Soil organic matters (SOM), specifically carbon and nitrogen, bring numerous benefits to soil’s physical and chemical properties. In this paper, we employ spectral data obtained by Fourier transform ...near-infrared (FT-NIR) spectroscopy to predict the content of organic carbon (OC) and total nitrogen (TN) in mineral soils. To address the limitation generated by massive hyperparameters on convolution neural network (CNN), we substitute using a technique named SVD concatenation to learn features. The proposed model combines the layers of fully connected and regression to complete the prediction task. We abbreviate it as SVD-CNN, which is capable provide a multi-tasks output simultaneously. In experiments, we study the prediction performances of SVD-CNN on two datasets of FT-NIR and LUCAS 2009 topsoil. Based on different situations, the highest performance of R2 achieves 0.8891 for OC and 0.9048 for TN on the FT-NIR dataset. Similarly, the most prominent results on the LUCAS 2009 topsoil dataset are R2 = 0.9304, RMSE = 3.6014 for OC and R2 = 0.9319, RMSE = 0.2733 for TN. Furthermore, we also evaluate the results obtained by solely using SVD concatenation, which reveals SVD-CNN performs a better generalization ability.
Display omitted
•Provide a novel deep SVD concatenation model to predict OC and TN accurately.•SVD-CNN behaves terrific prediction results using much fewer hyperparameters.•Employ Mineral soils of FT-NIR and LUCAS 2009 topsoil to verify the performances.•Soil organic matter is perceived as essential to soil function and health.
Honey is an extract of floral and secretions from a variety of bees. Some honey manufactures adulterate pure honey with industrial sugar, chemicals, and water either directly or indirectly. Many ...methods have been developed to detect honey adulterants including physicochemical analysis, microscopy, chromatography, immunoassay, thixotropicity, DNA metabarcoding, sensors, and spectroscopy. However, the most promising methods for the development of a portable test kit for honey adulterant detection are ELISA, electronic tongue, and NIR. The most sensitive and accurate method is NIR. These methods have shown satisfactory results when used individually or combined. Further research is still required to trial different combinations of methods to improve accuracy and the ability to detecting a wide variety of adulterants simultaneously. There is a need to develop a portable honey adulterant detection method, such as NIR spectroscopy using a smartphone.
•Honey is often adulterated directly or indirectly with sugars and inferior honey.•No one method is available to detect all the adulterants in honey.•No portable method is available to date for honey adulterants detection.•To develop a portable kit using promising methods: ELISA, sensors, and NIR.•Proposed to develop the portable method: NIR spectroscopy using a smartphone.
Fruits and vegetable powders are gaining attention due to their flavor, color, high nutritional content, and consumers’ demand for compact and lightweight foods. This study was undertaken to explore ...their commercial applications as an edible coating onto sliced apples to incorporate various functional and nutritional characteristics to apple chips. The subsequent aim of this work was to investigate miniature NIR spectroscopy as a tool to rapidly monitor and develop a predictive model for the drying of edible coating on these apple slices. The apple slices coated with selected fruit powders were dried and compared with uncoated samples. NIR spectra were collected at different drying times, and multivariate calibration models were developed using partial least-squares regression (PLSR) with raw and various pre-treated spectra. Instead of selecting different sets of feature wavelengths for coated and uncoated apple slices, a set of 7 key wavelengths was selected for convenient application to monitor moisture content during drying of apples with or without edible coatings. The results showed that the miniature NIR spectroscopy was able to monitor the drying process and discriminate between the coated and uncoated apple slices and drying times, primarily by the differences in sugar and water absorption bands.
•We used portable NIR for real-time monitoring of MC in apple slices.•We selected key wavelengths using VIP method.•We developed PLSR model to estimate the optimal drying time.
•Suitable habitat for Amomum tsaoko is located in border areas of Yunnan Province.•Highly suitable habitat favors the accumulation of Amomum tsaoko chemical components.•FT-NIR spectroscopy can ...accurately identify Amomum tsaoko from different origins.•ResNet can quickly and efficiently identify Amomum tsaoko from different origins.
Lanxangia tsao-ko (Crevost & Lemarié) M.F.Newman & Škorničk (L. tsao-ko) is widely cultivated for its important medicinal and economic values. However, there is a lack of regional planning studies, ecological suitability studies, and incomplete species distribution surveys. In this study, the maximum entropy model was used to simulate the species distribution of L. tsao-ko under current climatic scenarios. On this basis, Fourier transform near infrared (FT-NIR) spectroscopy combined with chemometrics and deep learning was further employed to comprehensively assess the geographical origin of L. tsao-ko. The results showed that under the current climate scenario, the suitable habitats of L. tsao-ko were mainly distributed in the western, northwestern and southeastern regions of Yunnan province, and southeastern areas, with an area of 8.20 × 104 km2. Absorbance values of FT-NIR spectra of samples from different suitable habitats showed a trend of highly suitable areas > moderate > low. Then, a two-dimensional correlation spectroscopy (2DCOS) images based on FT-NIR spectroscopy combined with a residual convolutional neural network (ResNet) was proposed for recognizing the geographic origin of L. tsao-ko. The training and test sets of synchronous 2DCOS images in the full band had 100 % accuracy, and all samples were correctly recognized in the external validation set. The results showed that the geographical origin of L. tsao-ko could be accurately identified based on full-band synchronous 2DCOS images, but attention should also be paid to the spectral information carried by a single spectral region (10000–7500 cm−1, 7500–5415 cm−1 and 5415–4000 cm−1).The results of the study provide a reference for the introduction and cultivation of L. tsao-ko.
Drought is a major abiotic stress that adversely affects the growth and productivity of plants. Malondialdehyde (MDA), a substance produced by membrane lipids in response to reactive oxygen species ...(ROS), can be used as a drought indicator to evaluate the degree of plasma membrane damage and the ability of plants to drought stress tolerance. Still measuring MDA is usually a labor- and time-consuming task. In this study, near-infrared (NIR) spectroscopy combined with partial least squares (PLS) was used to obtain rapid and high-throughput measurements of MDA, and the application of this technique to plant drought stress experiments was also investigated. Two exotic conifer tree species, namely, slash pine (
Pinus elliottii
) and loblolly pine (
Pinus taeda
), were used as plant material exposed to drought stress; different types of spectral preprocessing methods and important feature-selection algorithms were applied to the PLS model to calibrate it and obtain the best MDA-predicting model. The results show that the best PLS model is established
via
the combined treatment of detrended variable–significant multivariate correlation algorithm (DET-sMC), where latent variables (LVs) were 6. This model has a respectable predictive capability, with a correlation coefficient (
R
2
) of 0.66, a root mean square error (RMSE) of 2.28%, and a residual prediction deviation (RPD) of 1.51, and it was successfully implemented in drought stress experiments as a reliable and non-destructive method to detect the MDA content in real time.
Display omitted
•The optimized continuous wavelet transform (CWT) was used to preprocess soil spectra.•Extreme learning machine combined with CARS, SPA, MCUVE and GA was applied to determine pH of ...lime concretion black soil.•The GA-ELM and CARS-ELM achieved good results for determining pH in lime concretion black soil using Vis-NIR spectroscopy.•The prediction mechanism of soil pH using Vis-NIR spectroscopy in lime concretion black soil was presented.
Variable selection is widely accepted as an important step in the quantitative analysis of visible and near-infrared (Vis-NIR) spectroscopy, as it tends to improve the model’s robustness and predictive ability. In this study, a total of 140 lime concretion black soil samples were collected from two towns in Guoyang County, China. The Vis-NIR spectra measured in the laboratory were used to estimate soil pH by an extreme learning machine (ELM). First, the soil spectra were treated by the optimized continuous wavelet transform (CWT), and then four spectral feature selection methods (competitive adaptive reweighted sampling, CARS; successive projections algorithm, SPA; Monte Carlo uninformative variable elimination, MCUVE; genetic algorithm, GA) were applied with ELM in the CWT domain to determine the techniques with most predictions. For comparison, The PLS and SVM models were also developed. The coefficient of determination (R2), root mean square error (RMSE), and residual prediction deviation (RPD) were used to evaluate the model performance. Based on the validation dataset, the performance of the ELM models was superior to that of the PLS and SVM models expect SPA and MCUVE. In the ELM models, the order of the prediction accuracy was GA-ELM (R2p = 0.86; RMSEp = 0.1484; RPD = 2.64), CARS-ELM (R2p = 0.84; RMSEp = 0.1565; RPD = 2.50), ELM (R2p = 0.84; RMSEp = 0.1572; RPD = 2.49), SPA-ELM (R2p = 0.84; RMSEp = 0.1589; RPD = 2.47) and MCUVE-ELM (R2p = 0.83; RMSEp = 0.1599; RPD = 2.45). The proposed method of CARS-ELM had a relatively strong ability for spectral variable selection while retaining excellent prediction accuracy and short computing time (0.39 s). In addition, the variables selected by the four methods (CARS, SPA, MCUVE and GA) indicated the prediction mechanism for pH in lime concretion black soil may be the relation between pH and iron oxides and organic matter. In conclusion, CARS-ELM has great potential to accurately determine the pH in lime concretion black soil using Vis-NIR spectroscopy.
There are nearly 40 items that should ideally be reported when an NIR (near infrared) spectroscopy project is completed, either as a report or as a scientific paper. However, in our reading of the ...extensive literature, many of the papers presented or published report no more than 6–10 of these. The purpose of this tutorial is to indicate all of the items and the reasons for reporting them. Most of the items that need to be reported are important for anyone who seeks to duplicate the type of application and methods reported in a peer-reviewed journal article for their own work. Practically, all of the items are significant to any worker if the eventual objective of their work is to extend it to the level of industrial application. The tutorial will summarize these items, and give some explanation for their inclusion. The tutorial should be useful to potential authors, as well as to reviewers.
The potential of the visible–near infrared (Vis–NIR; 400–2500nm) laboratory spectroscopy for the estimation of soil properties has been previously demonstrated in the literature, and the Vis–NIR ...spatial spectroscopy is expected to provide direct estimates of these properties at the soil surface. The aim of this work was to examine whether Vis–NIR airborne spectroscopy could be used for mapping eight of the most common soil properties, including clay, sand, silt, calcium carbonate (CaCO3), free iron, cation-exchange capacity (CEC), organic carbon and pH, without mispredicting the local values of these properties and their spatial structures. Our study was based on 95 soil samples and a HyMap hyperspectral image available over 192 bare soil fields scattered within a 24.6km² area. Predictions of soil properties from HyMap spectra were computed for the eight soil properties using partial least squares regression (PLSR). The results showed that 1) four out of the eight soil properties (CaCO3, iron, clay and CEC) were suitable for mapping using hyperspectral data, and both accurate local predictions and good representations of spatial structures were observed and 2) the application of prediction models using hyperspectral data over the study area provided statistical characterizations within soilscape variations and variograms that describe in details the short range soil variations. All results were consistent with the previous pedological knowledge of the studied region. This study opens up the possibility of more extensive use of hyperspectral data for digital soil mapping of these successfully predicted soil properties.
NIR spectroscopy combined with chemometric methods has been used to develop a prediction models of the most influential parameters in curing process of two types of hams (140 hams) using different ...salting techniques, lean hams salted on a tray and fatty hams in a tub, in which sodium is partially replaced. Spectral data were examined by principal component analysis and cross-validated calibration equations were developed using partial-least squares regression. Calibration errors for each parameter, obtained from cross validation (RMSECV), were similar to those obtained by reference method. For lean and fatty hams the RMSECV values were: Moisture 0.78% and 0.80; Fat 2.5 and 1.2%; Protein 0.7 and 1.7%; water activity 0.008 and 0.006; Proteolysis Index 1.6 and 1.7%; Sodium 0.11 and 0.10%; and Potassium 0.04 and 0.10. Results allow the prediction of the parameters involved in ham curing process, demonstrating the viability of the proposed method for the control and monitoring of the different stages until obtaining the final product.
•Evaluation of curing process of ham with low sodium content by NIR spectroscopy•Development of prediction models of the influential parameters in ham curing process•NIRS shows viability for control and monitoring of the stages in ham curing process.