Visible Near-infrared Data Research Articles

Wheat grain classification using hyperspectral imaging: Concatenating Vis-NIR and SWIR Data for single and bulk grains

Wheat variety identification is an essential component of the official inspection of wheat grains to determine their quality and trade value. Traditionally, wheat class identification requires deep knowledge about the appearance of plants and kernels, their history and distribution. Therefore, there is an urgent need for an automatic technology to standardize the nomenclature of wheat varieties to enable both growers and producers to identify their grains practically. The present study investigated the feasibility of Visible-Near Infrared (Vis-NIR) and Short-Wave Infrared (SWIR) spectral imaging to identify wheat classes. Both sides of the wheat kernel as single kernel measurements and bulk grains were used to acquire hyperspectral data and vertical and horizontal data concatenation was implemented to explore performance differences. In addition, the classification of bulk kernels from single kernel data was investigated. Spectral data was pre-treated by standard normal variate (SNV), Savitzky-Golay first (SG-1) and second derivatives (SG-2) and linear discriminant analysis (LDA), support vector machine (SVM) and artificial neural network (ANN) were applied as the classification algorithms. Furthermore, feature selection was utilised using the minimum redundancy maximum relevance (mRMR) algorithm to investigate the performance difference between data concatenation and feature selection. The results showed that ventral (up) side data showed better classification performances than reverse (down) side data, while Vis-NIR data achieved higher classification accuracies than SWIR data. However, the best classification performance for single kernels was obtained by LDA-SNV using up and down data in the Vis-NIR and SWIR regions vertically and horizontally concatenated with an accuracy of 93.72% for 10-fold cross-validation and 94.93% for test sets. Models based on a hundred features did not achieve the accuracy of models based on concatenated data. Moreover, classification performances of bulk samples were higher than single kernels, which achieved 100% accuracy for both cross-validation and test sets. The study demonstrates that spectral imaging has a high potential to identify wheat classes non-destructively.

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.

Leveraging visible-near-infrared spectroscopy and machine learning to detect nickel contamination in soil: Addressing class imbalances for environmental management

Excessive concentrations of Ni in soil have many severe effects, negatively affecting human health and leading to disease, while also posing a threat to animals and plants. Although the dangers of high Ni concentrations have been widely recognized, rapid and large-scale tools for the identification of Ni contamination are still lacking. Visible-near-infrared (Vis-NIR) spectroscopy has been employed to rapidly identify Ni contamination; however, previous studies suffer from issues inherent to small datasets and the tendency to negate data imbalances. To address these issues, a large dataset comprising 18,675 soil samples was used to predict soil Ni contamination by combining Vis-NIR data with machine learning (ML). The data imbalance inherent to previous studies was addressed using two data sampling methods. To build a robust classification model for Ni contamination, four spectral preprocessing methods and four ML algorithms were compared. The optimal extreme gradient boosting model achieved recall, accuracy, area under the curve, and geometric mean scores of 0.8203, 0.8806, 0.9268, and 0.8508, respectively. Model predictions across the United States identified specific regions with high possibility of Ni contamination. Overall, the model developed in this study offers an improved accuracy in predicting soil Ni contamination at the continental scale, and can be used to prioritize further testing and guide policymaking.

Rapid characterization of soil horizons for different soil series utilizing Vis-NIR spectral information

The visible-near infrared (Vis-NIR) reflectance technique is a powerful tool, particularly for obtaining faster information about soil texture, organic matter, and calcium carbonate content. However, there is limited research on the characterization of soil horizons using Vis-NIR data in profiles of different soil series. This study investigated the relationship between soil properties and spectral reflectance (Vis-NIR) in eight soil profiles with varying genetic properties from Harran Plain, Türkiye, focusing on variations within profiles (A, B, and C horizons) and across different soil series. A total of 36 soil samples were collected from the A, B, and C horizons, and spectral reflectance was measured along with calcium carbonate, organic matter, and particle size distribution. High variability was observed in calcium carbonate (11.58–52.50%) and organic matter content (0.60–3.71%), reflecting complex soil composition influenced by parent material and land management. Distinct reflectance patterns were observed within profiles, reflecting variations in soil composition. Ap horizons with higher organic matter content often exhibited lower reflectance (visible region). Clay content influenced NIR reflectance, with higher absorption in clay-rich profiles. The Kaynakli series (Fine-loamy, mixed, mesic Typic Calcixerepts) showed differentiation in reflectance between A and B horizons after 700 nm due to horizon formation and clay/carbonate accumulation. Increasing calcium carbonate content in Ck horizons led to higher reflectance compared to other layers. Confirmed that Vis-NIR reflectance could explain a significant portion of the variance in soil properties (A: 87.7%, B: 88.3%, and C: 90.6%). PCA results supported the notion that spectral signatures captured by Vis-NIR reflectance measurements are indicative of inherent differences between A, B, and C horizons. This study contributes to the growing body of knowledge on the application of Vis-NIR spectroscopy for soil assessment and monitoring. However, future research should focus on understanding spectral reflectance variations under diverse soil and environmental conditions.

Machine Learning-Based Classification of Soil Parent Materials Using Elemental Concentration and Vis-NIR Data.

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.

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

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

Rapid determination of starch and alcohol contents in fermented grains by hyperspectral imaging combined with data fusion techniques.

Starch and alcohol serve as pivotal indicators in assessing the quality of lees fermentation. In this paper, two hyperspectral imaging (HSI) techniques (visible-near-infrared (Vis-NIR) and NIR) were utilized to acquire separate HSI data, which were then fused and analyzed toforecast the starch and alcohol contents during the fermentation of lees. Five preprocessing methods were first used to preprocess the Vis-NIR, NIR, and the fused Vis-NIR and NIR data, after which partial least squares regression models were established to determine the best preprocessing method. Following, competitive adaptive reweighted sampling, successive projection algorithm, and principal component analysis algorithms were used to extract the characteristic wavelengths to accurately predict the starch and alcohol levels. Finally, support vector machine (SVM)-AdaBoost and XGBoost models were built based on the low-level fusion (LLF) and intermediate-level fusion (ILF) of single Vis-NIR and NIR as well as the fused data. The results showed that the SVM-AdaBoost model built using the LLF data afterpreprocessing by standard normalized variable was most accurate for predicting the starch content, with an of 0.9976 and a root mean square error of prediction (RMSEP) of 0.0992. The XGBoost model built using ILF data was most accurate for predicting the alcohol content, with an of 0.9969 and an RMSEP of 0.0605. In conclusion, the analysis of fused data from distinct HSI technologies facilitates rapid and precise determination of the starch and alcohol contents in fermented grains.

Optimal soil organic matter mapping using an ensemble model incorporating moderate resolution imaging spectroradiometer, portable X-ray fluorescence, and visible near-infrared data

Digital soil mapping of soil organic matter (SOM) is necessary because of its importance for carbon sequestration, soil health, and food security. However, large-scale digital soil mapping of SOM remains a challenge to improve accuracy and provide more local information. To address this knowledge gap, a strategy that incorporatesremoteandproximalsensingdataintoanensemblemodelforthe digital soil mapping is proposed. In this study, moderate resolution imaging spectroradiometer, portable X-ray fluorescence, and visible near-infrared spectroscopy data from 402 soil samples were used to map the SOM at a resolution of 90 m, model the SOM with random forest, cubist, and ensemble models, and evaluate its environmental factors in the northeastern and northern Chinese plains, a typical agricultural plain (approximately 66,000,000 ha). The digital maps of the SOM were derived along with their uncertainties. The results show that the visible near-infrared and portable X-ray fluorescence data play an important role in the SOM distribution. Inclusion of these data in the model, improved the R2p by 6.25–35.42 %, and reduced the root mean square error of the prediction by 0.30–1.54 g kg−1. The ensemble model, which included remote and proximal sensing variables, outperformed the results of previous studies with a root mean square error of 6.68 g kg−1 and provided more detailed information. Thus, this study confirmed the effectivenessoftheproposedstrategy. The SOM product obtained by this strategy was able to accurately control soil management, and the structural equation model showed that human activities exerted a direct influence on SOM comparable to the overall effect of natural factors on SOM. The contribution of straw mulching to human activities was great with path coefficient >0.50. This suggests that land management, especially straw mulching, should be improved in this area. In summary, this study proposed a novel strategy for accurately and efficiently obtaining SOM products for agricultural decision-making, terrestrial carbon cycling, and carbon stock estimation. Future advancements will focus on more accurate and detailed global SOM maps or carbon storage by integrating multiple models with remote sensing data and proximal sensing data from available soil spectral libraries.

Predicting the dietary fiber content of fresh-cut bamboo shoots using a visible and near-infrared hyperspectral technique

The dietary fiber content in fresh-cut bamboo shoots is considered crucial for the quality of processed bamboo shoots products. This study aimed to explore the potential of applying two different hyperspectral techniques, namely visible near infrared (Vis-NIR) spectroscopy and near infrared (NIR) in the quick and non-destructive prediction of the dietary fiber content of fresh-cut bamboo shoots. The Vis-NIR and NIR hyperspectral data were collected to establish partial least square regression (PLSR) and principal component regression (PCR) calibration model for the average spectrum of fresh-cut bamboo shoots and their corresponding dietary fiber content. Subsequently, data fusion analysis, various pre-processing methods, and principal component analysis (PCA) were used to optimize the model. The results indicated that superior models were obtained based on low-level fusion data when compared with the corresponding methods based on single spectral data. The optimal SNV-PCA-PLSR model achieved a good performance with coefficient of determination of prediction (R2p) of 0.902, and root mean square errors of prediction (RMSEP) of 0.135. Therefore, hyperspectral technique combined with data fusion analysis can be a promising approach for non-invasive quality supervision of bamboo shoots products in varied processing states.

Proximal sensor data fusion for tropical soil property prediction: Soil fertility properties

Proximal sensors have proven capable of predicting multiple soil properties under different conditions. However, doubts remain about which sensor is preferable for delivering optimal prediction models and which preprocessing methods produce the most accurate results. Portable X-ray fluorescence (pXRF) spectrometry and visible near-infrared (Vis-NIR) diffuse reflectance spectroscopy have been widely used, while the NixProTM color sensor has been explored more recently. This study evaluated the use of pXRF, Vis-NIR, and NixProTM data to predict soil organic matter content (SOM), pH, base saturation (BS), the sum of bases (SB), cation exchange capacity (CEC) at pH = 7 and effective CEC (eCEC), via each sensor in isolation, and via combined sensors data. Moreover, factors interfering in the prediction models' accuracy (data preprocessing methods, soil horizon, soil class, parent material) were used as auxiliary variables. 604 soil samples were collected in Brazil, encompassing ten soil orders and 19 parent materials. Numerical and categorical prediction models (7,980) were created for six soil properties using a random forest algorithm, totaling 7980 models, delivering almost 24,000 results., Coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and residual prediction deviation (RPD) were used for validation of numerical predictions., Overall accuracy and kappa coefficient were calcualted for categorical predictions. Although the combination of sensors provided most of the best predictions, pXRF in isolation achieved accuracies close to the three sensors combined. NixProTM offered superior contributions to SOM and CEC predictions, but pXRF and Vis-NIR were responsible for the best results of most studied variables. On average, by adding pXRF to Vis-NIR data, predictive accuracy improved 32%; while adding Vis-NIR to pXRF data increased accuracy by ca. 6%. Soil-order-specific models improved predictions for Ultisols compared to general models (without soil order distinction), reaching R2 > 0.90. Soil parent material and horizon did not improve models significantly. Categorical predictions improved the accuracy for some properties, reaching an overall accuracy of 100% and kappa index of 1.0 for pH in A horizons of Ultisols via pXRF + Vis-NIR data. Proximal sensor data with no auxiliary variables provided almost all the best results. The fusion of proximal sensors can provide better predictions, but pXRF alone can deliver satisfactory results in most cases for the six soil properties.

The Feasibility of Two Handheld Spectrometers for Meat Speciation Combined with Chemometric Methods and Its Application for Halal Certification.

Handheld visible-near-infrared (Vis-NIR) and near-infrared (NIR) spectroscopy can be cost-effective, rapid, non-destructive and transportable techniques for identifying meat species and may be valuable for enforcement authorities, retail and consumers. In this study, a handheld Vis-NIR (400–1000 nm) and a handheld NIR (900–1700 nm) spectrometer were applied to discriminate halal meat species from pork (halal certification), as well as speciation of intact and ground lamb, beef, chicken and pork (160 meat samples). Several types of class modeling multivariate approaches were applied. The presented one-class classification (OCC) approach, especially with the Vis-NIR sensor (95–100% correct classification rate), was found to be suitable for the application of halal from non-halal meat-species discrimination. In a discriminant approach, using the Vis-NIR data and support vector machine (SVM) classification, the four meat species tested could be classified with accuracies of 93.4% and 94.7% for ground and intact meat, respectively, while with partial least-squares discriminant analysis (PLS-DA), classification accuracies were 87.4% (ground) and 88.6% (intact). Using the NIR sensor, total accuracies of the SVM models were 88.2% and 81.5% for ground and intact meats, respectively, and PLS-DA classification accuracies were 88.3% (ground) and 80% (intact). We conclude that the Vis-NIR sensor was most successful in the halal certification (OCC approaches) and speciation (discriminant approaches) for both intact and ground meat using SVM.

Nondestructive estimation of three apple fruit properties at various ripening levels with optimal Vis-NIR spectral wavelength regression data

Nondestructive estimation of fruit properties during their ripening stages ensures the best value for producers and vendors. Among common quality measurement methods, spectroscopy is popular and enables physicochemical properties to be nondestructively estimated. The current study aims to nondestructively predict tissue firmness (kgf/cm), acidity (pH level) and starch content index (%) in apples (Malus M. pumila) samples (Fuji var.) at various ripening stages using visible/near infrared (Vis-NIR) spectral data in 400–1000 nm wavelength range. Results show that non-linear regression done by an artificial neural network-cultural algorithm (ANN-CA) was able to properly estimate the investigated fruit properties. Moreover, the performance of the proposed method was evaluated for Vis-NIR data based on optimal NIR wavelength values selected by a genetic optimization tool. Regression coefficients (R) in estimated acidity, tissue firmness, and starch content properties were R=0.930±0.014, R=0.851±0.014, and R=0.974±0.006, respectively, using only the three most effective wavelengths from the acquired spectra.

Resistance and resilience of grasslands to drought detected by SIF in inner Mongolia, China

Currently, stability of grassland ecosystem is facing serious challenges due to the occurrence of global warming and the increased frequency and intensity of extreme droughts. The stability of grassland ecosystem has two distinct components: ‘resistance’ and ‘resilience’. However, the evaluation of resistance and resilience mechanisms is hindered by the lack of tools for accurately monitoring the response of grasslands to drought across spatio-temporal scales. In this study, the resistance and resilience of grassland ecosystem are investigated by combining multi-source data, including space-borne solar-induced chlorophyll fluorescence (SIF), Gross Primary Productivity (GPP) estimated by flux towers, and MODIS visible near-infrared (VNIR) data. The characteristics of grassland ecosystem resistance and resilience to drought are obtained from the grasslands of Inner Mongolia, China, which suffered from a prolonged scarcity of rainfall in 2009. Space-borne SIF is found to be a beneficial tool for monitoring the seasonal dynamics of vegetation productivity compared to MODIS VNIR data. Space-borne SIF features a higher accuracy for monitoring the recovery time, resistance and resilience of grasslands to drought compared to MODIS VNIR data. Spatially, the resilience of Inner Mongolia grasslands to drought measured by SIF is greater than that measured by MODIS VNIR data, while the resistance of Inner Mongolia grasslands to drought measured by SIF is less than that measured by MODIS VNIR data. Moreover, areas with high resistance are located at the interlaced zone of grassland ecosystem and farmland or forest, where the resilience is low. These results demonstrate that space-borne SIF has great potential for monitoring the resistance and resilience of grasslands in response to drought over large regions.

Evaluating pixel-based vs. object-based image analysis approaches for lithological discrimination using VNIR data of WorldView-3

The object-based against pixel-based image analysis approaches were assessed for lithological mapping in a geologically complex terrain using Visible Near Infrared (VNIR) bands of WorldView-3 (WV-3) satellite imagery. The study area is Hormuz Island, southern Iran, a salt dome composed of dominant sedimentary and igneous rocks. When performing the object-based image analysis (OBIA) approach, the textural and spectral characteristics of lithological features were analyzed by the use of support vector machine (SVM) algorithm. However, in the pixel-based image analysis (PBIA), the spectra of lithological end-members, extracted from imagery, were used through the spectral angle mapper (SAM) method. Several test samples were used in a confusion matrix to assess the accuracy of classification methods quantitatively. Results showed that OBIA was capable of lithological mapping with an overall accuracy of 86.54% which was 19.33% greater than the accuracy of PBIA. OBIA also reduced the salt-and-pepper artifact pixels and produced a more realistic map with sharper lithological borders. This research showed limitations of pixel-based method due to relying merely on the spectral characteristics of rock types when applied to high-spatial-resolution VNIR bands of WorldView-3 imagery. It is concluded that the application of an object-based image analysis approach obtains a more accurate lithological classification when compared to a pixel-based image analysis algorithm.

Determining the Volcanic Eruption Style of Tephra Deposits From Infrared Spectroscopy

AbstractOrbital imagery and spectroscopy at Mars have identified a variety of deposits potentially consistent with volcanic tephra formed during explosive volcanic eruptions, and some of these deposits may have formed due to water‐ or ice‐magma interactions during phreatomagmatic eruptions. If this is the case, these deposits could serve as an additional record of past water on Mars. Previous work has demonstrated that phreatomagmatic tephra is characterized by much lower crystallinities than tephras from other types of eruptions. We hypothesize that crystallinity could be inferred remotely using spectroscopy; however, tephra spectral properties have not been directly linked to their mineralogy. Here, we use Mars analog tephra samples to investigate if eruption styles and the past presence of water during the eruption of possible volcanic deposits on Mars can be determined using orbital spectroscopy. Visible/near‐infrared (VNIR) reflectance and thermal infrared (TIR) emission spectra were collected of basaltic volcanic tephras sourced from a range of eruption styles and deposit types on Earth. Our research demonstrates that, TIR and VNIR data are both sufficient to detect increased glass abundances in volcanic deposits, potentially indicating volatile interactions during an eruption, and that glass‐poor tephras have distinct TIR properties that can be used to infer tephra type (e.g., ignimbrite vs. scoria). Combining VNIR and TIR orbital data for analysis based on our new laboratory spectral endmember library may allow a reevaluation of Martian volcanic and volatile histories using current and future planetary orbital and in situ spectral datasets.

Mineral Identification and Mapping by Synthesis of Hyperspectral VNIR/SWIR and Multispectral TIR Remotely Sensed Data With Different Classifiers

Hyperspectral data, which have fine continuous spectrum, have been recognized to be more suitable for the detailed identification and classification of land surface, especially for minerals. The combination of the hyperspectral visible/near-infrared (VNIR) and shortwave infrared (SWIR) data with the hyperspectral thermal infrared (TIR) data is proven to be an effective way. However, how those effects are and what are the effects of introduction of multispectral TIR data on the minerals identification and classification are not well studied. To fully evaluate those effects, this article tries to use both simulated data and real data to testify the practicability of introduction of multispectral TIR data for the accuracies of mineral identification and classification. Four classifiers, i.e., spectral angle mapping, spectral feature fitting, orthogonal subspace projection, and adaptive coherence/cosine estimator, are selected in the experiment. Compared with the results using hyperspectral data alone, the introducing of multispectral TIR data in identification and classification has improved accuracies for both the simulated and real data. The overall accuracies are improved about 4%–13% for the simulated data and about 1%–5% for the real data by using different classifiers. Those improvements prove that the spectral diagnosed characteristics in TIR region even for multispectral data help identify and classify minerals. Although the improvements for real data are not well obvious due to the low spatial resolution, the multispectral TIR data are still effective supplements for hyperspectral VNIR and SWIR data in mineral identification and classification.

Precise Sweetness Grading of Mangoes (Mangifera indica L.) Based on Random Forest Technique With Low-Cost Multispectral Sensors

Before being exported, mangoes generally undergo rigorous external and internal quality inspection processes in which near-infrared (NIR) spectral approaches are favorable for grading purposes. A successful NIR-based grading system depends largely on high-quality spectral sensors and the reliability of the classifier. Motivated by the high economic impact of Cat Hoa Loc mangoes (Mangifera indica L.), we demonstrated that the sweetness of that mangoes could be precisely graded based on a random forest (RF) classifier in a three-phase approach with a low-cost Visible-Near infrared (VIS-NIR) multispectral sensor chipset. This approach is so-called RPR because RF, Partial Least Squares regression, and RF were respectively applied to consecutively determine the significant VIS-NIR responses, the good features as input variables, and the reliable RF classifier via our formulated discriminant index (DI). The experimental results confirmed that higher classification accuracy was achieved by using the extracted latent features rather than the raw VIS-NIR data. The DI was effectively used as a reliability measure to select the optimal classifier among those of identical training and testing accuracies of 100% and 82.1%, respectively. Performance comparison between the optimal RF classifier with a Support Vector Machines classifier and a multinomial logistic regression showed that the developed RF classifier was superior in various performance indices. Therefore, it is promising to extend the proposed approach to more complicated fruit grading problems with sufficient VIS-NIR datasets that are acquired from low-cost multispectral sensors.

A robust visible near-infrared index for fire severity mapping in Arctic tundra ecosystems

Tundra fires are projected to increase with anthropogenic climate change, yet our ability to assess key wildfire metrics such as fire severity remains limited. The Normalized Burn Ratio (NBR) is the most commonly applied index for fire severity mapping. However, the computation of NBR depends on short-wave infrared (SWIR) data, which are not commonly available from historical and contemporary high-resolution (≤4 m) optical imagery. The increasing availability of visible near-infrared (VNIR) measurements from proximal to spaceborne sensors/platforms has the potential to advance our understanding of the spatiotemporal patterns of fire severity within tundra fires. Here we systematically assess the feasibility of using VNIR data for fire severity mapping in ten Alaskan tundra fires (cumulatively burned ~1700 km2). We compared the accuracy of 10 published VNIR-based fire indices using both uni-temporal (post-fire image) and bi-temporal (pre-fire and post-fire image difference) assessments against ground-based fire severity data (Composite Burn Index, CBI) at 109 tundra sites. The Global Environmental Monitoring Index (GEMI) had the highest correspondence with CBI (R2 = 0.77 uni-temporal; R2 = 0.85 bi-temporal), with similar performance to NBR (R2 = 0.77 uni-temporal; R2 = 0.83 bi-temporal). Tundra vegetation types affected NBR but not GEMI, as SWIR reflectance was influenced to a greater extent in shrub than graminoid tundra. We applied GEMI to contemporary high-resolution (i.e. Quickbird 2) and historical meso-resolution imagery (i.e. Landsat Multispectral Scanner) to demonstrate the capability of GEMI for resolving fine-scale patterns of fire severity and extending fire severity archives. Results suggest that GEMI accurately captured the heterogeneous patterns of tundra fire severity across fire seasons, ecoregions, and vegetation types.

Characterization of Iron in Lake Towuti sediment

Sediments collected from Lake Towuti, an ultramafic-hosted lake in Indonesia, preserve a visible alternating pattern of red and green sediments due to variations in clay mineral and Fe-oxide composition and abundance consistent with changes in iron oxidation state through time. Spectral, mineralogical, and chemical analyses on soils, river, and sediment samples from across the lake and its catchment were carried out to better understand the starting composition of these sediments and the processes that affected them before and after deposition. Despite high Fe abundances in all samples and abundant Fe oxides in lateritic source regions, mineralogical analyses (X-ray diffraction (XRD) and Mössbauer spectroscopy) of the modern lake sediment show almost no well-crystalline iron oxides. In addition, sequential Fe extractions suggest an increasing proportion of easily extractable, poorly crystalline (X-ray amorphous) material with burial depth. XRD, bulk chemistry, and visible-near infrared (VNIR) spectral reflectance measurements demonstrate that clay mineralogy and bulk chemistry can be inferred from VNIR data. These results provide evidence for variations in Fe mineralogy and crystallinity based on location in this source to sink system. Understanding how the mineralogy and chemistry of sediments within a ferruginous lake basin are affected by transport, chemical alteration, physical alteration, and deposition from source to sink on Earth, and the degree to which these trends and underlying processes can be inferred from chemical and spectral properties, may provide useful direction in assessing paleoenvironmental conditions in other terrestrial lakes as well as ancient lacustrine environments preserved in the stratigraphic record of Mars.

Spectral Imaging and Archival Data in Analysing Madonna of the Rabbit Paintings by Manet and Titian.

A concise insight into the outputs provided by the latest prototype of visible-near infrared (Vis-NIR) multispectral scanner (National Research Council-National Institute of Optics, CNR-INO, Italy) is presented. The analytical data acquired on an oil painting Madonna of the Rabbit by É. Manet are described. In this work, the Vis-NIR was complemented with X-ray fluorescence (XRF) mapping for the chemical and spatial characterization of several pigments. The spatially registered Vis-NIR data facilitated their processing by spectral correlation mapping (SCM) and artificial neural network (ANN) algorithm, respectively, for pigment mapping and improved visibility of pentimenti and of underdrawing style. The data provided several key elements for the comparison with a homonymous original work by Titian studied within the ARCHive LABoratory (ARCHLAB) transnational access project.