scholarly journals Transferability and scaling of soil total carbon prediction models in Florida

2014 ◽  
Author(s):  
Sabine Grunwald ◽  
Congrong Yu ◽  
Xiong Xiong
Keyword(s):  
Prediction Error ◽  
Near Infrared ◽  
Prediction Models ◽  
Regional Scale ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Total Carbon ◽  
Support Vector ◽  
Domain Iii

The applicability, transfer, and scalability of visible/near-infrared (VNIR)-derived soil models are still poorly understood. The objectives of this study in Florida, U.S. were to: (i) compare three methods to predict soil total carbon (TC) using five fields (local scale) and a pooled (regional scale) VNIR spectral dataset, (ii) assess the model’s transferability among fields, and (iii) evaluate the up- and down-scaling behavior of TC prediction models. A total of 560 TC-spectral sets were modeled by Partial Least Square Regression (PLSR), Support Vector Machine (SVM), and Random Forest. The transferability and up- and down-scaling of models were limited by the following factors: (i) the spectral data domain, (ii) soil attribute domain, (iii) methods that describe the internal model structure of VNIR-TC relationships, and (iv) environmental domain space of attributes that control soil carbon dynamics. All soil logTC models showed excellent performance based on all three methods with R2 > 0.86, bias < 0.01%, root mean square prediction error (RMSE) = 0.09%, residual predication deviation (RPD) > 2.70% , and ratio of prediction error to inter-quartile range (RPIQ) > 4.54. PLSR performed substantially better than SVM to scale and transfer models. Upscaled soil TC models performed somewhat better in terms of model fit (R2), RPD, and RPIQ, whereas downscaled models showed less bias and smaller RMSE based on PLSR. Given the many factors that can impinge on empirically derived soil spectral prediction models, as demonstrated by this study, more focus on the applicability and scaling of them is needed.

scholarly journals Transferability and scaling of soil total carbon prediction models in Florida

2014 ◽  
Author(s):  
Sabine Grunwald ◽  
Congrong Yu ◽  
Xiong Xiong
Keyword(s):  
Prediction Error ◽  
Near Infrared ◽  
Prediction Models ◽  
Regional Scale ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Total Carbon ◽  
Support Vector ◽  
Domain Iii

The applicability, transfer, and scalability of visible/near-infrared (VNIR)-derived soil models are still poorly understood. The objectives of this study in Florida, U.S. were to: (i) compare three methods to predict soil total carbon (TC) using five fields (local scale) and a pooled (regional scale) VNIR spectral dataset, (ii) assess the model’s transferability among fields, and (iii) evaluate the up- and down-scaling behavior of TC prediction models. A total of 560 TC-spectral sets were modeled by Partial Least Square Regression (PLSR), Support Vector Machine (SVM), and Random Forest. The transferability and up- and down-scaling of models were limited by the following factors: (i) the spectral data domain, (ii) soil attribute domain, (iii) methods that describe the internal model structure of VNIR-TC relationships, and (iv) environmental domain space of attributes that control soil carbon dynamics. All soil logTC models showed excellent performance based on all three methods with R2 > 0.86, bias < 0.01%, root mean square prediction error (RMSE) = 0.09%, residual predication deviation (RPD) > 2.70% , and ratio of prediction error to inter-quartile range (RPIQ) > 4.54. PLSR performed substantially better than SVM to scale and transfer models. Upscaled soil TC models performed somewhat better in terms of model fit (R2), RPD, and RPIQ, whereas downscaled models showed less bias and smaller RMSE based on PLSR. Given the many factors that can impinge on empirically derived soil spectral prediction models, as demonstrated by this study, more focus on the applicability and scaling of them is needed.

Measurement of the Irganox Content in Polypropylene Polymers during Extrusion

2005 ◽  
Vol 13 (3) ◽  
pp. 147-154 ◽  
Author(s):  
Wolfgang Becker ◽  
Norbert Eisenreich
Keyword(s):  
Near Infrared ◽  
Prediction Models ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Process Conditions ◽  
Transmission Spectra ◽  
Mean Square ◽  
Score Plot ◽  
Least Square Regression

Near infrared spectroscopy was used as an in-line control system for the measurement of polypropylene filled with different amounts of Irganox additives. For this purpose transmission probes were installed in an extruder. The probes can withstand temperatures up to 300°C and pressures up to 60 MPa. Transmission spectra of polypropylene mixed with an Irganox additive were recorded. PCA score plot was carried out revealing the influence of varying conditions for the mixing of the sample preparation. Prediction models were generated with partial least square regression which resulted in a model which estimated Irganox with a coefficient of detremination of 0.984 and a root mean square error of prediction of 0.098%. Furthermore the possibilities for controlling process conditions by measuring transmission at a specific wavelength were shown.

Classification of Automobile Lubricant by Near-Infrared Spectroscopy Combined with Machine Classification

2011 ◽  
Vol 460-461 ◽  
pp. 667-672
Author(s):  
Yun Zhao ◽  
Xing Xu ◽  
Yong He
Keyword(s):  
Near Infrared ◽  
Prediction Models ◽  
Nir Spectroscopy ◽  
Partial Least Square ◽  
Least Square ◽  
Support Vector ◽  
Training Set ◽  
Test Set ◽  
Svm Model

The main objective of this paper is to classify four kinds of automobile lubricant by near-infrared (NIR) spectral technology and to observe whether NIR spectroscopy could be used for predicting water content. Principle component analysis (PCA) was applied to reduce the information from the spectral data and first two PCs were used to cluster the samples. Partial least square (PLS), least square support vector machine (LS-SVM), and Gaussian processes classification (GPC) were employed to develop prediction models. There were 120 samples for training set and test set. Two LS-SVM models with first five PCs and first six PCs were built, respectively, and accuracy of the model with five PCs is adequate with less calculation. The results from the experiment indicate that the LS-SVM model outperforms the PLS model and GPC model outperforms the LS-SVM model.

scholarly journals Estimation of soil properties with mid-infrared soil spectroscopy across yam production landscapes in West Africa

2021 ◽  
Author(s):  
Philipp Baumann ◽  
Juhwan Lee ◽  
Emmanuel Frossard ◽  
Laurie Paule Schönholzer ◽  
Lucien Diby ◽  
...  
Keyword(s):  
West Africa ◽  
Soil Fertility ◽  
Soil Properties ◽  
Regional Scale ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Total Carbon ◽  
Humid Forest ◽  
Mid Infrared

Abstract. Low soil fertility is challenging the sustainable production of staple crops in the yam belt of West Africa. Quantitative soil measures are needed to assess soil fertility decline and to improve crop fertilization management in the region. We developed and tested a mid-infrared (mid-IR) soil spectral library to enable timely and cost-efficient assessments of soil properties. Our collection included 80 soil samples from four landscapes (10 km × 10 km) and 20 fields/landscape across a gradient from humid forest to savanna, and 14 additional samples from one landscape that had been sampled within the Land Health Degradation Framework. We derived partial least square regression models to estimate soil properties with spectra.The models produced accurate cross-validated estimates of total carbon, total nitrogen, total sulfur, total iron, total aluminum, total potassium, total calcium, exchangeable calcium, effective cation exchange capacity, diethylenetriaminepentaacetic acid (DTPA) extractable iron and clay content (R2 > 0.75). The estimates of total zinc, pH, exchangeable magnesium, bioavailable copper and manganese were less predictable (R2 > 0.50). Our results confirm that mid-IR spectroscopy is a reliable and quick method assess the regional-scale variation in most soil properties, especially the ones closely associated with soil organic matter. Although the relatively small mid-IR library shows satisfactory performance, we expect that frequent but small model updates will be needed to adapt the library to the variation of soil quality attributes within individual fields in the regions and their temporal fluctuations.

scholarly journals Nondestructive Detection of Moisture Content in Walnut Kernel by Near-Infrared Diffuse Reflectance Spectroscopy

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Dan Peng ◽  
Yali Liu ◽  
Jiasheng Yang ◽  
Yanlan Bi ◽  
Jingnan Chen
Keyword(s):  
Moisture Content ◽  
Spectral Data ◽  
Diffuse Reflectance ◽  
Near Infrared ◽  
Diffuse Reflectance Spectroscopy ◽  
Reflectance Spectroscopy ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Support Vector

The rapid and accurate detection of the moisture content is of great significance to the quality evaluation and oil extraction process of walnut kernel. Near-infrared (NIR) spectroscopy is an ideal method for measuring the moisture content in walnut kernel. In this study, a regression model for moisture content in walnut kernel was developed based on NIR diffuse reflectance spectroscopy using chemometric methods. The different spectral pretreatment methods were adopted to preprocess the original spectral data. The whole spectra band was divided into 5 subbands, 10 subbands, 15 subbands, and 20 subbands to screen specific wavelengths relevant to the walnut kernel moisture content. PLS (partial least square regression), MLR (multivariate linear regression), PCR (principle component regression), and SVR (support vector regression) were used to establish the relationship model between the spectral data and measurement values of the moisture content. In comparison, the optimized modeling conditions were determined as follows: detection wavelength 1349–1490 nm, SNV-FD (standard normal variate transformation and first derivative) preprocessing method, and PLS algorithm. Under these conditions, the square correlation coefficient (R2) and root mean square error of prediction (RMSEP) of the prediction model were 0.9865 and 0.0017, respectively. The results of this study provided a feasible method for the rapid detection of moisture content in walnut kernel. To improve the performance and applicability of the model, it is necessary to continuously expand the size of the sample set.

scholarly journals Proximate composition determination in goat cheese whey by near infrared spectroscopy (NIRS)

PeerJ ◽  
2020 ◽  
Vol 8 ◽  
pp. e8619
Author(s):  
Isadora Kaline Camelo Pires de Oliveira Galdino ◽  
Hévila Oliveira Salles ◽  
Karina Maria Olbrich dos Santos ◽  
Germano Veras ◽  
Flávia Carolina Alonso Buriti
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Proximate Composition ◽  
Near Infrared ◽  
Prediction Models ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Composition Analysis ◽  
Reference Methods

Background In Brazil, over the last few years there has been an increase in the production and consumption of goat cheeses. In addition, there was also a demand to create options to use the whey extracted during the production of cheeses. Whey can be used as an ingredient in the development of many products. Therefore, knowing its composition is a matter of utmost importance, considering that the reference methods of food analysis require time, trained labor and expensive reagents for its execution. Methods Goat whey samples produced in winter and summer were submitted to proximate composition analysis (moisture, total solids, ashes, proteins, fat and carbohydrates by difference) using reference methods and near infrared spectroscopy (NIRS). The spectral data was preprocessed by baseline correction and the Savitzky–Golay derivative. The models were built using Partial Least Square Regression (PLSR) with raw and preprocessed data for each dependent variable (proximate composition parameter). Results The average whey composition values obtained using the referenced methods were in accordance with the consulted literature. The composition did not differ significantly (p > 0.05) between the summer and winter whey samples. The PLSR models were made available using the following figures of merit: coefficients of determination of the calibration and prediction models (R2cal and R2pred, respectively) and the Root Mean Squared Error Calibration and Prediction (RMSEC and RMSEP, respectively). The best models used raw data for fat and protein determinations and the values obtained by NIRS for both parameters were consistent with their referenced methods. Consequently, NIRS can be used to determine fat and protein in goat whey.

scholarly journals Prediction of Mineral Composition in Commercial Extruded Dry Dog Food by Near-Infrared Reflectance Spectroscopy

Animals ◽  
2019 ◽  
Vol 9 (9) ◽  
pp. 640 ◽  
Author(s):  
Goi ◽  
Manuelian ◽  
Currò ◽  
Marchi
Keyword(s):  
Mineral Content ◽  
Near Infrared ◽  
Prediction Models ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Coefficient Of Determination ◽  
Emission Spectrometry ◽  
Near Infrared Reflectance ◽  
Dog Food

The pet food industry is interested in performing fast analyses to control the nutritional quality of their products. This study assessed the feasibility of near-infrared spectroscopy to predict mineral content in extruded dry dog food. Mineral content in commercial dry dog food samples (n = 119) was quantified by inductively coupled plasma optical emission spectrometry and reflectance spectra (850–2500 nm) captured with FOSS NIRS DS2500 spectrometer. Calibration models were built using modified partial least square regression and leave-one-out cross-validation. The best prediction models were obtained for S (coefficient of determination; R2 = 0.89), K (R2 = 0.85), and Li (R2 = 0.74), followed by P, B, and Sr (R2 = 0.72 each). Only prediction models for S and K were adequate for screening purposes. This study supports that minerals are difficult to determine with NIRS if they are not associated with organic molecules.

scholarly journals Prediction of Physicochemical Properties in Honeys with Portable Near-Infrared (microNIR) Spectroscopy Combined with Multivariate Data Processing

Foods ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 317
Author(s):  
Olga Escuredo ◽  
María Shantal Rodríguez-Flores ◽  
Laura Meno ◽  
María Carmen Seijo
Keyword(s):  
Physicochemical Properties ◽  
Near Infrared ◽  
Prediction Models ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Botanical Origin ◽  
Linear Discriminant ◽  
Physicochemical Composition ◽  
Natural Foods

There is an increase in the consumption of natural foods with healthy benefits such as honey. The physicochemical composition contributes to the particularities of honey that differ depending on the botanical origin. Botanical and geographical declaration protects consumers from possible fraud and ensures the quality of the product. The objective of this study was to develop prediction models using a portable near-Infrared (MicroNIR) Spectroscopy to contribute to authenticate honeys from Northwest Spain. Based on reference physicochemical analyses of honey, prediction equations using principal components analysis and partial least square regression were developed. Statistical descriptors were good for moisture, hydroxymethylfurfural (HMF), color (Pfund, L and b* coordinates of CIELab) and flavonoids (RSQ > 0.75; RPD > 2.0), and acceptable for electrical conductivity (EC), pH and phenols (RSQ > 0.61; RDP > 1.5). Linear discriminant analysis correctly classified the 88.1% of honeys based on physicochemical parameters and botanical origin (heather, chestnut, eucalyptus, blackberry, honeydew, multifloral). Estimation of quality and physicochemical properties of honey with NIR-spectra data and chemometrics proves to be a powerful tool to fulfil quality goals of this bee product. Results supported that the portable spectroscopy devices provided an effective tool for the apicultural sector to rapid in-situ classification and authentication of honey.

scholarly journals Quantification of potassium concentration with Vis–SWNIR spectroscopy in fresh lettuce

2020 ◽  
Vol 13 (06) ◽  
pp. 2050029
Author(s):  
Yating Xiong ◽  
Shintaroh Ohashi ◽  
Kazuhiro Nakano ◽  
Weizhong Jiang ◽  
Kenichi Takizawa ◽  
...  
Keyword(s):  
Near Infrared ◽  
Potassium Concentration ◽  
Spectral Characteristics ◽  
Public Health Problem ◽  
Short Wave ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Support Vector ◽  
Major Public Health Problem

Chronic kidney disease (CKD) is becoming a major public health problem worldwide, and excessive potassium intake is a health threat to patients with CKD. In this study, visible–short-wave near-infrared (Vis–SWNIR) spectroscopy and chemometric algorithms were investigated as nondestructive methods for assessing the potassium concentration in fresh lettuce to benefit the CKD patients’ health. Interactance and transmittance measurements were performed and the competencies were compared based on the multivariate methods of partial least-square regression (PLS) and support vector machine regression (SVR). Meanwhile, several preprocessing methods [first- and second-order derivatives in combination with standard normal variate (SNV)] and wavelength selection method of competitive adaptive reweighted sampling (CARS) were applied to eliminate noise and highlight the spectral characteristics. The PLS models yielded better prediction than the SVR models with higher correlation coefficients ([Formula: see text]) and residual predictive deviation (RPD), and lower root-mean-square error of prediction (RMSEP). Excellent prediction of green leaves was obtained by the interactance measurement with [Formula: see text], [Formula: see text][Formula: see text]mg/100[Formula: see text]g, and [Formula: see text]; while the transmittance spectra of petioles provided optimal prediction with [Formula: see text], [Formula: see text][Formula: see text]mg/100[Formula: see text]g, and RPD[Formula: see text]=[Formula: see text]3.34, respectively. Therefore, the results indicated that Vis–SWNIR spectroscopy is capable of intelligently detecting potassium concentration in fresh lettuce to benefit CKD patients around the world in maintaining and enhancing their health.

Sign in / Sign up

Export Citation Format

Share Document