Search Results (61)

To address the challenge of nondestructively identifying watercore disease in apples during growth and maturation, a portable device was developed for real-time grading of apple watercore using visible/near-infrared (Vis/NIR) spectroscopy combined with a one-dimensional quadratic convolutional neural network (1DQCNN). The instrument enables rapid, nondestructive, and accurate detection of apple watercore grades. The AI-OX2000-13 micro-spectrometer is used as the core data acquisition unit, and an ARM processing system is built with the STM32F103VET6 as the main control chip. A 4G wireless communication module enables efficient and stable data transmission between the processor and computer, meeting the real-time detection needs of apple watercore content in orchard environments. To improve the scientific and accurate classification of watercore grades, this paper combines the BiSeNet and RIFE algorithms to construct a 3D model of apple watercore, allowing quantification of the degree of watercore and classification into four levels. Based on this, quadratic convolution operations are incorporated into a one-dimensional convolutional neural network (1DCNN), leading to the development of the 1D quadratic convolutional neural network (1DQCNN) model for watercore grade classification. Experimental results indicate that the model achieves a classification accuracy of 98.05%, outperforming traditional methods and conventional CNN models. The designed portable instrument demonstrates excellent accuracy and practicality in real-world applications. Full article

Computational imaging spectrometers using broad-bandpass filter arrays with distinct transmission functions are promising implementations of miniaturization. The number of filters is limited by the practical factors. Compressed sensing is used to model the system as linear underdetermined equations for hyperspectral imaging. This paper proposes the following method: parallel dictionary reconstruction and fusion for spectral recovery in computational imaging spectrometers. Orthogonal systems are the dictionary candidates for reconstruction. According to observation of ground objects, the dictionaries are selected from the candidates using the criterion of incoherence. Parallel computations are performed with the selected dictionaries, and spectral recovery is achieved by fusion of the computational results. The method is verified by simulating visible-NIR spectral recovery of typical ground objects. The proposed method has a mean square recovery error of ≤1.73 × 10⁻⁴ and recovery accuracy of ≥0.98 and is both more universal and more stable than those of traditional sparse representation methods. Full article

The quality of wine largely depends on the quality of wine grapes, which is determined by their chemical composition. Therefore, measuring parameters related to grape ripeness, such as soluble solids content (SSC), is crucial for harvesting high-quality grapes. Visible–Near-Infrared (Vis/NIR) spectroscopy enables effective, non-destructive detection of SSC in grapes. However, commercial Vis/NIR spectrometers are often expensive, bulky, and power-consuming, making them unsuitable for on-site applications. This article integrated the AS7265X sensor to develop a low-cost handheld IoT multispectral detection device, which can collect 18 variables in the wavelength range of 410–940 nm. The data can be sent in real time to the cloud configuration, where it can be backed up and visualized. After simultaneously removing outliers detected by both Monte Carlo (MC) and principal component analysis (PCA) methods from the raw spectra, the SSC prediction model was established, resulting in an ${\mathrm{R}}_V^2$ of 0.697. Eight preprocessing methods were compared, among which moving average smoothing (MAS) and Savitzky–Golay smoothing (SGS) improved the ${\mathrm{R}}_V^2$ to 0.756 and 0.766, respectively. Subsequently, feature wavelengths were selected using UVE and SPA, reducing the number of variables from 18 to 5 and 6, respectively, further increasing the ${\mathrm{R}}_V^2$ to 0.809 and 0.795. The results indicate that spectral data optimization methods are effective and essential for improving the performance of SSC prediction models. The IoT Vis/NIR Spectroscopic System proposed in this study offers a miniaturized, low-cost, and practical solution for SSC detection in wine grapes. Full article

The impact of stratospheric aerosols on Earth’s climate, particularly through atmospheric heating and ozone depletion, remains a critical area of atmospheric research. While satellite data provide valuable insights, independent validation methods are necessary for ensuring accuracy. Twilight near-infrared (NIR) radiometry offers a promising approach for investigating aerosol properties, such as optical depth and layer height, at high altitudes. This study aims to evaluate the effectiveness of twilight radiometry in corroborating satellite data and assessing aerosol characteristics. Two methods based on twilight radiometry—the color ratio and the derivative method—are employed to derive the aerosol layer height and optical depth. Radiances at 450, 550, 762, 775, and 1050 nm wavelengths are analyzed at varying solar zenith angles, using zenith viewing geometry for consistency. Comparisons of aerosol optical depths (AODs) between Research Pandora (ResPan) and AErosol RObotic NETwork (AERONET) data (R = 0.99) and between ResPan and Modern-Era Retrospective analysis for Research and Applications (MERRA-2) data (R = 0.86) demonstrate a strong correlation. Twilight ResPan data are also used to estimate the aerosol layer height, with results in good agreement with SAGE and lidar measurements, particularly following the Hunga Tonga eruption in Lauder, New Zealand. The simulation database, created using the libRadtran DISORT and Monte Carlo packages for daylight and twilight calculations, is capable of detecting AODs as low as 10⁻³ using the derivative method. This work highlights the potential of twilight radiometry as a simple, cost-effective tool for atmospheric research and satellite data validation, offering valuable insights into aerosol dynamics at stratospheric altitudes. Full article

The main objective of this study was to evaluate the possibilities of visible-near-infrared spectroscopy for investigating water and nitrogen stress in tomato plants. Two varieties of tomato plants (Red Bounty and Manusa) were grown in a greenhouse. Plants were divided into three groups: control, reduced nitrogen fertilization, and reduced watering. Spectral measurements of tomato leaves were made on-site. A USB4000 spectrometer for 450–1100 nm and a handheld AlbaNIR for the 900–1650 nm region were used for the spectra acquisition. Twenty-four vegetative indices were calculated using the reflectance characteristics of plants. Soft Independent Modeling of Class Analogy (SIMCA) models were developed for classification. Additionally, aquagrams were calculated. Results show differences between the spectra of leaves from control and stressed plants for both tomato varieties. Aquagrams clearly show the differences in water structures in the three groups of plants. The performance of developed SIMCA models for discriminating plants according to growing conditions was very high. The total accuracy was between 86.89% and 97.09%. Several vegetation indices successfully differentiate control and stressed plants for both tomato varieties. The results show successful differentiation of the control and stressed tomato plants based on spectral characteristics of the plants’ leaves in the visible and near-infrared region. Full article

Controlling forage quality and grazing are crucial for sustainable livestock production, health, productivity, and animal performance. However, the limited availability of reliable handheld sensors for timely pasture quality prediction hinders farmers’ ability to make informed decisions. This study investigates the in-field dynamics of Mombasa grass (Megathyrsus maximus) forage biomass production and quality using optical techniques such as visible imaging and near-infrared (VIS-NIR) hyperspectral proximal sensing combined with machine learning models enhanced by covariance-based error reduction strategies. Data collection was conducted using a cellphone camera and a handheld VIS-NIR spectrometer. Feature extraction to build the dataset involved image segmentation, performed using the Mahalanobis distance algorithm, as well as spectral processing to calculate multiple vegetation indices. Machine learning models, including linear regression, LASSO, Ridge, ElasticNet, k-nearest neighbors, and decision tree algorithms, were employed for predictive analysis, achieving high accuracy with R² values ranging from 0.938 to 0.998 in predicting biomass and quality traits. A strategy to achieve high performance was implemented by using four spectral captures and computing the reflectance covariance at NIR wavelengths, accounting for the three-dimensional characteristics of the forage. These findings are expected to advance the development of AI-based tools and handheld sensors particularly suited for silvopastoral systems. Full article

Visible near-infrared (Vis-NIR) spectroscopy is widely used for rapid soil element detection, but calibration models are often limited by instrument-specific constraints, including varying laboratory conditions and sensor configurations. To address this, we propose a novel calibration transfer method that eliminates the conventional requirement of designating ‘master’ and ‘slave’ devices. Instead, spectral data from two spectrometers are fused to create a master spectrum, while independent spectral data serve as slave spectra. We developed an ensemble stacking model, incorporating partial least squares regression (PLSR), support vector regression (SVR), and ridge regression (Ridge) in the first layer, with BoostForest (BF) as the second layer, trained on the fused master spectrum. This model was further integrated with three calibration transfer methods: direct standardization (DS), piecewise direct standardization (PDS), and spectral space transfer (SST), to enable seamless application across slave spectra. Applied to soil total nitrogen (TN) detection, the method achieved an R²_P of 0.842, RMSEP of 0.017, and RPD of 2.544 on the first slave spectrometer, and an R²_P of 0.830, RMSEP of 0.018, and RPD of 2.452 on the second. These results demonstrate the method’s ability to simplify calibration processes while enhancing cross-instrument prediction accuracy, supporting robust and generalizable cross-instrument applications. Full article

Spaceborne instruments have an irreplaceable role in detecting fundamental vegetation features that link physical properties to ecological theory, but their success depends on our understanding of the complex dynamics that control plant spectral properties—a scale-dependent challenge. We explored differences between the warmer and cooler areas of tree canopies with a ground-based experimental layout consisting of a spectrometer and a thermal camera mounted on a portable crane that enabled synergies between thermal and spectral reflectance measurements at the fine scale. Thermal images were used to characterise the thermal status of different parts of a dense circular cluster of containerised trees, and their spectral reflectance was measured. The sensitivity of the method was found to be unaffected by complex interactions. A statistically significant difference in both reflectance in the visible (VIS), near-infrared (NIR), and shortwave infrared (SWIR) bands and absorption features related to the chlorophyll, carotenoid, and water absorption bands was found between the warmer and cooler parts of the canopy. These differences were reflected in the Photochemical Reflectance Index with values decreasing as surface temperature increases and were related to higher carotenoid content and lower Leaf Area Index (LAI) values of the warmer canopy areas. With the increasingly improving resolution of data from airborne and spaceborne visible, near-infrared, and shortwave infrared (VSWIR) imaging spectrometers and thermal infrared (TIR) instruments, the results of this study indicate the potential of synergies between thermal and spectral measurements for the purpose of more accurately assessing the complex biochemical and biophysical characteristics of vegetation canopies. Full article

Grassland degradation poses a significant challenge to achieving the Sustainable Development Goals (SDGs) on the Qinghai–Tibetan Plateau (QTP). Effective monitoring of grassland degradation is essential for ecological restoration. Hyperspectral technology offers efficient and accurate identification of degradation. However, the influence of observation time, data analysis methods and classification techniques on the accuracy of identifying alpine grasslands remains unclear. In this study, the spectral reflectance of degraded alpine meadow, alpine meadow, alpine shrub and Tibetan barley was measured from May to September 2023 using a ground spectrometer in the northeastern QTP. First-order derivatives (FDR) and continuum removal were applied to the spectra, and characteristic parameters and vegetation indices were calculated. Support vector machine (SVM), random forest (RF), artificial neural network (ANN) and decision tree (DT) were then used to compare the classification accuracy between different months, transformation methods and characteristic parameters. The results showed that the spectral reflectance peaked in July, with significant differences in the near infrared (NIR) bands between alpine meadow and degraded alpine meadow. Alpine shrub and Tibetan barley showed greater differences in reflectance compared to other vegetation types, especially in the NIR bands. Data transformations improved reflectance and absorption characteristics in the NIR and visible bands. Indices such as DVI, RVI and NDGI effectively differentiated vegetation types. Optimal accuracy for the identification of degraded alpine meadow in July was achieved using FDR transformations and ANN or SVM for classification. This study provides methodological insights for monitoring grassland degradation on the QTP. Full article

In soil science, the allocation of soil samples to their respective origins holds paramount significance, as it serves as a crucial investigative tool. In recent times, with the increasing use of proximal sensing and advancements in machine-learning techniques, new approaches have accompanied these developments, enhancing the effectiveness of soil utilization in soil science. This study investigates soil classification based on four parent materials. For this purpose, a total of 59 soil samples were collected from 12 profiles and the vicinity of each profile at a depth of 0–30 cm. Surface soil samples were analyzed for elemental concentrations using X-Ray fluorescence (XRF) and inductively coupled plasma–optical emission spectrometry (ICP-OES) and soil spectra using a visible near-infrared (Vis-NIR) spectrometer. Soil samples collected from soil profiles (12 soil samples) and surface (47 soil samples) were used to classify parent materials using machine learning-based algorithms such as Support Vector Machine (SVM), Ensemble Subspace k-Near Neighbor (ESKNN), and Ensemble Bagged Trees (EBTs). Additionally, as a validation of the classification techniques, the dataset was subjected to five-fold cross-validation and independent sample set splitting (80% calibration and 20% validation). Evaluation metrics such as accuracy, F score, and G mean were used to evaluate prediction performance. Depending on the dataset and algorithm used, the classification success rates varied between 70% and 100%. Overall, the ESKNN (99%) produced better results than other classification methods. Additionally, Relief algorithms were employed to identify key variables for each dataset (ICP-OES: CaO, Fe₂O₃, Al₂O₃, MgO, and MnO; XRF: SiO₂, CaO, Fe₂O₃, Al₂O, and MnO; Vis-NIR: 567, 571, 572, 573, and 574 nm). Subsequent soil reclassification using these reduced variables revealed reduced accuracies using Vis-NIR data, with ESKNN still yielding the best results. Full article

In planetary science, visible (Vis) and near-infrared (NIR) reflectance spectra allow deciphering the chemical/mineralogical composition of celestial bodies’ surfaces by comparison between remotely acquired data and laboratory references. This paper presents the design of an automated test rig named Exoland Simulator equipped with two reflectance spectrometers covering the 0.38–2.2 µm range. It is designed to collect data of natural/synthetic rocks and minerals prepared in the laboratory that simulate the composition of planetary surfaces. The structure of the test rig is conceived as a Cartesian robot to automatize the acquisition. The test rig is also tested by simulating some project trajectories, and results are presented in terms of its ability to reproduce the programmed trajectories. Furthermore, preliminary spectral data are shown to demonstrate how the soil analogs’ spectra could allow an accurate remote identification of materials, enabling the creation of libraries to study the effect of multiple chemical–physical component variations on individual spectral bands. Despite the primary scope of Exoland, it can be advantageously used also for tribological purposes, to correlate the wear behavior of soils and materials with their composition by also analyzing the wear scars. Full article

Globally, rice is one of the most important staple food crops. The most significant metric for evaluating the rice growth and productivity is the Leaf Area Index (LAI), which can be effectively monitored using remote sensing data. Hyperspectral remote sensing provides contiguous bands at narrow wavelengths for mapping LAI at various rice phenological stages, and it is functionally related to canopy spectral reflectance. Hyperspectral signatures for different phases of rice crop growth was recorded using Airborne Visible Near-Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) along with corresponding ground based observations. Ground-based hyperspectral canopy spectral reflectance measurements were recorded with FieldSpec 3 Hi-Res spectroradiometer (ASD Inc., Forsyth County, GA, USA; spectral range: 350–2500 nm) and LAI data from 132 farmer’s fields in Southern India. Among 29 hyperspectral vegetation indices tested, 8 were found promising for mapping rice LAI at various phenological stages. Among all the growth stages, the elongation stage was the most accurately estimated using vegetation indices that exhibited a significant correlation with the airborne hyperspectral reflectance. The validation of hyperspectral vegetation indices revealed that the best fit model for estimating rice LAI was mND₇₀₅ (red-edge, blue, and NIR bands) at seedling and elongation, SAVI (red and NIR bands) at tillering and WDRVI (red and NIR bands) at booting stage. Full article

Visible-near infrared (Vis-NIR) and mid-infrared (MIR) spectroscopy are increasingly being used for the fast determination of soil properties. The aim of this study was (i) to test the use of MIR spectra (Agilent 4300 FTIR Handheld spectrometer) for the prediction of soil properties and (ii) to compare the prediction performances of MIR spectra and Vis-NIR (ASD FieldSpecPro) spectra; the Vis-NIR data were adopted from a previous study. Both the MIR and Vis-NIR spectra were coupled with partial least squares regression, different pre-processing techniques, and the same 114 soil samples, collected from the agricultural land located between boreal forests and semi-arid steppe belts (Kastanozems). The prediction accuracy (R² = 0.70–0.99) of both techniques was similar for most of the soil properties assessed. However, (i) the MIR spectra were superior for estimating CaCO₃, pH, SOC, sand, Ca, Mg, Cd, Fe, Mn, and Pb. (ii) The Vis-NIR spectra provided better results for silt, clay, and K, and (iii) the hygroscopic water content, Cu, P, and Zn were poorly predicted by both methods. The importance of the applied pre-processing techniques was evident, and among others, the first derivative spectra produced more reliable predictions for 11 of the 17 soil properties analyzed. The spectrally active CaCO₃ had a dominant contribution in the MIR predictions of spectrally inactive soil properties, followed by SOC and Fe, whereas particle sizes and hygroscopic water content appeared as confounding factors. The estimation of spectrally inactive soil properties was carried out by considering their secondary correlation with carbonates, clay minerals, and organic matter. The soil information covered by the MIR spectra was more meaningful than that covered by the Vis-NIR spectra, while both displayed similar capturing mechanisms. Both the MIR and Vis-NIR spectra seized the same soil information, which may appear as a limiting factor for combining both spectral ranges. The interpretation of MIR spectra allowed us to differentiate non-carbonated and carbonated samples corresponding to carbonate leaching and accumulation zones associated with topography and land use. The prediction capability of the MIR spectra and the content of nutrient elements was highly related to soil-forming factors in the study area, which highlights the importance of local (site-specific) prediction models. Full article

Grape quality and ripeness play a crucial role in producing exceptional wines with high-value characteristics, which requires an effective assessment of grape ripeness. The primary purpose of this research is to explore the possible application of visible–near-infrared spectral (Vis-NIR) technology for classifying the maturity stages of wine grapes based on quality indicators. The reflection spectra of Cabernet Sauvignon grapes were recorded using a spectrometer in the spectral range of 400 nm to 1029 nm. After measuring the soluble solids content (SSC), total acids (TA), total phenols (TP), and tannins (TN), the grape samples were categorized into five maturity stages using a spectral clustering method. A traditional supervised classification method, a support vector machine (SVM), and two deep learning techniques, namely stacked autoencoders (SAE) and one-dimensional convolutional neural networks (1D-CNN), were employed to construct a discriminant model and investigate the association linking grape maturity stages and the spectral responses. The spectral data went through three commonly used preprocessing methods, and feature wavelengths were extracted using a competitive adaptive reweighting algorithm (CARS). The spectral data model preprocessed via multiplicative scattering correction (MSC) outperformed the other two preprocessing methods. After preprocessing, a comparison was made between the discriminant models established with full and effective spectral data. It was observed that the SAE model, utilizing the feature spectrum, demonstrated superior overall performance. The classification accuracies of the calibration and prediction sets were 100% and 94%, respectively. This study showcased the dependability of combining Vis-NIR spectroscopy with deep learning methods for rapidly and accurately distinguishing the ripeness stage of grapes. It has significant implications for future applications in wine production and the development of optoelectronic instruments tailored to the specific needs of the winemaking industry. Full article

Organic leafy vegetables face challenges related to potential substitution with non-organic products and vulnerability to dehydration and deterioration. To address these concerns, visible and near-infrared spectroscopy (VIS-NIR) combined with linear discriminant analysis (LDA) was employed in this study to rapidly distinguish between organic and non-organic leafy vegetables. The organic category includes organic water spinach (Ipomoea aquatica Forsskal), amaranth (Amaranthus tricolor L.), lettuce (Lactuca sativa var. ramosa Hort.), and pakchoi (Brassica rapa var. chinensis (Linnaeus) Kitamura), while the non-organic category consists of their four non-organic counterparts. Binary classification was performed on the reflectance spectra of these vegetables’ leaves and stems, respectively. Given the broad range of the VIS-NIR spectrum, stability selection (SS), random forest (RF), and analysis of variance (ANOVA) were used to evaluate the importance of the wavelengths selected by genetic algorithm (GA). According to the GA-selected wavelengths and their SS-evaluated values and locations, the significant bands for leaf spectra classification were identified as 550–910 nm and 1380–1500 nm, while 750–900 nm and 1700–1820 nm were important for stem spectra classification. Using these selected bands in the LDA classification, classification accuracies of over 95% were achieved, showcasing the effectiveness of utilizing the proposed method to rapidly identify organic leafy vegetables and the feasibility and potential of using a cost-effective spectrometer that only contains necessary bands for authenticating. Full article