. Models for pH and IMF (except Vis snapshot camera) showed good fit with high Rcv2 (0.29–0.92) and low SECV values. Good prediction accuracy with high Rp2 (0.44–0.90), RPD and low SEP values was also observed. While low values of Rp2 for shear force was observed, the expected curvilinear relationship between predicted values of shear force and predicted values of pH was observed suggesting that spectroscopic measurements were able detect biophysical factors associated to these two attributes. Overall, it can be concluded that diffuse reflectance spectroscopy combined with chemometrics has a great potential to be used as an on/in-line quality monitoring system for the meat processing industry.

Cellulose paper-based SERS sensor for sensitive detection of 2,4-D residue levels in tea coupled uninformative variable elimination-partial least squares

Food safety is a growing concern in recent years. This work presents the design of a simple and sensitive method for predicting 2,4-D (2,4-dichlorophenoxyacetic acid) residue levels in green tea extract employing surface-enhanced Raman spectroscopy (SERS) coupled uninformative variable elimination-partial least squares (UVE-PLS). Herein, SERS active citrate functionalized silver nanoparticles (AgNPs) with enhancement factor 1.51 × 108 was used to prepare cellulose paper (common office) templated SERS sensor for acquiring SERS spectra of 2,4-D. The principle of the work was based on the interaction between 2,4-D and citrate group of AgNPs via chlorine atoms in the concentration range 1.0 × 10−4 to 1.0 × 103 µg/g. Three different wavenumber selection chemometric algorithms were studied comparatively to build an optimum calibration model, among them UVE-PLS showed enhanced performance as evident from the RPD value of 6.01 and Rp = 0.9864. Under optimized experimental condition proposed paper-based SERS sensor exhibited detection limit and RSD of 1.0 × 10−4 µg/g and <5%, respectively. In addition, the validation results by HPLC method were satisfactory (p > 0.05).

Evaluation of physiological properties and texture traits of durian pulp using near-infrared spectra of the pulp and intact fruit

This study aimed to investigate the feasibility of non-destructively predicting physiological properties (color, dry matter, and soluble solids) and texture properties (initial firmness, average firmness, rupture force, rupture distance, toughness, average penetrating force, and penetrating energy) of ‘Monthong’ durian using Fourier transform near-infrared spectroscopy of the pulp of the largest locule, the intact fruit at the largest locule, and the stylar end of the intact fruit. Based on partial least squares regression modeling, the internal quality evaluation of durian obtained by scanning the pulp could provide rough screening capability, with coefficient of determination of validation (r2), root mean square error of prediction (RMSEP), and the ratio of standard error of validation to standard deviation (RPD) values for the dry matter content, average penetrating force, and rupture force of 0.89, 3.60%, and 3.27; 0.73, 5.53 N, and 1.95; and 0.74, 6.15 N, and 1.96, respectively. Only the dry matter content of the pulp could be reasonably predicted based on scanning the intact durian fruit at the largest locule, with r2, RMSEP, and RPD values of 0.79, 5.23%, and 2.18, respectively. This finding could be applied at the first stage of trade between durian agriculturalists and exporters to prevent the exportation of immature durian and would be helpful for the industries producing frozen durian pulp and intact durian fruit for export.

Predicting terpene content in dried conifer shoots using near infrared spectroscopy

Terpenes are phytochemicals found in multiple plant genera, especially aromatic herbs and conifers. Terpene content quantification is costly and complex, requiring the extraction of oil content and gas chromatography analyses. Near infrared (NIR) spectroscopy could provide an alternative quantitative method, especially if calibration can be developed with the spectra of dried plant material, which are easier and faster to acquire than oil-based spectra. Here, multispecies NIR spectroscopy calibrations were developed for total terpene content (mono- and sesquiterpenes) and for specific terpenes (α-pinene, β-pinene and myrcene) with five conifers species ( Picea glauca, Picea rubens, Pinus resinosa, Pinus strobus and Thuja occidentalis). The terpene content of fresh shoot samples was quantified with gas chromatography. The NIR spectra were measured on freeze-dried samples (n = 137). Using a subset of the samples, modified partial least squares regressions of total terpene and the three individual terpenes content were generated as a functions of the NIR spectra. The standard errors of the internal cross-validations (values between 0.25 and 2.28) and the ratio of prediction to deviation ratios (RPD values between 2.20 and 2.38) indicate that all calibrations have similar accuracy. The independent validations, however, suggest that the calibrations for total terpene and α-pinene content are more accurate (respective coefficient of determination: r2 = 0.85 and 0.82). In contrast, calibrations for β-pinene and myrcene had a low accuracy (respectively: r2 = 0.62 and 0.08), potentially because of the low concentration of these terpenes in the species studied. The calibration model fits (i.e., r2) are comparable to previously published calibration using the spectra of dried shoot samples and demonstrate the potential of this method for terpenes in conifer samples. The calibration method used could be useful in several other domains (e.g. seedling breeding program, industrial), because of the wide distribution of terpenes and especially of pinenes.

Hyperspectral characteristics and quantitative analysis of leaf chlorophyll by reflectance spectroscopy based on a genetic algorithm in combination with partial least squares regression.

The precise and nondestructive detection of leaf chlorophyll content is one key to assessing the health status of crops. The objective of this study was to develop a precision method for determining the leaf chlorophyll content in rape. A genetic algorithm (GA) combined with the partial least squares (PLS) method was used to establish a chlorophyll content PLS regression estimation model based on screening the characteristic spectral regions of chlorophyll. The results show that the characteristic bands of chlorophyll in rape are 510-535, 675-695, 905-965, 1025-1225, 1165-1175, 1295-1385, 1495-1765, 1875-1895, 1970-2145, and 2179-2185nm. Based on the characteristics of each input spectrum, the Rv2 and RPD values of the best model reached 0.97 and 5.41, respectively. This represented an increase of 0.20 and 3.42, respectively, over these values for the original full-spectrum model. The best model also achieved an RMSEP of 2.63mgg-1, which was only 3.59% of the total sample average and was 3.78mgg-1 less than that of the original full-spectrum model. Therefore, the best model provided good prediction accuracy for the chlorophyll content of rape. The model based on the Log (1/R) spectral transformation performed best in terms of prediction accuracy. The genetic algorithm combined with the partial least squares method (GA-PLS) can effectively screen the characteristic bands of rape chlorophyll, reduce the number of variables in the model, and produce high estimation accuracy.

LF-NMR intelligent evaluation of rheology and printability for 3D printing of cookie dough pretreated by microwave

This study was aimed at intelligent evaluation rheological properties of three-dimensional (3D) printing cookie dough system treated with microwave based on low-field nuclear magnetic resonance (LF-NMR). The results showed that after microwave treatment, starch was partially gelatinized and water dispersed (the semi-bound water A22 decreased mainly at the whole NMR spectrum), which lead to the changes in rheology and 3D printing properties of the system. The apparent viscosity and rheological parameters G′ and G″ of the system showed an upward trend as whole which consistent with textural properties. The Pearson correlation analysis revealed that the parameters A22 and ATotal of NMR had good correlation with the rheological parameters η, G′ and G″. The prediction model was constructed combination of LF-NMR and PLSR to rapid nondestructive monitoring of rheology and printability. The PLSR models exhibited superior predictive performance with the correlation coefficients of rheological properties (η, G′ and G″) were 0.912, 0.985 and 0.943, and the RPD values were 3.665, 3.419 and 3.391 respectively, which showed that the rheological properties of 3D printing cookie dough system can be predicted accurately with the established model.

Predicting the quality traits of white striped turkey breast by visible/near infra-red spectroscopy and multivariate data analysis

The appearance of white striations over the breast of chicken and turkey meat is considered as a recent emerging and growing problem. The aim of this research is to investigate the ability of visible-near infra-red (VIS/NIR) spectroscopy to predict the quality traits of different levels of white striping (thickness of white striations, moderate < 1 mm and severe ≥ 1 mm) defects in turkey breast muscle. Accordingly, 36 turkey breast fillets affected by different level of white striping defects (normal, moderate and severe) were selected from 20-wk old tom turkeys. Colour traits (L*, a* and b*), pH, marinade uptake, drip loss, cooking loss, and chemical composition (moisture, fat, protein and ash) have been evaluated. Our findings showed that prediction models using partial least squares (PLS) were good for colour traits (a* for example; RPD values were 3.22 and 1.27, R2 P were 0.91 and 0.57 while RER values were 11.8 and 3.12) , pH (RPD values were 5.00 and 0.01, R2 P were 0.95 and 0.07 while RER values were –1.00 and 15.50), and chemical composition (protein content for instance, the prediction values were as the following: RPD values were 1.93 and 0.79, R2 P were 0.80 and 0.34 and then RER were 8.48 and 3.80) in particular for normal and severe white striped meat respectively. In conclusion, the results of this research showed that VIS/NIR spectroscopy prediction models were satisfactory to predict the quality traits in the majority of cases. HIGHLIGHTS White striping is a recent muscle abnormality that affects adversely poultry meat. Visible-near infra-red (VIS/NIR) spectroscopy was used to predict the quality traits of turkey breast meat affected by white striping. Partial least squares (PLS) was good indicator to predict several quality traits of normal meat.