Principal Component Regression Model Research Articles

Forecasting wine phenolic composition from infrared spectra of grapes extracts and monitoring of fermentations with optimised time-specific prediction models

Incorporating monitoring and forecasting technologies has the potential to enhance the different aspects of winemaking. By monitoring certain chemical parameters, it is possible to evaluate the progress of the fermentation and phenolic extraction, while also detecting deviations from expected behaviour. This study aims to investigate the development of a rapid forecasting method and different strategies to improve the accuracy of process monitoring. The first part involves the introduction of partial least squares (PLS) calibration models able to forecast the trajectories of phenolic extraction during fermentation using grape extract spectra. Additionally, novel methods for reoptimizing calibration models are proposed, with the intention of increasing the prediction accuracy. Whilst this method is transferable to PLS models, principal component regression (PCR) models were used instead as a more simplistic way to test the new methods. First, dynamic PCR linear regression coefficients were adapted over time to capture the compound evolution in the wine matrix. Secondly, PCR calibration models were reoptimized using interpolated spectral and reference data. The forecasting PLS calibration models have shown promising results for total anthocyanin content (mg/L), colour density, polymeric pigments (mg/L), MCP tannins (mg/L), and total phenolic index with overall R2 values on the validation set above 0.6, and low RSMEV values. Using interpolated data to re-optimise models was found to be more effective than global models or those using the calculated regression coefficients methods for predicting the concentration of a particular compound at a certain time point. While R2 values are suboptimal for all considered PCR models, in 72% of the cases analysed, the interpolation method for re-optimisation showed RMSEV values between 6% and 83% lower than those reported for a more traditional PCR model and other re-optimisation strategies. Interpolated models have shown consistency in predicting values, along with good performance metrics, indicating that they could be applied to samples for which calibration models do not exist.

China’s inflation forecasting in a data-rich environment: based on machine learning algorithms

ABSTRACT Inflation forecasting stands as a central concern in macroeconomics. This paper focuses on predicting China’s inflation within a data-rich environment. Specifically, we compile a large panel of China’s monthly macroeconomic and financial variables, employing various machine learning models on this predictor panel to forecast China’s inflation, encompassing both CPI and PPI, across various forecasting horizons extending up to 24 months. Our findings indicate the following: First, the machine learning models, when coupled with a large dataset of macroeconomic and financial predictors, demonstrate a superior ability to forecast China’s inflation compared to benchmark time series models and principal component regression models. These advantages become even more notable at medium-to-long horizons and during periods of high inflation volatility, as well as CPI/PPI divergence periods. Second, our experiments reveal that penalized linear regression models, such as ridge and elastic net, consistently outperform the benchmarks and nonlinear machine learning methods in most cases. Lastly, variables related to price, stock, and money & credit are identified as the most crucial factors for forecasting inflation in China.

Risk governance and regulatory adjustments in the public commercial banks of OECD

PurposeThis study aims to explore the relationship between risk governance characteristics (chief risk officer [CRO], chief financial officer [CFO] and senior directors [SENIOR]) and regulatory adjustments (RAs) in Organization for Economic Cooperation and Development public commercial banks.Design/methodology/approachUsing principal component analysis (PCA) and regression models, the research analyzes a representative data set of these banks.FindingsA significant negative correlation between risk governance characteristics and RAs is found. Sensitivity analysis on the regulatory Tier 1 capital ratio and the total capital ratio indicates mixed outcomes, suggesting a complex relationship that warrants further exploration.Research limitations/implicationsThe study’s limited sample size calls for further research to confirm findings and explore risk governance’s impact on banks’ capital structures.Practical implicationsEnhanced risk governance could reduce RAs, influencing banking policy.Social implicationsThe study advocates for improved banking regulatory practices, potentially increasing sector stability and public trust.Originality/valueThis study contributes to understanding risk governance’s role in regulatory compliance, offering insights for policymaking in banking.

The Positive Association between Grit and Mental Toughness, Enhanced by a Minimum of 75 Minutes of Moderate-to-Vigorous Physical Activity, among US Students

Drawing from the 2015 Gucciardi et al.’s mental toughness (MT) framework, this study examines the association between grit and MT in US college students, while considering the moderating role of at least 75 min of moderate-to-vigorous physical activity (MVPA) based on recommendations from the American College of Sports Medicine. We administered the Grit-S Scale and the Mental Toughness Index in two samples of a total of 340 US undergraduate student-athletes and graduate students. The Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies was employed to ensure internal validity, while statistical procedures including principal component analysis and regression models were utilized to analyze the collected data. A weighted component combining grit and the interaction between MVPA and grit significantly predicted MT, explaining 23% of its variability. Drawing from a specific conceptual framework, this study provides novel insights into the relationship between grit, engagement in at least 75 min of MVPA per week, and MT among US collegiate students. The findings support a positive association between grit, MVPA, and both MT and a specific component of MT, highlighting the significance of these factors in enhancing performance and suggesting potential implications for future research and practical applications in the field.

Transformations for non-destructive evaluation of brix in mango by reflectance spectroscopy and machine learning

Mango is a very popular climacteric fruit in America and Europe. Among the internal properties of the mango, total soluble solids (TSS) are an adequate indicator to estimate the quality of mango, however, the measurement of this indicator requires destructive tests. Several research have addressed similar issues; they have made use of pre-processing transformations without making it clear which of them is statistically better. Here, we created a new spectral database to build machine learning (ML) models. We analyzed a total of 18 principal component regression (PCR) models and 18 partial least squared regression (PLSR) models, where 4 types of transformations, 3 different feature extractors, and 3 different pre-processing techniques are combined. The research proposes a double cross validation (CV) both to determine the optimal number of components and to obtain the final metrics. The best model had a root mean square error (RMSE) of 1.1382 °Brix and a RMSE on the transformed scale of 0.5140. The best model used 4 components, used y<sup>2</sup> transformation, reflectance R as the independent variable and MSC as a pre-processing technique.

Bayesian LASSO for population stratification correction in rare haplotype association studies.

Population stratification (PS) is one major source of confounding in both single nucleotide polymorphism (SNP) and haplotype association studies. To address PS, principal component regression (PCR) and linear mixed model (LMM) are the current standards for SNP associations, which are also commonly borrowed for haplotype studies. However, the underfitting and overfitting problems introduced by PCR and LMM, respectively, have yet to be addressed. Furthermore, there have been only a few theoretical approaches proposed to address PS specifically for haplotypes. In this paper, we propose a new method under the Bayesian LASSO framework, QBLstrat, to account for PS in identifying rare and common haplotypes associated with a continuous trait of interest. QBLstrat utilizes a large number of principal components (PCs) with appropriate priors to sufficiently correct for PS, while shrinking the estimates of unassociated haplotypes and PCs. We compare the performance of QBLstrat with the Bayesian counterparts of PCR and LMM and a current method, haplo.stats. Extensive simulation studies and real data analyses show that QBLstrat is superior in controlling false positives while maintaining competitive power for identifying true positives under PS.

Rapid monitoring of heavy metal-ammonia complexes in solutions by UV–vis/ATR-FTIR spectroscopy and chemometric models

Ammonia can form stable chemical complexes with heavy metal ions, which significantly affect the treatment efficiency of these wastewaters. Thus, accurately determining the concentration of heavy metal ammonia complex ions is crucial to understanding the complex decomposition mechanism. The current study predicted the composition of copper ammonia solution through thermodynamic calculations. The mid-infrared first derivative spectra obtained from density functional theory (DFT) calculation and measurements of the simulated solutions were compared, which indicated that [Cu(NH3)4]2+ was the primary form of complexes in solution. The acquired FTIR spectra and UV–vis spectra demonstrated a strong correlation with the [Cu(NH3)4]2+ concentrations; whereas a principal component regression (PCR) model was implemented for concentration computation. The UV–vis-PCR model was found to be a fast and accurate method for quantification of copper-ammonia complex concentration, and its detection limit and quantification limit could reach 5 mg·L−1 and 10 mg·L−1, respectively, in the 5–200 mg·L−1 range. This study established qualitative and quantitative methods for analyzing copper ammonia complex in water, which provided the feasibility for rapid real-time monitoring of copper ammonia complex.

Differentiation through E-nose and GC-FID data modeling of rosé sparkling wines elaborated via traditional and Charmat methods.

The growing demand for rosé sparkling wine has led to an increase in its production. Traditional or Charmat wine-making influence the aromatic profiles in wine. An analysis such as gas chromatography makes an accurate assessment of wines based on volatile detection but is resource intensive. On the other hand, the electronic nose (E-nose) has emerged as a versatile tool, offering rapid, cost-effective discrimination of wines, and contributing insights into quality and production processes because of its aptitude to perform a global aromatic pattern evaluation. In the present study, rosé sparkling wines were produced using both methods and major volatile compounds and polyols were measured. Wines were tested by E-nose and predictive modelling was performed to distinguish them. Volatile profiles showed differences between Charmat and traditional methods, especially at 5 months of aging. A partial least square discriminant analysis (PLS-DA) was carried out on E-nose detections, obtaining a model that describes 94% of the variability, separating samples in different clusters and correctly identifying different classes. The differences derived from PLS-DA clustering agree with the results obtained by gas-chromatography. Moreover, a principal components regression model was built to verify the ability of the E-nose to non-destructively predict the amount of different volatiles analyzed. Production methods of Rosé sparkling wine affect the final wine aroma profiles as a result of the differences in terms of volatiles. The PLS-DA of the data obtained with E-nose reveals that distinguishing between Charmat and traditional methods is possible. Moreover, predictive models using gas chromatography-flame ionization detection analysis and E-nose highlight the possibility of fast and efficient prediction of volatiles from the E-nose. © 2023 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Comparison of principal component regression (PCR) and partial least square regression (PLSR) modeling methods for quantifying polyethylene (PE) in recycled polypropylene (rPP) with near-infrared spectrometry (NIR)

Recycled polypropylene (rPP) often contains a small amount of polyethylene (PE). Since polypropylene (PP) and PE are incompatible, the presence of PE compromises the performance of rPP materials and needs to be closely monitored. In our previous work, Raman and near-infrared (NIR) spectrometries were evaluated to monitor PE content in rPP with partial least square regression (PLSR) modeling. The NIR spectrometry exhibited a wider application range, but the accuracy of the prediction models might be further improved. In the current work, a different modeling method, principal component regression (PCR) was employed to analyze PE content in rPP with NIR spectrometry. Spectrum pretreatment methods, including multivariate scatter correction (MSC), standard normal variate transformation (SNV), smoothing, and first derivative, were investigated to improve the NIR spectrum quality. Forward and backward interval methods were used to optimize spectral range selection. The outcomes were compared with our previous PLSR modeling results. The highest accuracy in independent validation was achieved by a PCR model with an R 2 of 0.9991 and a root-mean-square error of prediction (RMSEP) of 0.1596 PE%. On the other hand, a PLSR model achieved the lowest RMSEP of 0.9712 PE% for a non-colored post-consumer rPP sample. The PCR models might be sensitive to interference and more suitable for post-industrial materials, which have a simpler chemical composition. The PLSR models might have better stability and be more suitable for complicated post-consumer samples. Both the PCR and PLSR models were successfully applied to a gray commercial rPP sample.

Application of GIS and spatiotemporal analyses in viral infection modelling using multiple datasets – A case study on the SARS-CoV-2 epidemic

Introduction/objectiveViral and infectious diseases such as COVID-19 continue to pose a significant public health threat. In order to create an early warning system for new pandemics or emerging versions of the virus, it is imperative to study its epidemiology. In this study, we created a geospatial model to predict the weekly contagion and lethality rates of COVID-19 in Ireland. MethodsMore than forty parameters including atmospheric pollutants, metrological variables, sociodemographic factors, and lockdown phases were introduced as input variables to the model. The significant parameters in predicting the number of new cases and the death toll were identified. QGIS software was employed to process input data, and a principal component regression (PCR) model was developed using the statistical add-on XLSTAT. Results and conclusionsThe developed models were able to predict more than half of the variations in contagion and lethality rates. This indicates that the proposed model can serve to help prediction systems for the identification of future high-risk conditions. Nevertheless, there are additional parameters that could be included in future models, such as the number of deaths in care homes, the percentage of contagion and mortality among health workers, and the degree of compliance with social distancing.

Association of Geographic Distance and Hospital Characteristics With Use of Interhospital Transfer by Air: A Multicenter Retrospective Study

ObjectiveInterhospital transfer by air (IHTA) represents the majority of helicopter air ambulance transports in the United States, but the evaluation of what factors are associated with utilization has been limited. We aimed to assess the association of geographic distance and hospital characteristics (including patient volume) with the use of IHTA. MethodsThis was a multicenter, retrospective study of helicopter flight request data from 2018 provided by a convenience sample of 4 critical care transport medicine programs in 3 US census regions. Nonfederal referring hospitals located in the home state of the associated critical care transport medicine program and within 100 miles of the primary receiving facility in the region were included if complete data were available. We fit a Poisson principal component regression model incorporating geographic distance, the number of emergency department visits, the number of hospital discharges, case mix index, the number of intensive care unit beds, and the number of general beds and tested the association of the variables with helicopter emergency medical services utilization. ResultsA total of 106 referring hospitals were analyzed, 21 of which were hospitals identified as having a consistent request pattern. Using the hospitals with a consistent referral pattern, geographic distance had a significant positive association with flight request volume. Other variables, including emergency department visit volume, were not associated. Overall, the included variables offered poor explanatory power for the observed variation between referring facilities in the use of IHTA (r2 = 0.09). Predicted flights based on the principal component regression model for all referring hospitals suggested the majority of referring hospitals used multiple flight programs. ConclusionGeographic distance is associated with the use of IHTA. Unexpectedly, most basic hospital characteristics are not associated with the use of IHTA, and the degree of variation between referring facilities that is explained by patient volume is limited. The evaluation of nonhospital factors, such as the density and availability of critical care or advanced life support ground emergency medical services resources, is needed.

Mineral oil detection in ghee using attenuated total reflectance-fourier transform infrared spectroscopy (ATR-FTIR) in conjunction with chemometrics

Ghee (anhydrous milk fat), being a costly product, is susceptible to adulteration by unscrupulous personnel in the market. The presence of mineral oil in ghee was examined using Attenuated Total Reflectance-Fourier Transform Infrared spectroscopy (ATR-FTIR) spectroscopy in conjunction with chemometrics. Spectral data in the wavenumber range 4000–500 cm−1 were collected for pure ghee, mineral oil, and pure ghee samples spiked with mineral oil at different concentrations (2 %, 4 %, 6 %, 10 %, and 15 %). Principal Component Analysis (PCA) revealed distinct clustering patterns in specific wavenumber regions (1350–950 and 1800–1600 cm−1) at 5% level of significance, effectively distinguishing pure ghee from adulterated samples. Soft Independent Modeling of Class Analogy (SIMCA) showed classification efficiency of 100 % for the samples of pure ghee and mineral oil. Developed Partial Least Square (PLS) and Principal Component Regression (PCR) models showed high R2 values (above 0.99) indicating strong predictive accuracy for mineral oil adulteration levels in ghee. Thus, using ATR-FTIR and chemometrics, detection of as low as 2 % of mineral oil in ghee is possible.

Depressive symptoms associated with brain morphometry in Mild Cognitive Impairment stage due to Alzheimer’s and Parkinson’s disease

Objectives: Although there are studies linking depressive symptoms with psychiatric diseases, and then, with brain morphometry, scarce is the literature examining the association between depressive symptoms and brain morphometry in the prodromal stage of neurodegenerative disorders. In the current analysis, we used a fair sample of Mild Cognitive Impairment (MCI) stage due to Alzheimer’s disease (AD) and Parkinson’s disease (PD) patients, to examine the association between different depressive symptoms and a large variety of brain morphometric factors.
 Methods/ Design: Our sample consisted of 352 patients. The Geriatric Depression Scale (GDS) was used for the association with brain measurements. Principal Components Analysis (PCA) and regression models were used for the analyses. Age, sex, years of education, Addenbrooke’s cognitive examination revised (ACE-R), and estimated total intracranial volume were used as covariates.
 Results: Factor3 was significantly and positively correlated with GDS total, Dysthymia, Anxiety and Hopelessness. r_factor1, r_factor2 and r_factor5 were significantly and positively correlated with Anxiety, while r_factor5 was also correlated with GDS total. Concerning volumes, v_factor3 was found to be correlated with GDS total, Dysthymia, Anxiety and Hopelessness.
 Conclusions: The association between depressive symptoms and upcoming neurodegenerative disorders is reflected in human brain structural alterations, suggesting specific modifications in network-like patterns and neuronal connectivity. Characterizing differences in the morphometry of brain regions among MCI patients with depressive symptoms may aid the early diagnosis and treatment of these symptoms.

Population stratification correction using Bayesian shrinkage priors for genetic association studies.

Population stratification (PS) is a major source of confounding in population-based genetic association studies of quantitative traits. Principal component regression (PCR) and linear mixed model (LMM) are two commonly used approaches to account for PS in association studies. Previous studies have shown that LMM can be interpreted as including all principal components (PCs) as random-effect covariates. However, including all PCs in LMM may dilute the influence of relevant PCs in some scenarios, while including only a few preselected PCs in PCR may fail to fully capture the genetic diversity. To address these shortcomings, we introduce Bayestrat-a method to detect associated variants with PS correction under the Bayesian LASSO framework. To adjust for PS, Bayestrat accommodates a large number of PCs and utilizes appropriate shrinkage priors to shrink the effects of nonassociated PCs. Simulation results show that Bayestrat consistently controls type I error rates and achieves higher power compared to its non-shrinkage counterparts, especially when the number of PCs included in the model is large. As a demonstration of the utility of Bayestrat, we apply it to the Multi-Ethnic Study of Atherosclerosis (MESA). Variants and genes associated with serum triglyceride or HDL cholesterol are identified in our analyses. The automatic and self-selection features of Bayestrat make it particularly suited in situations with complex underlying PS scenarios, where it is unknown a priori which PCs are potential confounders, yet the number that needs to be considered could be large in order to fully account for PS.

Forecasting Canadian Age-Specific Mortality Rates: Application of Functional Time Series Analysis

In the insurance and pension industries, as well as in designing social security systems, forecasted mortality rates are of major interest. The current research provides statistical methods based on functional time series analysis to improve mortality rate prediction for the Canadian population. The proposed functional time series-based model was applied to the three-mortality series: total, male and female age-specific Canadian mortality rate over the year 1991 to 2019. Descriptive measures were used to estimate the overall temporal patterns and the functional principal component regression model (fPCA) was used to predict the next ten years mortality rate for each series. Functional autoregressive model (fAR (1)) was used to measure the impact of one year age differences on mortality series. For total series, the mortality rates for children have dropped over the whole data period, while the difference between young adults and those over 40 has only been falling since about 2003 and has leveled off in the last decade of the data. A moderate to strong impact of age differences on Canadian age-specific mortality series was observed over the years. Wider application of fPCA to provide more accurate estimates in public health, demography, and age-related policy studies should be considered.

Potato flour content determination of potato–wheat flour mixture based on hyperspectral imaging

SummaryPotato–wheat flour mixture (PWFM) has important significance for the development of potato staple food products. However, conventional chemical methods are unable to detect the content of potato flour. Hyperspectral imaging (HSI) technology combined with chemometrics was investigated to predict the feasibility of potato flour content in PWFM. In this study, seven pretreatment algorithms were performed to process the raw spectral data. The results showed that the standard normalised variables (SNV) to establish a partial least square regression (PLSR) model had the most predictive accuracy with the determination coefficient of prediction () of 0.9729. The characteristic wavelengths of raw spectral information were extracted using three algorithms to reduce the model complexity. Eventually, the extracted characteristic wavelengths of potato flour content combine with SNV to establish PLSR, principal component regression (PCR) and support vector regression (SVR) models. The results revealed that the optimal model was SNV‐competitive adaptive reweighted sampling (CARS)‐PLSR with the values of of 0.9853. These results showed that HSI determination of potato flour content in PWFM was feasible and provided a non‐destructive method.

Principal Component Regression Modeling and Analysis of PM10 and Meteorological Parameters in Sarajevo with and without Temperature Inversion

The specific geographic location of Sarajevo, which is located in a valley surrounded by mountains, provides the opportunity to analyze the relation between the concentration of PM10 and meteorological parameters with and without temperature inversion. The main aim of this paper was to develop forecasting models of the hourly average of PM10 values in the Sarajevo urban area based on meteorological parameters measured in Sarajevo and on the Bjelasnica mountain with and without temperature inversion by using principal component regression (PCR). Also, this research explored and analyzed the differences in the values of the meteorological parameters and PM10 in Sarajevo with and without temperature inversion, and the difference in temperatures between Sarajevo and Bjelasnica with temperature inversion using statistical hypothesis testing with a total of 240 hypothesis tests performed. The measurements of meteorological parameters were taken from 2020 to 2022 for both Sarajevo (630 m) and the Bjelasnica mountain (2067 m), which allowed for the identification of time periods with and without temperature inversion, while measurements of PM10 were taken only in Sarajevo. Data were collected during the heating season (November, December, January, February and March). Since analyses have shown that only January and November had time periods with and without temperature inversion during each hour of the day, a total of seven cases were identified: two cases with and five cases without temperature inversion. For each case, three PCR models were developed using all principal components, backward elimination and eigenvalue principal component elimination criteria (λ<1). A total of 21 models were developed. The performance of the models were evaluated based on the coefficient of determination R2 and the standard error SE. The backward elimination models were shown to have high performances with the highest value of R2= 97.19 and the lowest value of SE=1.32. The study showed that some principal components with eigenvalues λ<1 were significantly related to the independent variable PM10 and thus were retained in the PCR models. In the study, it was shown that backward elimination PCR was an adequate tool to develop PM10 forecasting models with high performances and that it could be useful for authorities for early warnings or other action to protect citizens from very harmful pollution. Hypothesis tests showed different relations of meteorological parameters and PM10 with and without temperature inversion.

Predictive modeling and analysis of key drivers of groundwater nitrate pollution based on machine learning

Nitrate comtamination of shallow groundwater in agricultural intensification regions is a prevalent and global environment issue affecting food security, human health, and the water ecology. Developing a prediction model for groundwater nitrate contamination is crucial for protection of groundwater resources. Machine learning modeling offer potentials to predict contamination, but often fails to adequately screen input features in complex non-linear environments before modeling. Additionally, there is a tendency to overlook the interpretable description of the relationship between major water chemistry parameters and nitrate concentration after modeling, which hinders scientific decision-making by water resource managers. In this study, a dataset consisting of hydrochemical test results from 316 groundwater samples collected between 2011 and 2015 in intensive agricultural areas of Northeast China was collected. Prior to modeling, the dataset was grouped based on land use type, vadose zones types, and thickness. Based on the grouping of data sets, self-organizing map (SOM) and Spearman's coefficients were employed to identity the correlations between water chemical parameters and nitrate concentration (NO3–-N), which provided a logical basis for selecting the key input variables. A radial basis function artificial neural network (RBF ANN) prediction model and principal components regression (PCR) models was constructed using the dataset, and particle swarm optimization algorithm was applied to determine optimal parameter combinations of the RBF ANN. After conducting modeling, the advantages and disadvantages of RBF ANN and principal components regression (PCR) models were thoroughly examined and discussed, and the primary factors that impact nitrate concentrations in groundwater were analyzed using a PCR model. The results revealed that the RBF ANN model showed greater accuracy, while the PCR model offered better interpretability. Therefore, the integration of the two models is advantageous for nitrate prediction research. Human activities, rainfall, land-use types, vadose zones types and thickness are external factors that affecting nitrate concentration, and the difference between nitrification. Denitrification, and dissimilatory nitrate reduction to ammonium (DNRA) is internal driving factors for the change of nitrate concentration in the aquifer, and partially determine differences in the spatial distribution of aquifer nitrate concentrations under various land use types. This study provides a comprehensive approach for predicting nitrate pollution in groundwater under non-linear environmental conditions, supporting decision making in sustainable groundwater development, management, and conservation.

Expeditious and accurate detection of palm oil adulteration in virgin coconut oil by utilizing ATR-FTIR spectroscopy along with chemometrics and regression models

Virgin coconut oil (VCO), being one of the most treasured and healthy edible oil, is at great risk of blending with cheaper oils like palm oil (PO). Fourier transform infrared (FTIR) spectroscopy with an Attenuated total reflection (ATR) accessory was used together with multivariate chemometrics for the classification and evaluation of numerous concentrations of PO (0.5–30% v/v) in VCO. Linear Discriminant Analysis (LDA) showed a 100% correct classification for both the initial and cross-validation groups for all the subsets of PO blends. Principal components regression (PCR) and Partial least squares regression (PLS-R) calibration models were generated and compared for normal, 1st, and 2nd derivatives of the combined informational spectral domain (3010–2800 cm−1 & 1800–700 cm−1) and separate informational domains of the spectra 3010–2800 cm−1 and 1800–700 cm−1 to get the best-fitting models. Regression models for the 2nd derivatives of 1800–700 cm−1 informational spectral domain gave exquisite outcomes of prediction with immense accuracy and precision with the highest R2 of 0.998, and the root mean square error of prediction (RMSEP) of 0.375% v/v for PLS-R and R2 of 0.998 and RMSEP of 0.441% v/v for PCR respectively. The lowest detectable limit of PO in VCO was estimated as 0.5% v/v. Hence, it has been concluded that PO adulteration of up to 0.5% with VCO can be quickly determined by using ATR-FTIR spectroscopy fitted with multivariate chemometrics.

Soil Attributes Mapping with Online Near-Infrared Spectroscopy Requires Spatio-Temporal Local Calibrations

Building machine learning (ML) calibrations using near-infrared (NIR) soil spectroscopy direct in agricultural areas (online NIR), soil attributes can be fine-scale mapped in a faster and more cost-effective manner, guiding management decisions to ensure the maintenance of soil functions. However, a financially and environmentally unattractive density of 3–5 laboratory soil samples per ha is required to build these calibrations. Since no reports have evaluated if they are reusable or if a new calibration is required for each acquisition, this study’s objective was to acquire online NIR spectra in an agricultural field where ML models were previously built and validated, assessing their performance over time. Two spectral acquisitions were held over a fallow tropical field, separated by 21 days. Soil properties (clay, organic matter, cation exchange capacity, pH, phosphorus, potassium, calcium, and magnesium) were predicted using principal components regression models calibrated with day 1 spectra. Day 1 and day 21 predicted values and maps interpolated by ordinary kriging were compared. Spectra characteristics (morphology, features, and intensity) were evaluated. Predicted values from the two days were not correlated, as no causal relationship was found for the only Pearson’s correlation coefficient (r) significative at 99% (p < 0.01) (calcium, with r = 0.22 in the comparison pairing the nearest neighbors from the two days). For clay, organic matter, and cation exchange capacity, despite their robust prediction on day 1, no significative r values were found, ranging from −0.14 to 0.32, when comparing day 1 with day 21. The maps of the two days presented no similar spatial distribution, hindering their use for management decisions. Soil moisture is a suggested source of variation, but the analysis indicated that it was not the only one, requiring further investigation of the effect of soil surface conditions and environmental variables. Although further investigations should be performed, the results presented suggest that online NIR spectra ML models require spatio-temporal local calibrations to perform properly.