Visible Near-infrared Spectra Research Articles

Enhancing soil nitrogen measurement via visible-near infrared spectroscopy: Integrating soil particle size distribution with long short-term memory models

Good quality of soil nitrogen data, which is essential for the advancement of both enhanced agricultural management and ecological environment, traditionally depends on labor intensive chemical procedures. Visible near-infrared (Vis-NIR) spectroscopy, acknowledged for its efficiency, environmental compatibility and rapidity, merges as a promising alternative. However, the effectiveness of Vis-NIR measurement models are significantly compromised by soil particle size distribution (PSD), presenting a substantial challenge in improving the measurement accuracy and reliability. Here an innovative deep learning methodology that integrates PSD with Vis-NIR spectroscopy was proposed for the measurement of nitrogen content in soil samples. By leveraging the LUCAS dataset, different strategies for integrating PSD with Vis-NIR spectral data in deep learning models were explored, revealing that our proposed InSGraL framework, which incorporated mixed features of PSD and spectra as LSTM inputs achieves superior performance. Compared to models utilizing solely Vis-NIR data, InSGraL exhibits a 39.47 % reduction in RMSE and a 42.55 % decrease in MAE, and demonstrates robust performance across various land cover types, achieving an R2 of 0.94 on grassland samples. Moreover, Shapley Additive exPlanations (SHAP) analysis revealed that incorporating PSD modifies the spectral input importance distribution, effectively mitigating spectral interference from particle size while highlighting critical wavelengths previously obscured. This study provides an innovative modeling strategy to mitigate the influence of PSD by integrating it within deep learning framework using Vis-NIR, contributing a deeper understanding of the relationship between PSD and Vis-NIR spectra for the measurement of nitrogen content and offering an effective means to attain soil nitrogen data.

Precision variety identification of shelled and in-shell pecans using hyperspectral imaging with machine learning

Pecans are essential nuts containing polyunsaturated fatty acids and dietary fiber which offer health benefits to humans. They are exported and sold in both in-shell and shelled forms. However, varietal identification poses a challenge to both producers and processors, which results in variety substitution for economic advantages. The aim of this study was to investigate the efficacy of visible near-infrared (VNIR) and near-infrared (NIR) hyperspectral imaging systems (HSI) to accurately identify pecan cultivars (Cape fear, Desirable, Stuart blend, and Sumner). The in-shell and shelled spectra were acquired using VNIR and NIR-HSI at wavelengths 400–1000 nm and 900–1700 nm, respectively. The spectra dimensionality was reduced using principal component analysis (PCA). Thereafter, the selected principal components (PCs) were used to build six machine learning classifiers (Decision Tree, Random Forest, Gradient Boosting, Partial Least Square Discriminant Analysis, Support Vector Machine, and Linear Discriminant Analysis (LDA)) for four-class classification. LDA with and without PCA achieved the highest accuracy for both pecan forms. For shelled pecans, the LDA without PCA achieved 90.59 % and increased to 91.67 % accuracy with PCA on the VNIR spectra, while the LDA without PCA achieved 93.36 % and increased to 93.52 % accuracy with PCA on the NIR spectra. For the in-shell pecans, LDA without PCA achieved 98.59 % and increased to 99.12 % accuracy with PCA on the VNIR spectra, while LDA with and without PCA achieved 98.26 % accuracy for the NIR spectra. Moreover, Successive Projection Algorithm was also implemented for wavelength selection and modeling with satisfactory results. Overall, higher accuracy was achieved in the in-shell pecan. This study revealed the usefulness of HSI systems in identifying pecan varieties.

In-situ prediction of soil organic carbon contents in wheat-rice rotation fields via visible near-infrared spectroscopy

Visible near-infrared (VNIR) spectroscopy is a reliable method for estimating soil properties. However, its effectiveness in accurately predicting soil organic carbon (SOC) contents, particularly in wheat-rice rotation fields, remains uncertain. In this study, we collected 202 samples from wheat-rice fields (0–20 ​cm) in southeastern China and measured in-situ spectra of the vertical surface of the soil cores and the laboratory spectra of the dried and sieved soil samples. Our study focused on evaluating three algorithms - external parameter orthogonalization (EPO), direct standardization (DS), and piecewise direct standardization (PDS) - to address the influence of external factors, particularly soil moisture. To carry out our analysis, the dataset was divided into calibration (141 samples) and validation (61 samples) sets via the Kennard-Stone algorithm. A subset of the corresponding in-situ and laboratory spectra in the calibration set (transfer set) was used to derive the transfer matrix for EPO, DS, and PDS, enabling the conversion of in-situ spectra to laboratory spectra by characterizing their differences. Four machine learning models, including cubist, partial least squares regression (PLSR), random forest (RF), and memory-based learning (MBL), were used to predict the SOC, particulate organic carbon (POC), and mineral-associated organic carbon (MAOC) contents based on the laboratory, in-situ, and corrected in-situ spectra. The results revealed that the laboratory spectra outperformed the non-corrected in-situ spectra, with coefficients of determination (R2) of 0.91, 0.75, and 0.80 for SOC, POC, and MAOC, respectively. Among the models, MBL and PLSR exhibited the highest average R2 at 0.85–0.86. EPO marginally improved the prediction accuracy (R2 increased from 0.85 to 0.87 for SOC, 0.64 to 0.69 for POC, and 0.75 to 0.82 for MAOC). These promising prediction accuracies underscore the potential of VNIR spectra for in-situ predictions in wheat-rice fields in Southeast China, offering insights for predicting SOC contents via in-situ spectroscopy.

Detection of vague object signatures on deep learning surveillance devices

The deep learning of object detection has become a breakthrough in recent years. Many papers demonstrated that this method records significant reliability results. However, the question arises whether objects that were successfully detected are initially conditioned clear in daylight. The object being detected is in the form of a photographic product that has numerous problems. It can be distant or have low-contrast so that their signatures are challenging to recognize, especially detection of persons in surveillance systems for dark-environments. This paper contributes to proving the deep learning method capable of detecting night-person (NP) with high precision and recall in the dark without image enhancement, by using ordinary cameras which operate on day-night or visible-near infrared spectrum runs on embedded systems. For that, an infrared-cut filter mechanical shutter is designed to block for the day or deliver infrared light for the night. The NP signatures are illuminated by an external infrared light source, providing three-channel high-resolution images. The distance of a NP from the camera becomes a decisive successful detection. The external infrared light source makes objects under or overexposed affecting the object being recognized. The validation with thoroughly new data of the NP constantly provides high precision and recall.

Correction methods for visible near-infrared spectroscopy in water pH detection to mitigate temperature influence

The pH value is an important indicator for determining water quality, and visible near-infrared (Vis-NIR) spectroscopy is an ideal technique for rapid detection. The Vis-NIR spectrum of water is greatly affected by temperature. When using Vis-NIR spectroscopy to detect the pH value of water, temperature interference will affect the prediction accuracy of the water pH value. In this study, several chemometric methods developed in recent years were used to correct the spectra of distilled water samples under temperature interference to improve the prediction accuracy of water pH values. Specifically, this includes the external parameter orthogonalization (EPO) algorithm and the generalized least square weighting (GLSW) algorithm. Spectra of distilled water samples at different temperatures in the 400–1049 nm range were collected, and the correction effects of the EPO algorithm and the GLSW algorithm on the spectra after temperature changes, as well as the prediction errors of water pH values, were tested and examined, compared with traditional full-temperature spectral correction models. The results show that both the EPO algorithm and the GLSW algorithm methods require only a small number of representative samples to obtain filtering matrices. By correcting the spectra of distilled water samples at all temperatures to the reference temperature level, good correction effects can be achieved. Additionally, the prediction accuracy of water pH values of the models corrected by both methods is better than that of the traditional method, and the complexity of the models is also greatly reduced.

Pedotransfer functions development for modeling FC and PWP using Vis-NIR spectra combined with PLSR and regression models

The utilization of the soil pedotransfer functions (PTFs) developed based on the basic soil propertied is an alternative, fast, cost-effective and applicable approach for the prediction of field capacity (FC) and permanent wilting point (PWP). In addition, the Visible–Near-Infrared (Vis-NIR) spectra in soil science has gained prominence due to its practicality and relevance. In this paper, we used the data of the soil PWP and FC of 135 soil samples, easily measurable soil properties and Vis-NIR spectroscopy. The multiple linear regression (MLR) model was utilized to formulate PTFs model and Vis-NIR spectroscopy combined with MLR and partial least-squares (PLSR) was used to develop Spectrotransfer Function (STF). Results showed that among the easily measurable soil properties, particle-size diameter (dg) with Beta of −0.72 and −0.63 the most influential parameters for predicting FC and PWP, respectively, followed by the clay content. Developed PTFs for both FC and PWP with a R2 of 0.71 and 0.68, respectively, had a better performance than other previous developed PTFs. Results also revealed that the PLSR with a higher R2 (0.81) and lower RMSE (4 %) significantly performed better in comparison to STF for both FC and PWP prediction.

Feature Variable Selection Based on VIS-NIR Spectra and Soil Moisture Content Prediction Model Construction

The hydrological cycle, surface energy balance, and the management of water resources are all significantly impacted by soil moisture. Because it governs the physical processes of evapotranspiration and rainfall penetration, surface soil moisture is a significant climatic variable. In this work, visible-near infrared (VIS-NIR) bands were used to compare and analyze the spectra of loess samples with varying moisture concentrations. The investigation looked at how changes in the soil moisture content impacted the response of the soil spectra. The researchers used a genetic algorithm (GA), interval combination optimization (ICO), and competitive adaptive reweighted sampling (CARS) to filter feature variables from full-band spectral data. To forecast the moisture content of loess on the soil surface, models like partial least squares regression (PLSR), support vector machine (SVM), and random forest (RF) were created. The findings indicate that: (1) the most reliable spectrum preprocessing technique is the first derivative (FD), which can significantly enhance the model’s prediction power and spectral characteristic information. (2) The feature band selection method’s prediction effect of soil moisture content is typically superior to that of full-spectrum data. (3) The random forest (RF) prediction model for soil moisture content with the highest accuracy was built by combining the genetic algorithm (GA) with the FD preprocessed spectra. The results may provide a new understanding on how to use VIS-NIR to measure soil moisture content.

Non-Destructive Assessment of Stone Heritage Weathering Types Based on Machine Learning Method Using Hyperspectral Data

Abstract. Stone cultural heritage is exposed to various environments, resulting in a diverse range of weathering types. The identification of these weathering types is vital for targeted conservation efforts. In this paper, a weathering type classification method based on hyperspectral imaging technology is proposed. Firstly, fresh sandstones are collected from Yungang Grottoes to carry out the simulated weathering experiments, including freeze-thaw cycles and wet-dry cycles with acid, alkali and salt solutions. Subsequently, the hyperspectral imaging system was used to collect the visible-near-infrared (VNIR) and short-wave infrared (SWIR) images of the sandstone samples with different weathering types and degrees. The surface spectral reflectance of sandstone samples with different weathering types were used as training data, with weathering types serving as the labels. Support vector machine (SVM), K-nearest neighbour (KNN), linear discriminant analysis (LDA) and random forest (RF) were used to establish weathering type classification models. The results show that the SVM model and LDA model based on both VNIR and SWIR spectra exhibit outstanding performance, with a best accuracy of 0.994. The framework proposed in this paper facilitates rapid and non-contact assessment of the weathering types of the superficial layers of stone cultural heritage, thereby supporting more targeted conservation work.

Spectroscopy of Magnesium Sulfate Double Salts and Their Implications for Mars Exploration

Magnesium sulfate has been widely detected on the surface of Mars. The occurrence of magnesium sulfate and mixed cationic sulfates preserves clues regarding the sedimentary environment, hydrological processes, and climate history of ancient Mars. In this study, seven magnesium sulfate double salts were synthesized in the laboratory using a high-temperature solid phase reaction or slow evaporation of aqueous solutions. The samples were analyzed using X-ray diffraction to confirm their phase and homogeneity. Subsequently, the Raman, mid-infrared spectra, and visible near-infrared spectra of these samples were collected and analyzed. Our results showed that the spectra of the analyzed magnesium sulfate double salts exhibited distinctive spectral features. These laboratory results may provide new insights for the identification of various magnesium sulfate double salts on Mars during the interpretation of in situ data collected by Scanning Habitable Environments with Raman and Luminescence for Organics and Chemicals (SHERLOC), SuperCam, and the ExoMars Raman Laser Spectrometer (RLS). In addition, the MIR and VNIR spectra features obtained in this study provide an improved reference and spectra library for decipherment of data sourced from the Thermal Emission Spectrometer (TES), Thermal Emission Imaging System (THEMIS), and Mars Mineralogical Spectrometer (MMS).

Non-destructive determination of water content in fruits using Vis-NIR spectroscopy

Visible near-infrared (Vis-NIR) spectroscopy is less accurate for detecting -OH molecules, therefore, the use of Vis-NIR spectroscopy is challenging for samples containing high water content, such as fruits. However, as Vis-NIR spectroscopy is a portable and economical instrument, it can be used in the field by small-scale farmers. This study aimed to evaluate Vis-NIR spectra to measure water content in fruits. Four fruits were used in this study, including dragon fruit, guava, sapodilla and banana (100 pieces each). All fruits were randomly divided into a calibration set (two-thirds of the samples) and a prediction set (one-third of the samples). Water content was predicted using partial least square regression (PLSR) analysis. The PLSR calibration model had a coefficient of determination (R²) of 0.29 for dragon fruit, 0.63 for guava, 0.62 for sapodilla and 0.80 for banana. The prediction model had an R² of 0.11 for dragon fruit, 0.63 for guava, 0.52 for sapodilla and 0.75 for banana. These results show that Vis-NIR spectroscopy has the potential to predict water content in relatively low water-content fruits, such as bananas.

Non-Destructive Evaluation of the Physiochemical Properties of Milk Drink Flavored with Date Syrup Utilizing VIS-NIR Spectroscopy and ANN Analysis.

A milk drink flavored with date syrup produced at a lab scale level was evaluated. The production process of date syrup involves a sequence of essential unit operations, commencing with the extraction, filtration, and concentration processes from two cultivars: Sukkary and Khlass. Date syrup was then mixed with cow's and camel's milk at four percentages to form a nutritious, natural, sweet, and energy-rich milk drink. The sensory, physical, and chemical characteristics of the milk drinks flavored with date syrup were examined. The objective of this work was to measure the physiochemical properties of date fruits and milk drinks flavored with date syrup, and then to evaluate the physical properties of milk drinks utilizing non-destructive visible-near-infrared spectra (VIS-NIR). The study assessed the characteristics of the milk drink enhanced with date syrup by employing VIS-NIR spectra and utilizing a partial least-square regression (PLSR) and artificial neural network (ANN) analysis. The VIS-NIR spectra proved to be highly effective in estimating the physiochemical attributes of the flavored milk drink. The ANN model outperformed the PLSR model in this context. RMSECV is considered a more reliable indicator of a model's future predictive performance compared to RMSEC, and the R2 value ranged between 0.946 and 0.989. Consequently, non-destructive VIS-NIR technology demonstrates significant promise for accurately predicting and contributing to the entire production process of the product's properties examined.

Utilizing VIS-NIR Technology to Generate a Quality Index (Qi) Model of Barhi Date Fruits at the Khalal Stage Stored in a Controlled Environment.

Saudi Arabia is a prominent producer of dates, producing 1.6 million tons annually. There is a need to evaluate the physical properties and quality of fruits non-destructively and then modeled and predict them throughout the storage period. The aim of the current study was to generate a quality index (Qi) and visible-near-infrared spectra (VIS-NIR) models non-destructively to predict properties of Barhi dates including objective and sensory evaluations. A total of 1000 Barhi fruits were sorted into three stages of maturation, ranging from 80 to 100% yellowish. The physical properties (hardness, color, TSS, pH, and sensory evaluations) of Barhi dates were measured and modeled with Qi based on VIS-NIR of fresh Barhi fruits and during storage in ambient (25 °C), cold (1 °C), and CA (1 °C with 5%:5% O2:CO2, 85% RH) conditions for up to 3 months. The prediction of Qi was non-destructively based on VIS-NIR utilizing PLSR and ANN data analysis. The results showed that the shelf-life of stored Barhi fruits were 20, 40, and 120 days corresponding to 25 °C, cold (1 °C), and CA, respectively. It was found that VIS-NIR spectroscopy was helpful in estimating the Qi of Barhi fruits for PLSR and ANN data analysis, respectively, in calibration with an R2 of 0.793 and 0.912 and RMSEC of 0.110 and 0.308 and cross-validation with an R2 of 0.783 and 0.912 and RMSEC of 0.298 and 0.308. The VIS-NIR spectrum has proven to be an effective method for the evaluation of the Qi of Barhi fruits and their physical properties throughout the supply chain in the handling, processing, transportation, storage and retail sectors. It was found that ANN is more suitable than PLSR analysis.

Proximal sensing approach for characterization of calcareous soils using multiblock data analysis

Application of visible-near infrared (VNIR) or mid-infrared (MIR) proximal sensing for prediction of soil attributes has proven successful in many cases and is currently extensively used. However, in some cases, predictions fail, especially for properties that do not have a strong spectral signature. Multiblock data analysis techniques are an extension of partial least squares regression (PLSR) that allows the incorporation of data obtained from different instruments into a single model. The techniques have not been used in soil characterization particularly in chemical and elemental soil analysis. Therefore, the aim of the study was to analyze the use of two multiblock algorithms, sequential orthogonalized partial least squares (SO-PLS) and response-oriented sequential alternation (ROSA), to improve the prediction of several soil attributes from VNIR and MIR spectra and their 2nd order derivatives in calcareous soils from Iran. A total of 130 soil samples were taken from 0 to 30 cm depth in Kamfiroz (Mulla Sadra Dam Watershed), Fars Province, Iran. The analyzed soil properties included soil organic matter (SOM), electrical conductivity (EC), carbonate calcium equivalent (CCE), clay and sand contents, and plant-available (DTPA-extractable) micronutrients such as manganese (Mn), iron (Fe), nickel (Ni), zinc (Zn), and copper (Cu). Multiblock models (SO-PLS and ROSA) were compared with single-block PLSR models obtained from VNIR, MIR and their 2nd order derivatives. The results indicated that SO-PLS improved the prediction performance for all studied properties compared to single-block PLSR models from VNIR, MIR or their 2nd order derivatives, and multiblock ROSA. The highest improvement was achieved for properties where single-block models were less accurate. However, the ROSA models were less accurate than single-block models. The best SO-PLS models were obtained for CCE (R2 = 0.96, RPIQ = 5.95, and NRMSE = 7.24%), followed by SOM (R2 = 0.91, RPIQ = 3.38, and NRMSE = 11.45%), log Fe (R2 = 0.89, RPIQ = 3.16, and NRMSE = 9.98%), Cu (R2 = 0.87, RPIQ = 3.21, and NRMSE = 15.51%), clay content (R2 = 0.85, RPIQ = 3.57, and NRMSE = 10.14%), Ni (R2 = 0.76, RPIQ = 2.60, and NRMSE = 28.25%), EC (R2 = 0.74, RPIQ = 1.63, and NRMSE = 20.94%), sand (R2 = 0.68, RPIQ = 1.82, and NRMSE = 27.58%), and Zn (R2 = 0.63, RPIQ = 1.65, and NRMSE = 18.14%). However, Mn was poorly predicted by all evaluated methods. The results confirmed the potential of the SO-PLS model to improve the prediction of soil properties using a combination of spectral information obtained with different instruments.

Predicting nickel concentration in soil using fractional-order derivative and visible-near-infrared spectroscopy indices.

Accurate monitoring and estimation of heavy metal concentrations is an important process in the prevention and treatment of soil pollution. However, the weak correlation between spectra and heavy metals in soil makes it difficult to use spectroscopy in predicting areas with a risk of heavy metal pollution. In this paper, a method for detection of Ni in soil in eastern China using the fractional-order derivative (FOD) and spectral indices was proposed. The visible-near-infrared (Vis-NIR) spectra were preprocessed using the FOD (range: 0 to 2, interval: 0.1) to solve the problems of baseline drift and overlapping peaks in the original spectra. The product index (PI), ratio index (RI), sum index (SI), difference index (DI), normalized difference index (NDI), and brightness index (BI) were applied and compared. The results showed that the spectral detail increased as the FOD increased, and the interference of the baseline drift and overlapping peaks was eliminated as the spectral reflectance decreased. Furthermore, the FOD extracted the spectral sensitivity information more effectively and improved the correlation between the Vis-NIR spectra and the Ni concentration, and the NDI had a maximum correlation coefficient (r) of 0.803 for order 1.9. The estimation model based on the NDI dataset constructed after FOD processing had the best performance, with a validation accuracy [Formula: see text] of 0.735, RMSE of 3.848, and RPD of 2.423. In addition, this method is easy to carry out and suitable for estimating other heavy metal elements in soil.

Prediction of tannin content and quality parameters in astringent persimmons from visible and near-infrared spectroscopy.

Tannin content and postharvest quality characteristics of persimmon fruit are often determined by the destructive analysis that consumes time, does not allow the acquisition of data from the same fruit continuously, and requires expensive high-performance equipment. This research was done to investigate the potential for non-destructive estimation of astringency and quality parameters in persimmon fruit based on visible/near-infrared (VNIR) spectra. VNIR spectra readings, the reference tannin content, and quality parameters were measured from fruits of "Cheongdo-Bansi" and "Daebong" persimmon cultivars at harvest and throughout the ripening/deastringency period. The spectra readings from half of the total fruit were utilized for the calibration set, while the other half readings were used for the prediction set. To develop models correlating the spectra data to the measured reference parameters data, the partial least square regression (PLSR) method was utilized. In the case of 'Daebong', the coefficients of determination (R2) between VNIR spectra and the actual measured values of TSS, firmness, simple sugars, and tannin content were (0.95, 0.94, 0.96, and 0.96) and (0.93, 0.89, 0.96, and 0.93), for the calibration and prediction sets, respectively. Similarly, the R2-values of (0.86, 0.93, 0.79, and 0.81) and (0.83, 0.91, 0.75, and 0.75) were recorded in 'Cheongdo-Bansi' for the calibration and prediction sets, respectively. Additionally, the acquired data were divided into two sets in a 3:1 ratio to develop predictive models and to validate the models in multiple regressions. PLSR models were developed in multiple regression to estimate the tannin content of both cultivars from firmness and simple sugars with R2-values of 0.83 and 0.79 in 'Cheongdo-Bansi' for the calibration and prediction sets, respectively, whereas, R2-values of 0.80 and 0.84 were recorded in 'Daebong' for the calibration and prediction sets, respectively. The overall findings of this study showed the possibility of using VNIR spectra for the prediction of postharvest quality and tannin contents from intact persimmon fruit with quick, chemical-free, and low-cost assessment methods. Also, the multiple regression using physicochemical parameters could fairly predict the tannin content in persimmon fruit though destructively but save time and low-cost.

Combining Vis-NIR and NIR Spectral Imaging Techniques with Data Fusion for Rapid and Nondestructive Multi-Quality Detection of Cherry Tomatoes.

Firmness, soluble solid content (SSC) and titratable acidity (TA) are characteristic substances for evaluating the quality of cherry tomatoes. In this paper, a hyper spectral imaging (HSI) system using visible/near-infrared (Vis-NIR) and near-infrared (NIR) was proposed to detect the key qualities of cherry tomatoes. The effects of individual spectral information and fused spectral information in the detection of different qualities were compared for firmness, SSC and TA of cherry tomatoes. Data layer fusion combined with multiple machine learning methods including principal component regression (PCR), partial least squares regression (PLSR), support vector regression (SVR) and back propagation neural network (BP) is used for model training. The results show that for firmness, SSC and TA, the determination coefficient R2 of the multi-quality prediction model established by Vis-NIR spectra is higher than that of NIR spectra. The R2 of the best model obtained by SSC and TA fusion band is greater than 0.9, and that of the best model obtained by the firmness fusion band is greater than 0.85. It is better to use the spectral bands after information fusion for nondestructive quality detection of cherry tomatoes. This study shows that hyperspectral imaging technology can be used for the nondestructive detection of multiple qualities of cherry tomatoes, and the method based on the fusion of two spectra has a better prediction effect for the rapid detection of multiple qualities of cherry tomatoes compared with a single spectrum. This study can provide certain technical support for the rapid nondestructive detection of multiple qualities in other melons and fruits.

Application of visible-near infrared spectroscopy in tandem with multivariate analysis for the rapid evaluation of matcha physicochemical indicators.

Consumer preference for matcha is heavily influenced by its physicochemical properties. The visible-near infrared (Vis-NIR) spectroscopy technology coupled with multivariate analysis was investigated for rapid and non-invasive evaluation of particle size and the ratio of tea polyphenols to free amino acids (P/F ratio) of matcha. The multivariate selection algorithms such as synergy interval (Si), variable combination population analysis (VCPA), competitive adaptive reweighted sampling (CARS), and interval combination population analysis (ICPA) were compared, and eventually, the variable selection strategy of ICPA and CARS hybridization was firstly proposed for selecting the characteristic wavelengths from Vis-NIR spectra to build partial least squares (PLS) models. Results indicated that the ICPA-CARS-PLS models achieved satisfactory performance for the evaluation of matcha particle size (Rp=0.9376) and P/F ratio (Rp=0.9283). Hence the rapid, effectual, and nondestructive online monitoring, Vis-NIR reflectance spectroscopy in tandem with chemometric models is significant for the industrial production of matcha.

Estimation of soil inorganic carbon with visible near-infrared spectroscopy coupling of variable selection and deep learning in arid region of China

Soil inorganic carbon (SIC) is the primary component of the soil carbon pool in arid and semiarid regions and strongly impacts the global carbon cycle, ecosystem services, and soil functions. The global climate change and intensify of human activities, could substantially change SIC, which highlights the importance of monitoring SIC. Rapid and accurate estimation of SIC concentration is critical for soil inorganic carbon pool monitoring. Currently, visible near-infrared (Vis-NIR) spectroscopy is a promising technique for estimating SIC via a rapid and cost-effective manner. Thus, in this study, we collected 315 topsoil samples from the Alar Reclamation Area in South Xinjiang, China, and measured their Vis-NIR spectra and SIC content. Then, we used deep learning algorithms, including a one-dimensional convolutional neural network (1D-CNN), two-dimensional convolutional neural network (2D-CNN), long short-term memory network (LSTM), and deep belief network (DBN), combined with variable selection algorithms (particle swarm algorithm (PSO), interval random frog (IRF), competitive adaptive reweighting algorithm (CARS), ant colony algorithm (ACO), and iteratively retaining informative variables (IRIV) to estimate SIC. Results showed that all five variable selection algorithms could effectively extract the featured spectral information of SIC, and reduce the number of spectral variables by >97%, simplifying the model structure. The variable selection algorithm could markedly improve the SIC spectral estimation accuracy, and the corresponding estimation accuracy follows the order: IRF > IRIV > PSO > CARS > ACO. All four deep learning models have high prediction accuracy, and the modeling accuracy of each method follow the order: LSTM > 1D-CNN > 2D-CNN > DBN. The combined IRF and LSTM model achieved the highest estimation accuracy (R2 = 0.93, RMSE = 1.26 g kg−1 in the calibration dataset; R2 = 0.92, RMSE = 1.37 g kg−1 in the validation dataset). This study demonstrated that deep learning combined with variable selection algorithms can detect SIC content quickly and accurately.

Detecting different pesticide residues on Hami melon surface using hyperspectral imaging combined with 1D-CNN and information fusion.

Efficient, rapid, and non-destructive detection of pesticide residues in fruits and vegetables is essential for food safety. The visible/near infrared (VNIR) and short-wave infrared (SWIR) hyperspectral imaging (HSI) systems were used to detect different types of pesticide residues on the surface of Hami melon. Taking four pesticides commonly used in Hami melon as the object, the effectiveness of single-band spectral range and information fusion in the classification of different pesticides was compared. The results showed that the classification effect of pesticide residues was better by using the spectral range after information fusion. Then, a custom multi-branch one-dimensional convolutional neural network (1D-CNN) model with the attention mechanism was proposed and compared with the traditional machine learning classification model K-nearest neighbor (KNN) algorithm and random forest (RF). The traditional machine learning classification model accuracy of both models was over 80.00%. However, the classification results using the proposed 1D-CNN were more satisfactory. After the full spectrum data was fused, it was input into the 1D-CNN model, and its accuracy, precision, recall, and F1-score value were 94.00%, 94.06%, 94.00%, and 0.9396, respectively. This study showed that both VNIR and SWIR hyperspectral imaging combined with a classification model could non-destructively detect different pesticide residues on the surface of Hami melon. The classification result using the SWIR spectrum was better than that using the VNIR spectrum, and the classification result using the information fusion spectrum was better than that using SWIR. This study can provide a valuable reference for the non-destructive detection of pesticide residues on the surface of other large, thick-skinned fruits.

Visible to near-infrared reflectance and Raman spectra of evaporites from sulfate-chloride Mars analogue brines

While much attention has been given to the identification and characterization of single-phase salts on Mars, relatively little has been applied to mixed evaporative assemblages. Given the likely existence of these assemblages on Mars (e.g., basin deposits) and the lack of data on their spectral signatures, here we present an experimental study of multicomponent S and Cl-bearing Mars-relevant brines. We modeled, synthesized and evaporated brines in the laboratory under both martian and terrestrial (P, T, pCO2) environmental conditions, and characterized the resulting precipitates using Visible–Near Infrared (VNIR), Raman spectroscopy, XRD and SEM-EDS. We compared these results to mineral assemblages calculated using the FREZCHEM thermodynamic model. For mixed brines primarily containing Na+, K+, Mg2+, Ca2+, SO42− and Cl−, epsomite (MgSO4•7H2O) and bischofite (MgCl2•6H2O) overwhelm VNIR and Raman spectra, while anhydrous crystalline salts and Na- and K-sulfates are unidentified. Mg-sulfates are identifiable in the VNIR and Raman even at low or no modeled mass abundance in an evaporative assemblage and are often the only clearly identifiable salt. These results imply that regions of Mg-sulfate identification on Mars may have only minor amounts of Mg-sulfate present, and significant amounts of halides or other sulfates may be undetectable. This may be due to a combination of late-stage Mg-sulfate precipitation and non-linear spectral mixing. Raman is more sensitive than VNIR to the identification of Ca-sulfate salts in these mixed assemblages. We predict that high abundances of mixed chloride and sulfate salts species will be identified as the Curiosity Rover continues to explore the Sulfate Unit of Gale Crater, and note that the Perseverance rover offers the first opportunity to identify such mixed assemblages in Jezero Crater with this combination of techniques.