Root Mean Square Error Of Prediction Research Articles

Prediction of body condition score throughout lactation by random regression test-day models.

Regular monitoring of body condition score (BCS) changes during lactation is a crucial management tool in dairy cattle; however, the current BCS measurements are often discontinuous and unevenly spaced in time. The aim of this study was to investigate the ability of random regression test-day models (RR-TDM) to predict BCS for the entire lactation in dairy cows even if the actual scoring is limited to one BCS record. The data consisted of test-day records of milk yield (MY), fat percentage (FP), protein percentage (PP) and BCS (based on a 9-point scale with unit increments; 1-9) collected from 2014 to 2022 in 128 herds in the Walloon Region of Belgium. In total, 20,698 test-day records on 2166 first-parity Holstein cows (2-12 with an average of 9.42 test-day records per cow) were available for MY, FP and PP; and 7985 records on the same animals (2-12 with an average of 3.68 records per cow) were available for BCS. To estimate the solutions, only one randomly selected BCS record per animal along with all her MY, FP and PP records were used, which were then used to predict BCS data (calibration set). The remaining BCS (1-11 with an average 2.86 BCS records per animal) were used to evaluate the goodness of the predictions (validation set). Multiple-trait RR-TDM was used to estimate (co)variance components through the average information restricted maximum likelihood (AI-REML) algorithm. Predicted BCS were grouped into nine classes as the original observed BCS used for comparison. Pearson correlation between the predicted and observed BCS, prediction error (PE), absolute prediction error (APE) and root mean squared prediction error (RMSE) were calculated. Mean (standard deviation; SD) BCS was 4.97 (1.01), 4.95 (1.07) and 4.98 (1.00) BCS units in the full, calibration and validation datasets, respectively. Pearson correlation between the observed and predicted BCS was 0.71, mean (SD) PE was 0.04 (0.52) BCS units, mean (SD) APE was 0.48 (0.53) BCS units and RMSE was 0.72 BCS units. These findings demonstrate the ability of RR-TDM to predict BCS for the entire lactation using a single BCS record along with available test-day records of milk yield and composition in Holstein dairy cows.

Reflectance spectroscopy analysis and lithium content estimation in lithium-rich rocks and stream sediments: Insights from Tuanjie Peak, Western Kunlun, China

Lithium, a rare metal of strategic importance, has garnered heightened global attention. This investigation delves into the laboratory visible-near infrared and short-wavelength infrared reflectance (VNIR-SWIR 350 nm–2500 nm) spectral properties of lithium-rich rocks and stream sediments, aiming to elucidate their quantitative relationship with lithium concentration. This research seeks to pave new avenues and furnish innovative technical solutions for probing sedimentary lithium reserves. Conducted in the Tuanjie Peak region of Western Kunlun, Xinjiang, China, this study analyzed 614 stream sediments and 222 rock specimens. Initial steps included laboratory VNIR-SWIR spectral reflectance measurements and lithium quantification. Following the preprocessing of spectral data via Savitzky-Golay (SG) smoothing and continuum removal (CR), the absorption positions (Pos2210nm, Pos1910nm) and depths (Depth2210, Depth1910) in the rock spectra, as well as the Illite Spectral Maturity (ISM) of the rock samples, were extracted. Employing both the Successive Projections Algorithm (SPA) and genetic algorithm (GA), wavelengths indicative of lithium content were identified. Integrating the lithium-sensitive wavelengths identified by these feature selection methods, A quantitative predictive regression model for lithium content in rock and stream sediments was developed using partial least squares regression (PLSR), support vector regression (SVR), and convolutional neural network (CNN). Spectral analysis indicated that lithium is predominantly found in montmorillonite and illite, with its content positively correlating with the spectral maturity of illite and closely related to Al-OH absorption depth (Depth2210) and clay content. The SPA algorithm was more effective than GA in extracting lithium-sensitive bands. The optimal regression model for quantitative prediction of lithium content in rock samples was SG-SPA-CNN, with a correlation coefficient prediction (Rp) of 0.924 and root-mean-square error prediction (RMSEP) of 0.112. The optimal model for the prediction of lithium content in stream sediment was SG-SPA-CNN, with an Rp and RMSEP of 0.881 and 0.296, respectively. The higher prediction accuracy for lithium content in rocks compared to sediments indicates that rocks are a more suitable medium for predicting lithium content. Compared to the PLSR and SVR models, the CNN model performs better in both sample types. Despite the limitations, this study highlights the effectiveness of hyperspectral technology in exploring the potential of clay-type lithium resources in the Tuanjie Peak area, offering new perspectives and approaches for further exploration.

A 1D-inception-ResNet based global detection model for thin-skinned multifruit spectral quantitative analysis

Near-infrared spectroscopy (NIRS) analysis technology has important research and application value in the inspection of agricultural product quality due to its nondestructive characteristics. Deep learning methods represented by convolutional neural networks (CNNs) reduce the reliance on expert experience and prior knowledge in spectral analysis. They can automatically extract effective feature information from the original spectral data to improve the prediction accuracy of the model. However, the diverse characteristics of fruit varieties present a challenge to the robustness of the model. This study proposes1D-Inception-ResNet, an end-to-end CNN model for multifruit spectral quantitative analysis. The effectiveness of the model is validated on two thin-skinned fruit datasets with similar physicochemical properties. The root mean square error of prediction (RMSEP) for soluble solids content (SSC) and dry matter (DM) were 0.48 °Brix and 0.60 %, and the coefficients of determination of prediction (Rp2) were 0.95 and 0.89, respectively. Compared with traditional partial least squares regression (Rp2 of 0.86 and 0.80, RMSEP of 0.84 °Brix and 0.81 %, respectively) and extreme learning machine (Rp2 of 0.82 and 0.77, RMSEP of 0.95 °Brix and 0.86 %, respectively), our proposed method resulted in a lower RMSEP (46.1% and 28.1% lower, respectively) and higher RP2 (13.1% and 13.4% higher, respectively) for SSC and DM prediction. The results show that compared to other linear and nonlinear algorithms, 1D-Inception-ResNet significantly enhances the modeling effectiveness. Furthermore, external validation using a new sample set showed RMSEP values of 0.62 °Brix and 1.45 % for the SSC and DM models of Inception-ResNet, respectively. In conclusion, using an appropriate CNN network structure to establish a global model for diverse fruits expands the application scope of the model and improves the prediction stability across different species, which is significant in the future application of agricultural products and foods.

Optimizing the effects of potato size and shape on near-infrared prediction models of potato quality using a linear-nonlinear algorithm

The potato size and shape can affect the accuracy of predicting potato quality using near-infrared (NIR) spectroscopy. This study used NIR spectroscopy and a linear-nonlinear algorithm to eliminate the influence of potato size and shape on the accuracy of the prediction model for potato starch and moisture content. Savitzky-Golay (SG) filtering and four dimensionality reduction algorithms (iterative variable subset optimization (IVSO), variable combination population analysis- iteratively retaining informative variables (VCPA-IRIV), bootstrapping soft shrinkage (BOSS), and principal component analysis (PCA)) were used to optimize the NIR spectrum and extract spectral data. Partial least squares (PLS) linear regression and a nonlinear model (convolutional neural network–bi-directional long short-term memory (CNN-BiLSTM)) were used to establish and compare 52 quantitative prediction models. The optimum prediction model was the SG-IVSO-PLS-CNN-BiLSTM. Its correlation coefficient of prediction (Rp), root mean square error of prediction (RMSEP), and relative percent deviation (RPD) were 0.949, 1.350 %, and 3.172 for predicting the moisture content and 0.937, 1.110 %, and 2.863 for predicting the starch content. The SG-IVSO-PLS-CNN-BiLSTM eliminated the influence of potato size and shape on the accuracy of the prediction model. This method is suitable for predicting potato quality in the potato processing industry.

A dielectric method for predicting pear firmness combining deep data augmentation and ensemble learning

Firmness is valuable in evaluating pear quality, as it determines ripeness and storability. This research presents a new method that combines deep data augmentation and ensemble learning for predicting firmness in three pear cultivars using dielectric spectra. Firstly, 126 sets of pear dielectric spectra and firmness data were obtained, and the characteristic dielectric frequencies were selected based on the prediction accuracy of partial least squares regression (PLSR) model established using different preprocessing methods. Then the generative adversarial networks (GAN), least squares GAN (LSGAN), and Wasserstein GAN (WGAN) models with different numbers of generated samples in the model's training set on the prediction accuracy of the PLSR model were compared. Finally, the optimal GAN model was combined with support vector regression (SVR), artificial neural networks (ANN), random forest (RF), and AdaBoost decision tree (AdaBoost-DT) to predict pear firmness. Results showed that the selected characteristic dielectric frequencies included two ε′ and eight ε" points. GAN, LSGAN, and WGAN all improved the prediction accuracy of the PLSR model, and the model accuracy improvement of GAN and LSGAN was proportional to the generated sample numbers added to the training set. GAN had the highest accuracy improvement for PLSR model, with the mean Rp2 (determination coefficient of prediction set) and RMSEP (root mean square error of prediction set) increasing up to 13.70% and −19.48% during 100–1000 epochs (added 126 sets of generated data in the GAN-PLSR model' training set), respectively. Ensemble learning models (RF, AdaBoost-DT) outperformed SVR and ANN. GAN-AdaBoost-DT model added 126 sets of generated data in the training set had the highest prediction accuracy, with average Rp2 and RMSEP of 0.90 and 3.35 N during 300–1000 epochs, respectively. This study proved the feasibility of deep data augmentation and ensemble learning methods to improve the prediction accuracy of pear firmness model without increasing the labor and time costs.

Calibration transfer between NIR instruments using optimally predictive calibration subsets.

In this study, a new approach for the selection of informative standardization samples from the original calibration set for the transfer of a calibration model between NIR instruments is proposed and evaluated. First, a calibration model is developed, after variable selection by the Final Complexity Adapted Models (FCAM) method, using the significance of the PLS regression coefficients (FCAM-SIG) as selection criterion. Then, the resulting model is used for the selection of the best fitting subset of calibration samples with optimally predictive ability, called the optimally predictive calibration subset (OPCS). Next, the standardization samples are selected from the OPCS. The spectra on the slave instruments are transferred to corresponding spectra on the master instrument by the widely used Piecewise Direct Standardization (PDS) method. Thereafter, for the test set on the slave instrument, a 3D response surface plot is drawn for the root mean squared error of prediction (RMSEP) as a function of the number of OPCS samples and window sizes used for the PDS method. Finally, the smallest set of calibration samples, in combination with the optimal window size, providing the optimal RMSEP, is selected as standardization set. The proposed OPCS approach for the selection of standardization samples is tested on two real-life NIR data sets providing 13 X-y combinations to model. The results show that the obtained numbers of OPCS-based standardization samples are statistically significantly lower than those obtained with the widely used representative sample selection method of Kennard and Stone, while the predictive performances are similar.

Aggregation and assessment of grape quality parameters with visible-near-infrared spectroscopy: Introducing a novel quantitative index

Grape quality is generally assessed by measuring individual indicators rather than utilizing a comprehensive metric. A flexible approach to aggregating multiple quality-related parameters of grapes is introduced in this study, and an aggregative index was proposed for the synthetical evaluation of grape quality. First, visible-near-infrared (Vis-NIR) spectral data of two grape varieties were obtained, and the physical and chemical quality indicators were measured as reference standards. The variation trends and correlations of the indicators were analyzed, and an aggregative quality indicator (AQI) was proposed using the min-max normalization and factor analysis methods. The maturity stages of grapes were categorized by analyzing the AQI values. The spectral data underwent preprocessing using multiplicative scatter correction (MSC), Savitzky-Golay smoothing (SG), first-order derivative (FD), SG+FD and de-trending (DT) methods. Feature wavelengths were extracted using uninformative variable elimination (UVE), competitive adaptive reweighted sampling (CARS), and the UVE-CARS algorithms. Three regression models for the AQI were established based on partial least squares regression (PLSR), support vector machine regression (SVR) and convolutional neural network (CNN). Results indicated that the PLSR combined with the FD+SG preprocessing and CARS-selected feature wavelengths achieved optimal performance for Cabernet Sauvignon grapes, with the coefficient of determination for the prediction set (Rp2)=0.972, for the calibration set (Rc2)=0.995, the root mean square error of prediction (RMSEP)=0.040 and residual predictive deviation (RPD)=6.064. In addition, for the Muscat Kyoho grape, CNN combined with DT preprocessed full-spectrum data yielded the best prediction for the AQI, with Rp2=0.989, Rc2=0.981, RMSEP=0.103 and RPD=9.482. This research demonstrated that the non-destructive prediction of grape aggregative qualities can be achieved through the combination of Vis-NIR spectroscopy and a chemometric analysis, offering a practical and comprehensive metric for determining grape maturity stages and optimal harvest times. This approach is particularly valuable for the wine industry, as it facilitates better decision-making and quality control.

Influence of the peel on online detecting soluble solids content of pomelo using Vis-NIR spectroscopy coupled with chemometric analysis

The application of Visible-near infrared spectroscopy (Vis-NIRs) to internal quality detection of pomelo with large sizes and thick peels is still challenging. Considering that the peel has a large mass ratio in pomelo and a great added value in industrial processing, a postharvest processing mode of grading after peeling without affecting consumption of pomelos may be an approach to avoid adverse influence of peel on soluble solids content (SSC) evaluation. In this study, we investigated the performance variation of Vis-NIRs for SSC online determination of pomelos with and without peel for the first time. An online detection system for pomelo spectra acquisition was developed, and the spectral characteristic difference of the intact and peeled pomelos was analyzed. Subsequently, the performance of calibration models was gradually improved and comparatively analyzed by various spectral processing and wavelength selection methods. Furthermore, convolutional neural network (CNN) was utilized to explore its ability for feature extraction. The results showed that combined with standard normal variate (SNV) and second order detrending and changeable-size moving window algorithms, the partial least squares regression (PLSR) model using spectra of peeled pomelos achieved the best prediction results. Specifically, the model attained a determination coefficient of prediction (Rp2) of 0.88, a root mean square error of prediction (RMSEP) of 0.294%, and a residual predictive deviation (RPD) value of 2.57. This study demonstrates that the peel has a significantly negative effect on the prediction performance and the CNN could be an alternative to conventional PLSR method. Our work may open new avenues for the internal quality assessment of agro-products with complex tissue structure.

XGBoost algorithm assisted multi-component quantitative analysis with Raman spectroscopy

To improve prediction performance and reduce artifacts in Raman spectra, we developed an eXtreme Gradient Boosting (XGBoost) preprocessing method to preprocess the Raman spectra of glucose, glycerol and ethanol mixtures. To ensure the robustness and reliability of the XGBoost preprocessing method, an X-LR model (which combined XGBoost preprocessing and a linear regression (LR) model) and a X-MLP model (which combined XGBoost preprocessing and a multilayer perceptron (MLP) model) were developed. These two models were used to quantitatively analyze the concentrations of glucose, glycerol and ethanol in the Raman spectra of mixed solutions. The proportion map of hyperparameters was firstly used to narrow down the search range of hyperparameters in the X-LR and the X-MLP models. Then the correlation coefficients (R2), root mean square of calibration (RMSEC), and root mean square error of prediction (RMSEP) were used to evaluate the models’ performance. Experimental results indicated that the XGBoost preprocessing method achieved higher accuracy and generalization capability, with better performance than those of other preprocessing methods for both LR and MLP models.

Quantitative determination of zearalenone in wheat by the CSA-NIR technique combined with chemometrics algorithms

In the current study, a colorimetric sensor array combined with near-infrared (NIR) spectroscopy was used to quantitatively analyze zearalenone in wheat. The portable NIR spectrometer was used to scan the porphyrin reaction points of the wheat colorimetric sensor and collect spectral data. Subsequently, based on all the NIR spectral data, the two models and three feature selection algorithms are compared, and the best performance model and the best feature variable input are selected. Concurrently, the Kernel-based Extreme Learning Machine (KELM) model optimized by the two parameter optimization algorithms was compared, and the best parameter optimization algorithm was selected. Among all evaluation models, the KELM model optimized by the Competitive Adaptive Reweighted Sampling algorithm combined with the rime optimization algorithm has the best prediction effect. The predicted RP2 is 0.9900, and the root mean square error of prediction (RMSEP) is 18.4610 μg∙kg-1.

Extreme Learning Machine Combined With Whale Optimization Algorithm for Spectral Quantitative Analysis of Complex Samples

ABSTRACTExtreme learning machine (ELM) is combined with the discretized whale optimization algorithm (WOA) for spectral quantitative analysis of complex samples. In this method, the spectral variables selected by the discretized WOA were used to build the ELM model. Before establishing the model, the activation function and the number of hidden nodes in ELM as well as the transfer function of the discretized WOA are determined. Furthermore, the predictive performance of the full‐spectrum partial least squares (PLS), ELM, and WOA‐ELM models was compared with four complex sample datasets: blood, light gas oil and diesel fuels, ternary mixture, and corn samples using root mean square error of prediction (RMSEP) and correlation coefficient (R). The results show that the WOA‐ELM model has the best prediction accuracy compared to full‐spectrum PLS and ELM models. Therefore, the proposed method provides a novel approach for the quantitative analysis of complex samples.

Evaluating Soluble Solids in White Strawberries: A Comparative Analysis of Vis-NIR and NIR Spectroscopy.

In recent years, due to breeding improvements, strawberries with low anthocyanin content and a white rind are now available, and they are highly valued in the market. Strawberries with white skin color do not turn red when ripe, making it difficult to judge ripeness. The soluble solids content (SSC) is an indicator of fruit quality and is closely related to ripeness. In this study, visible-near-infrared (Vis-NIR) spectroscopy and near-infrared (NIR) spectroscopy are used for non-destructive evaluation of the SSC. Vis-NIR (500-978 nm) and NIR (908-1676 nm) data collected from 180 samples of "Tochigi iW1 go" white strawberries and 150 samples of "Tochigi i27 go" red strawberries are investigated. The white strawberry SSC model developed by partial least squares regression (PLSR) in Vis-NIR had a determination coefficient R2p of 0.89 and a root mean square error prediction (RMSEP) of 0.40%; the model developed in NIR showed satisfactory estimation accuracy with an R2p of 0.85 and an RMSEP of 0.43%. These estimation accuracies were comparable to the results of the red strawberry model. Absorption derived from anthocyanin and chlorophyll pigments in white strawberries was observed in the Vis-NIR region. In addition, a dataset consisting of red and white strawberries can be used to predict the pigment-independent SSC. These results contribute to the development of methods for a rapid fruit sorting system and the development of an on-site ripeness determination system.

Rapid Determination of Soil Organic Carbon and Permanganate Oxidizable Carbon: Comparison of Individual and Data Fusion Performance Using Fourier Transform Mid-Infrared Photoacoustic Spectroscopy (FTIR-PAS) and Laser-Induced Breakdown Spectroscopy (LIBS)

Rapid and accurate prediction of soil organic carbon (SOC) and the carbon fractions that are sensitive to management are vital for evaluating soil fertility and SOC turnover from both long-term and short-term perspectives. This study used 396 soil samples to investigate the individual and combined use of FTIR-PAS and LIBS for both SOC and permanganate oxidizable carbon (POXC) prediction coupled with partial least squares regression (PLSR). The results showed that LIBS from 205 to 899 nm (LIBS-H) was suitable for predicting SOC and POXC, with a coefficient of determination in prediction ( R P 2 ) of 0.68 and 0.73, and a root mean square error in prediction (RMSEP) of 0.57% and 169 mg kg−1, respectively. FTIR-PAS also exhibited good potential for the prediction of SOC and POXC with a slightly poorer performance ( R P 2 of 0.66 and RMSEP of 0.59% for SOC; R P 2 of 0.72 and RMSEP of 171 mg kg−1 for POXC). The prediction ability of SOC was improved by low-level data fusion based on direct concatenation of FTIR-PAS spectra and LIBS spectra at the range of 184–205 nm (LIBS-L), resulting in an R P 2 of 0.72 and an RMSEP of 0.53%. In general, there is good potential for combining FTIR-PAS and LIBS-L to improve the SOC prediction. Both FTIR-PAS and LIBS-H can be applied for individual prediction of SOC and POXC. In addition, FTIR-PAS offers the advantages of reduced complexity in the modeling and easier sample preparation.

Comparative analysis of the performance of different approaches for the adaptation of a calibration model for diesel analysis

This work presents a comparative study of three model adaptations from an existing PLS model between two infrared spectrophotometers used in diesel analysis. Domain invariant partial least squares (di-PLS), dynamic orthogonal projection (DOP), and model updating (MU) were compared. The density of diesel was used as a case study. A set of 1156 diesel fuel samples was randomly split into a training set (766 samples) and a validation set (390 samples) of the PLS model. Also, a new set of 105 diesel samples was divided with the Kennard-Stone algorithm into a transferring set (15 samples) used to adapt the calibration model and a test set (90 samples) used to perform the external validation. The comparison was carried out considering the root mean square error of prediction (RMSEP) after model adaptation and the percentage of samples whose prediction error falls within the tolerance limits admitted by the reference method according to the ASTM-E-1655 standard.The results showed reductions of 80%, 87%, and 92% in RMSEP after applying di-PLS, DOP, and MU, respectively. However, di-PLS and DOP failed the test of agreement with the reference method since more than 5% of the validation samples had prediction errors beyond the admitted tolerance limits. In the case study, the results point to MU as the only valid model adaptation to be used in diesel analysis. These results are expected to be of value to the audience interested in the implementation of infrared spectroscopy in industrial applications.

Artificial Neural Network Models for Solution Concentration Measurement during Cooling Crystallization of Ceritinib

The development of a quantitative in-line UV spectroscopic method for monitoring of solute concentration during the crystallization process of the active pharmaceutical ingredient (API), ceritinib is described. The method is based on artificial neural networks (ANN). A seeded cooling crystallization process of ceritinib from tetrahydrofuran was studied as a model system. The model was constructed from collected ATR-UV spectra and temperature records within the metastable zone. The collected spectra were preprocessed with the first derivative using the Savitzky-Golay filter. ANN models with different architectures were created and the optimal architecture was chosen based on the root mean square error of prediction (RMSEP) criterion. In addition, ANN models were compared with the models obtained by the linear partial least squares regression (PLSR). Due to the nonlinear relationship in the data set, ANN models predict the solution concentration with higher accuracy compared to linear models. The developed models were successfully used in real-time solution concentration measurement during ceritinib crystallization along with a supersaturation control module developed in-house.

Coomans plot classification of lard in the ink blends and ink extracts from printed packaging films using lard Fourier transform infrared spectral profile and multivariate analysis

Lard in blends of commercial gravure ink (ranging from 0.5 to 20%) and ink extracts from eleven commercially printed packaging films for foodstuffs was characterized using Fourier transform infrared (FTIR) spectroscopy. The FTIR spectral bands at 4000 ‒ 650 cm-1 associated with the lard fingerprint were acquired and used to classify the lard and its blends using partial least squares (PLS) regression and discriminant analysis (DA). Commercial gravure inks (also used for preparing calibration curve samples), blends of lard ranging from 0.5 to 20% in gravure inks, and commercially printed food packaging films were tested. Linear correlation of predicted and actual values of lard were determined using PLS calibration and validation models. They produced a high coefficient of determination (R2 ) of 0.943, a low root mean square error of calibration (RMSEC) of 1.674, as well as a high R2 = 0.999 and a low root mean square error of prediction (RMSEP) of 1.233, respectively. The PLS calibration was verified employing a leave-oneout cross-validation, while DA was used to classify a series of lard standard, lard-added ink, and commercial food packaging films. The Coomans plot classification of the lardadded ink and commercial food packaging films illustrated that the food packaging samples were plotted in the right and left hemispheres in the lard-added ink class. This result also demonstrated that FTIR coupled with chemometric PLS predicted the lard content in the printing inks with high overall accuracy, as indicated by a low mean difference (MD) value of 0.577 and a low standard deviation of difference (SDD) value of 0.599. The DA allowed the ink packaging samples that potentially contained lard to be distinguished from those without lard. Sample 7 (commercially printed food packaging ink) exhibits the highest possibility of containing lard.

Blend uniformity monitoring in a continuous manufacturing mixing process for a low-dosage formulation using a stream sampler and near infrared spectroscopy

Continuous manufacturing has the potential to offer several benefits for the production of oral solid dosage forms, including reduced costs, low-scale equipment, and the application of process analytical technology (PAT) for real-time process control. This study focuses on the implementation of a stream sampler to develop a near infrared (NIR) calibration model for blend uniformity monitoring in a continuous manufacturing mixing process. Feeding and mixing characterizations were performed for three loss-in-weight feeders and a commercial continuous mixer to prepare powder blends of 2.5–7.5 % w/w ibuprofen DC 85 W with a total throughput of 33 kg/h. The NIR spectral acquisition was performed after the mixing stage using a stream sampler for flowing powders. A continuous mixer shaft speed of 250 RPM was selected to operate the mixing process based on a variability analysis developed with in-line spectral data acquired using the stream sampler at 6 RPM. A partial least squares regression (PLS-R) model was performed and evaluated, yielding a root-mean-square error of prediction (RMSEP) of 0.39 % w/w and a bias of 0.05 % w/w. An independent experimental run conducted two days later revealed that the continuous mixing process and the NIR calibration model presented low day-to-day variation. The minimum practical error (MPE) and sill values through variographic analysis showed low variance associated with the sampling process using the stream sampler. Results demonstrated the promising capacity of the stream sampler coupled to an NIR probe to be implemented within continuous manufacturing processes for the real-time determination of API concentration.

Combining Laser-Induced Breakdown Spectroscopy and Visible Near-Infrared Spectroscopy for Predicting Soil Organic Carbon and Texture: A Danish National-Scale Study.

Laser-induced breakdown spectroscopy (LIBS) and visible near-infrared spectroscopy (vis-NIRS) are spectroscopic techniques that offer promising alternatives to traditional laboratory methods for the rapid and cost-effective determination of soil properties on a large scale. Despite their individual limitations, combining LIBS and vis-NIRS has been shown to enhance the prediction accuracy for the determination of soil properties compared to single-sensor approaches. In this study, we used a comprehensive Danish national-scale soil dataset encompassing mostly sandy soils collected from various land uses and soil depths to evaluate the performance of LIBS and vis-NIRS, as well as their combined spectra, in predicting soil organic carbon (SOC) and texture. Firstly, partial least squares regression (PLSR) models were developed to correlate both LIBS and vis-NIRS spectra with the reference data. Subsequently, we merged LIBS and vis-NIRS data and developed PLSR models for the combined spectra. Finally, interval partial least squares regression (iPLSR) models were applied to assess the impact of variable selection on prediction accuracy for both LIBS and vis-NIRS. Despite being fundamentally different techniques, LIBS and vis-NIRS displayed comparable prediction performance for the investigated soil properties. LIBS achieved a root mean square error of prediction (RMSEP) of <7% for texture and 0.5% for SOC, while vis-NIRS achieved an RMSEP of <8% for texture and 0.5% for SOC. Combining LIBS and vis-NIRS spectra improved the prediction accuracy by 16% for clay, 6% for silt and sand, and 2% for SOC compared to single-sensor LIBS predictions. On the other hand, vis-NIRS single-sensor predictions were improved by 10% for clay, 17% for silt, 16% for sand, and 4% for SOC. Furthermore, applying iPLSR for variable selection improved prediction accuracy for both LIBS and vis-NIRS. Compared to LIBS PLSR predictions, iPLSR achieved reductions of 27% and 17% in RMSEP for clay and sand prediction, respectively, and an 8% reduction for silt and SOC prediction. Similarly, vis-NIRS iPLSR models demonstrated reductions of 6% and 4% in RMSEP for clay and SOC, respectively, and a 3% reduction for silt and sand. Interestingly, LIBS iPLSR models outperformed combined LIBS-vis-NIRS models in terms of prediction accuracy. Although combining LIBS and vis-NIRS improved the prediction accuracy of texture and SOC, LIBS coupled with variable selection had a greater benefit in terms of prediction accuracy. Future studies should investigate the influence of reference method uncertainty on prediction accuracy.

PROSAC as a selection tool for SO-PLS regression: A strategy for multi-block data fusion

BackgroundSpectral data from multiple sources can be integrated into multi-block fusion chemometric models, such as sequentially orthogonalized partial-least squares (SO-PLS), to improve the prediction of sample quality features. Pre-processing techniques are often applied to mitigate extraneous variability, unrelated to the response variables. However, the selection of suitable pre-processing methods and identification of informative data blocks becomes increasingly complex and time-consuming when dealing with a large number of blocks. The problem addressed in this work is the efficient pre-processing, selection, and ordering of data blocks for targeted applications in SO-PLS. ResultsWe introduce the PROSAC–SO–PLS methodology, which employs pre-processing ensembles with response-oriented sequential alternation calibration (PROSAC). This approach identifies the best pre-processed data blocks and their sequential order for specific SO-PLS applications. The method uses a stepwise forward selection strategy, facilitated by the rapid Gram-Schmidt process, to prioritize blocks based on their effectiveness in minimizing prediction error, as indicated by the lowest prediction residuals. To validate the efficacy of our approach, we showcase the outcomes of three empirical near-infrared (NIR) datasets. Comparative analyses were performed against partial-least-squares (PLS) regressions on single-block pre-processed datasets and a methodology relying solely on PROSAC. The PROSAC–SO–PLS approach consistently outperformed these methods, yielding significantly lower prediction errors. This has been evidenced by a reduction in the root-mean-squared error of prediction (RMSEP) ranging from 5 to 25 % across seven out of the eight response variables analyzed. SignificanceThe PROSAC–SO–PLS methodology offers a versatile and efficient technique for ensemble pre-processing in NIR data modeling. It enables the use of SO-PLS minimizing concerns about pre-processing sequence or block order and effectively manages a large number of data blocks. This innovation significantly streamlines the data pre-processing and model-building processes, enhancing the accuracy and efficiency of chemometric models.

An improved meteorological variables-based aerosol optical depth estimation method by combining a physical mechanism model with a two-stage model

A two-stage model integrating a spatiotemporal linear mixed effect (STLME) and a geographic weight regression (GWR) model is proposed to improve the meteorological variables-based aerosol optical depth (AOD) retrieval method (Elterman retrieval model-ERM). The proposed model is referred to as the STG-ERM model. The STG-ERM model is applied over the Beijing-Tianjin-Hebei (BTH) region in China for the years 2019 and 2020. The results show that data coverage increased by 39.0% in 2019 and 40.5% in 2020. Cross-validation of the retrieval results versus multi-angle implementation of atmospheric correction (MAIAC) AOD shows the substantial improvement of the STG-ERM model over earlier meteorological models for AOD estimation, with a determination coefficient (R2) of daily AOD of 0.86, root mean squared prediction error (RMSE) and the relative prediction error (RPE) of 0.10 and 36.14% in 2019 and R2 of 0.86, RMSE of 0.12 and RPE of 37.86% in 2020. The fused annual mean AOD indicates strong spatial variation with high value in south plain and low value in northwestern mountainous areas of the BTH region. The overall spatial seasonal mean AOD ranges from 0.441 to 0.586, demonstrating strongly seasonal variation. The coverage of STG-ERM retrieved AOD, as determined in this exercise by leaving out part of the meteorological data, affects the accuracy of fused AOD. The coverage of the meteorological data has smaller impact on the fused AOD in the districts with low annual mean AOD of less than 0.35 than that in the districts with high annual mean AOD of greater than 0.6. If available, continuous daily meteorological data with high spatiotemporal resolution can improve the model performance and the accuracy of fused AOD. The STG-ERM model may serve as a valuable approach to provide data to fill gaps in satellite-retrieved AOD products.