Spectral Data Collection Research Articles

Optimizing wheat crop performance: Genomic and phenomic insights into yield and days to maturity prediction using multi‐temporal UAV imagery

AbstractThis study assesses strategies for utilizing multispectral imaging data (from flowering to maturity) to predict late‐season traits in the Norwegian wheat breeding program, comparing them with genomic prediction (GP). In the phenomic prediction (PP) approach, spectral bands, their multispectral relationship matrix (M‐matrix), and vegetation indices (VIs) were considered. GP involved the genomic relationship matrix (G), extended to multi‐kernel predictors by incorporating environmental and genotype–environment interaction effects, complemented with multispectral reflectance data. Two different models including PLSR (partial least square regression) and Bayesian genomic best linear unbiased prediction regressor were applied. The phenological stage of spectral data collection impacted the trait prediction accuracy correlating with the relationship between multispectral data and measured traits. Higher correlations resulted in higher PP prediction accuracy. The results revealed that spectral bands and M‐matrix outperformed VIs by 10%–40% across different timepoints and all timepoints together for grain yield (GY) prediction. The single‐kernel GP model (G) outperformed PP by 28% (using Bayesian) and 29% (using PLSR). The integration of multi‐kernel GP models with spectral data improved GY prediction by up to 4%. In terms of days to maturity (DM) prediction, phenomic methods excelled, surpassing the single‐kernel GP (G: r = 0.63) model by 11% (Bayesian). In conclusion, this study underscores the effectiveness of phenomics prediction for traits like DM and its potential to enhance predictions for complex traits such as GY while highlighting the importance of correlation between measured traits and spectral data, kernel combinations, and model selection for prediction accuracy.

Near-infrared spectroscopy combined with support vector machine for the identification of Tartary buckwheat (Fagopyrum tataricum (L.) Gaertn) adulteration using wavelength selection algorithms

The frequent occurrence of adulterating Tartary buckwheat powder with crop flours in the market necessitates an urgent need for a simple analysis method to ensure the quality of Tartary buckwheat. This study employed near-infrared spectroscopy (NIRS) for the collection of spectral data from Tartary buckwheat samples adulterated with whole wheat, oat, soybean, barley, and sorghum flours. The competitive adaptive reweighted sampling (CARS) and successive projection algorithm (SPA) were deployed to identify informative wavelengths. By integrating support vector machine (SVM) and partial least squares discriminant analysis (PLS-DA), we constructed qualitative models to discern Tartary buckwheat adulteration. The PLS-DA model exhibited prediction accuracies between 89.78 % and 94.22 %, while the mean-centering (MC)-PLS-DA model showcased impressive predictive accuracy of 93.33 %. Notably, the feature-based Autoscales-CARS-CV-SVM model achieved more excellent identification accuracy. These findings exhibit the excellent potential of chemometrics as a powerful tool for detecting food product adulteration.

Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects

In recent times, astronomy has entered a new era with rapidly growing data sources and advanced observation techniques. The construction of powerful telescopes has enabled the collection of spectral data from millions of celestial objects. However, the increasing number and variety of data have made it challenging to categorize these celestial objects. This study employs machine learning methods to address the fundamental problem of classifying stars, galaxies, and quasars in astronomy. The dataset underwent detailed preprocessing to identify effective features for classification. KNIME Analytics Platform was used for data analysis and visualization, facilitating rapid and efficient data analysis through its drag-and-drop interface. Among the machine learning methods used in our study—Decision Trees, Random Forest, and Naive Bayes—the highest accuracy rate of 97.86% was achieved with the Random Forest model. Notably, despite its lower overall performance compared to other models, the Naive Bayes classifier exhibited superior performance in distinguishing the STAR class, which is one of the study's interesting findings. Future studies aim to enhance model accuracy by using larger and more diverse datasets and exploring different machine learning algorithms. Additionally, the impact of deep learning methods on classification performance will be investigated.

Research on Nondestructive Inspection of Fruits Based on Spectroscopy Techniques: Experimental Scenarios, ROI, Number of Samples, and Number of Features

Spectral technology is a scientific method used to study and analyze substances. In recent years, the role of spectral technology in the non-destructive testing (NDT) of fruits has become increasingly important, and it is expected that its application in the NDT of fruits will be promoted in the coming years. However, there are still challenges in terms of dataset collection methods. This article aims to enhance the effectiveness of spectral technology in NDT of citrus and other fruits and to apply this technology in orchard environments. Firstly, the principles of spectral imaging systems and chemometric methods in spectral analysis are summarized. In addition, while collecting fruit samples, selecting an experimental environment is crucial for the study of maturity classification and pest detection. Subsequently, this article elaborates on the methods for selecting regions of interest (ROIs) for fruits in this field, considering both quantitative and qualitative perspectives. Finally, the impact of sample size and feature size selection on the experimental process is discussed, and the advantages and limitations of the current research are analyzed. Therefore, future research should focus on addressing the challenges of spectroscopy techniques in the non-destructive inspection of citrus and other fruits to improve the accuracy and stability of the inspection process. At the same time, achieving the collection of spectral data of citrus samples in orchard environments, efficiently selecting regions of interest, scientifically selecting sample and feature quantities, and optimizing the entire dataset collection process are critical future research directions. Such efforts will help to improve the application efficiency of spectral technology in the fruit industry and provide broad opportunities for further research.

Passive high explosive neutron inspection (PHENIX): a new method to confirm the presence or absence of high explosives for nuclear treaty verification

Advanced instruments and methods need to be developed now to create a technical basis to support the negotiation of future nuclear arms control treaties. One new capability that is anticipated is the ability to confirm either the declared presence or declared absence of high explosive (HE) material in the presence of special nuclear material (SNM). Towards this goal, Passive HE Neutron Inspection (PHENIX) has been developed and demonstrated as a method for confirming the presence or absence of HE in the presence of plutonium. The method exploits the inherent presence of neutrons associated with the decay of plutonium as an internal probe source for performing prompt gamma-ray neutron activation analysis (PGNAA), searching for the presence of HE as revealed by the emission of characteristic gamma rays following neutron absorption in hydrogen and nitrogen which are building blocks of present-day, military-grade HE. Tests using stoichiometrically-correct hemishells of mock HE with plutonium show that a system can be expected to positively confirm the presence or absence of these signatures, supporting determination of HE presence or absence with Pu, in a few hours. To protect other potentially sensitive gamma-ray signatures from a treaty accountable item, an analog information barrier has been conceptualized and tested which physically prevents the collection of gamma-ray spectral data outside of user selected energy windows strategically chosen to view only narrow spectral regions corresponding to the hydrogen (2223.2 keV) and nitrogen (9807.2 keV, 10,318.2 keV, and 10,829.2 keV) PGNAA signatures.

Determination of soluble solids content of multiple varieties of tomatoes by full transmission visible-near infrared spectroscopy.

Soluble solids content (SSC) is a pivotal parameter for assessing tomato quality. Traditional measurement methods are both destructive and time-consuming. To enhance accuracy and efficiency in SSC assessment, this study employs full transmission visible and near-infrared (Vis-NIR) spectroscopy and multi-point spectral data collection techniques to quantitatively analyze SSC in two tomato varieties ('Provence' and 'Jingcai No.8' tomatoes). Preprocessing of the multi-point spectra is carried out using a weighted averaging approach, aimed at noise reduction, signal-to-noise ratio improvement, and overall data quality enhancement. Taking into account the potential influence of various detection orientations and preprocessing methods on model outcomes, we investigate the combination of partial least squares regression (PLSR) with two orientations (O1 and O2) and two preprocessing techniques (Savitzky-Golay smoothing (SG) and Standard Normal Variate transformation (SNV)) in the development of SSC prediction models. The model achieved the best results in the O2 orientation and SNV pretreatment as follows: 'Provence' tomato (Rp = 0.81, RMSEP = 0.69°Brix) and 'Jingcai No.8' tomatoes (Rp = 0.84, RMSEP = 0.64°Brix). To further optimize the model, characteristic wavelength selection is introduced through Least Angle Regression (LARS) with L1 and L2 regularization. Notably, when λ=0.004, LARS-L1 produces superior results ('Provence' tomato: Rp = 0.95, RMSEP = 0.35°Brix; 'Jingcai No.8' tomato: Rp = 0.96, RMSEP = 0.33°Brix). This study underscores the effectiveness of full transmission Vis-NIR spectroscopy in predicting SSC in different tomato varieties, offering a viable method for accurate and swift SSC assessment in tomatoes.

Raman spectroscopic measurements and imaging on sub-newton Berkovich and spherical imprints in fused silica

This paper lays out best practices for evaluating and optimizing a Raman spectroscopy setup to ensure the collection of reliable spectral data and/or Raman images on indented glasses. The Raman spectroscopic measurements and imaging were conducted on residual imprints created with Berkovich and spherical probes at forces in the sub-newton range in fused silica. The capability of a conventional optical instrument for mapping spectral variations in sub-newton imprints on glasses is evaluated by studying the influence of the optical configuration (choice of microscope objective) on the spatial resolution of the spectroscopy setup. The spatial resolution was quantitatively assessed in Z profile measurements and qualitatively evaluated by mapping changes in spectral features and correlated densification within the indented regions of fused silica specimens. The paper discusses the importance of appropriately matching the analysis volume of the Raman spectroscopic setup with the size of the indentation-induced densification zone by demonstrating the detrimental effects a mismatch may have on accurately capturing the magnitude of spectral changes and correlated densification.

Near infrared spectroscopy for cooking time classification of cassava genotypes.

Cooking time is a crucial determinant of culinary quality of cassava roots and incorporating it into the early stages of breeding selection is vital for breeders. This study aimed to assess the potential of near-infrared spectroscopy (NIRS) in classifying cassava genotypes based on their cooking times. Five cooking times (15, 20, 25, 30, and 40 minutes) were assessed and 888 genotypes evaluated over three crop seasons (2019/2020, 2020/2021, and 2021/2022). Fifteen roots from five plants per plot, featuring diameters ranging from 4 to 7 cm, were randomly chosen for cooking analysis and spectral data collection. Two root samples (15 slices each) per genotype were collected, with the first set aside for spectral data collection, processed, and placed in two petri dishes, while the second set was utilized for cooking assessment. Cooking data were classified into binary and multiclass variables (CT4C and CT6C). Two NIRs devices, the portable QualitySpec® Trek (QST) and the benchtop NIRFlex N-500 were used to collect spectral data. Classification of genotypes was carried out using the K-nearest neighbor algorithm (KNN) and partial least squares (PLS) models. The spectral data were split into a training set (80%) and an external validation set (20%). For binary variables, the classification accuracy for cassava cooking time was notably high ( ranging from 0.72 to 0.99). Regarding multiclass variables, accuracy remained consistent across classes, models, and NIR instruments (~0.63). However, the KNN model demonstrated slightly superior accuracy in classifying all cooking time classes, except for the CT4C variable (QST) in the NoCook and 25 min classes. Despite the increased complexity associated with binary classification, it remained more efficient, offering higher classification accuracy for samples and facilitating the selection of the most relevant time or variables, such as cooking time ≤ 30 minutes. The accuracy of the optimal scenario for classifying samples with a cooking time of 30 minutes reached = 0.86 and = 0.84, with a Kappa value of 0.53. Overall, the models exhibited a robust fit for all cooking times, showcasing the significant potential of NIRs as a high-throughput phenotyping tool for classifying cassava genotypes based on cooking time.

Can Raman Spectra of NMC Material Family be Detangled?

Raman spectroscopy is an advanced tool for investigating the structural and chemical properties of Li-ion battery materials. With the ability to probe the vibrational modes of crystals, it can provide valuable insights into the structural evolution and chemical reactions that occur during battery cycling. This technique has been used extensively to study electrode materials, solid electrolytes, and interfaces in Li-ion batteries, providing a deeper understanding of the mechanisms governing their performance and degradation. [1]Raman spectroscopy plays a crucial role in the characterization of LiNi1-x-yMnxCoyO2 (NMC) materials, which are widely used as positive electrodes. It can provide information on the phase transitions, crystal symmetry, and degradation that occur during battery cycling. [2] The Raman spectrum of LiMO2 is composed of peaks that correspond to the vibrational modes of the crystal lattice. The most prominent line in Raman spectrum of the R-3m space group symmetry should correspond to the A1g mode, which in case of LiMO2 crystal arises from the symmetric stretching vibration of the metal-oxygen (M-O) bonds in the octahedral coordination. The second predicted peak in the spectrum is Eg which involves the movement of oxygens in opposite directions across adjacent O-layers. [2] The interpretation of the NMC Raman spectra can be challenging due to several factors. One of the main difficulties is the complexity of its crystal structure, giving rise to a large number of vibrational modes in the spectrum. The presence of multiple metal-oxygen (M-O) bond types in the octahedral coordination can lead to overlapping Raman peaks, making it difficult to distinguish between the different modes. Another challenge is the presence of defects and disorder, which can lead to changes in the crystal symmetry and vibrational modes of the material, resulting in additional peaks or shifts in the Raman spectrum. Factors such as particle size, morphology, and orientation might also affect the Raman spectrum, as might the excitation wavelength and polarization of the incident light. To overcome these challenges, a combination of experimental and theoretical techniques, such as X-ray diffraction and density functional theory calculations, is typically used to assist in the interpretation of the Raman spectra. [3] Despite the efforts, the full interpretation of NMC Raman spectra, particularly with respect to its charged states, remains undone.In our investigation, we found noticeable changes in the Raman spectra across samples with similar, but non-identical, compositions. We also see that partially and fully charged NMC samples have significantly more than two or three Raman modes varied or shifted, likewise suggesting more complex spectrum. The systematic comparison of a larger number of spectra allowed us to identify these variations and correlate them with specific material compositions. We developed a novel approach for interpreting Raman spectra of NMC materials that involves an extensive collection of spectral data. This method requires us to gather Raman spectra from diverse NMC samples with varying compositions, particle sizes, and morphologies. We use advanced analysis to identify correlations and trends between the spectral features and the material properties. This demanding approach gives a more comprehensive understanding of the relationship between the Raman spectra and the composition of NMC samples, which can facilitate better interpretation and design of these materials for use in Li-ion batteries. In this work, we will highlight the potential of this method to enable us to more accurately interpret Raman spectra of charge and discharge states that might further help in developing easy monitoring of NMC electrodes during their operation. A detailed data analysis will be presented at the conference. Funding for this work was provided by the National Science Center in Poland under the Sonata BIS 11 program (No. UMO-2021/42/E/ST5/00390).[1] P.P.R.M.L. Harks et al. J. Power Sources 288 (2015) 92-105[2] E. Flores et al. Front. Energy Res., 6 (2018) 82[3] E. Flores et al. Chem. Mater. 2020, 32, 1, 186–194

Spectral variables as criteria for selection of soybean genotypes at different vegetative stages

Understanding the association between variables obtained by multispectral imaging, such as plant canopy reflectance at different wavelengths and vegetation indices (VIs), and agronomic traits of interest for soybean is crucial for breeding programs. This approach, associated with the evaluation of the best stage for spectral data collection, can identify easier-to-measure variables to be used in the indirect selection of genotypes for more expensive-to-measure traits or those that are expressed later, resulting in a faster, labor-saving, and large-scale selection process. The hypothesis of this study is the possibility of identifying promising variables for the selection of soybean genotypes through the use of vis and that different times of collection of information regarding reflectance interfere in the selection responses. Thus, our objectives were: i) to estimate heritability (h2) for agronomic traits and VIs; ii) to estimate the gains with direct selection (DS) on the VIs and indirect selection (IS) for the agronomic traits selected by the higher heritability; iii) to estimate correlations between spectral variables, VIs, and agronomic traits; iv) to identify the most promising populations for the evaluated variables; and vi) to identify the most adequate phenological stage for spectral data collection. We installed a field experiment in a randomized block design with four repetitions, 28 F3 soybean populations, and four control treatments. Agronomic traits evaluated were: days to maturity (DM), plant height (PH), first pod insertion height (PIH), number of branches (NB), and grain yield (GY). Spectral collections were performed at the V8 (45 days after emergence), R1 (60 days after emergence) and R5 (80 days after emergence) stages. Correlations between agronomic traits, reflectance at 790 nm (near-infrared), 735 nm (RedEdge), 660 nm (red), 550 nm (green), and 450 nm (blue) wavelengths, and VIs were estimated. The heritability were estimated for agronomic traits and VIs. Our findings reveal that it is possible to select soybean genotypes using spectral variables based on heritability and phenotypic aspects. Enhanced vegetation index (EVI) and soil-adjusted vegetation index (SAVI) have high heritability values (>75%) at V8. It is possible to obtain satisfactory selection gains for agronomic traits, especially GY, based on selection on EVI and SAVI at V8 stage. By this approach, the F3 segregating populations that provided the highest selection gains were P7, P8, P9, P14, P27, and P28. Spectral data collection at V8 stage provided higher h2 for VIs and agronomic traits, while R5 is the most suitable stage for estimating associations between VIs and agronomic traits.

Photoacoustic Spectroscopy Combined with Integrated Learning to Identify Soybean Oil with Different Frying Durations.

Soybean oil produces harmful substances after long durations of frying. A rapid and nondestructive identification approach for soybean oil was proposed based on photoacoustic spectroscopy and stacking integrated learning. Firstly, a self-designed photoacoustic spectrometer was built for spectral data collection of soybean oil with various frying times. At the same time, the actual free fatty acid content and acid value in soybean oil were measured by the traditional titration experiment, which were the basis for soybean oil quality detection. Next, to eliminate the influence of noise, the spectrum from 1150 cm-1 to 3450 cm-1 was selected to remove noise by ensemble empirical mode decomposition. Then three dimensionality reduction methods of principal component analysis, successive projection algorithm, and competitive adaptive reweighting algorithm were used to reduce the dimension of spectral information to extract the characteristic wavelength. Finally, an integrated model with three weak classifications was used for soybean oil detection by stacking integrated learning. The results showed that three obvious absorption peaks existed at 1747 cm-1, 2858 cm-1, and 2927 cm-1 for soluble sugars and unsaturated oils, and the model based on stacking integrated learning could improve the classification accuracy from 0.9499 to 0.9846. The results prove that photoacoustic spectroscopy has a good detection ability for edible oil quality detection.

Rapid probing of glucose influx into cancer cell metabolism: using adjuvant and a pH-dependent collection of central metabolites to improve in-cell D-DNP NMR.

Changes to metabolism are a hallmark of many diseases. Disease metabolism under physiological conditions can be probed in real time with in-cell NMR assays. Here, we pursued a systematic approach towards improved in-cell NMR assays. Unambiguous identifications of metabolites and of intracellular pH are afforded by a comprehensive, downloadable collection of spectral data for central carbon metabolites in the physiological pH range (4.0-8.0). Chemical shifts of glycolytic intermediates provide unique pH dependent patterns akin to a barcode. Using hyperpolarized 13C1 enriched glucose as the probe molecule of central metabolism in cancer, we find that early glycolytic intermediates are detectable in PC-3 prostate cancer cell lines, concurrently yielding intracellular pH. Using non-enriched and non-enhanced pyruvate as an adjuvant, reactions of the pentose phosphate pathway become additionally detectable, without significant changes to the barriers in upper glycolysis and to intracellular pH. The scope of tracers for in-cell observations can thus be improved by the presence of adjuvants, showing that a recently proposed effect of pyruvate in the tumor environment is paralleled by a rerouting of cancer cell metabolism towards producing building blocks for proliferation. Overall, the combined use of reference data for compound identification, site specific labelling for reducing overlap, and use of adjuvant afford increasingly detailed insight into disease metabolism.

Soil moisture effects on predictive VNIR and MIR modeling of soil organic carbon and clay content

Portable visible to near-infrared (VNIR) and mid-infrared (MIR) soil spectroscopy holds great potential to support field applications in soil science and management by complementing conventional soil analytical methods. Under field conditions, however, soil moisture can critically affect the quality of reflectance measurements. In this study, we examined the effects of soil moisture on VNIR and MIR soil spectra and how its magnitude and variation impact the accuracy and robustness of predictive spectral models. We carried out a systematic re-wetting experiment on two soil datasets of different scale and origin that were measured at four gravimetric moisture levels (air-dried, 5 %, 10 %, 15 %) with portable VNIR and MIR instruments. The spectral data of each moisture class, as well as randomized combinations of different moisture contents, were then used to calibrate VNIR, MIR and combined PLSR models to estimate soil organic carbon (SOC) and clay content, where combined models included spectra concatenation (VNMIR) and model output average (MOA). The overall shape of MIR spectra was more significantly distorted by soil moisture than VNIR spectra, while the general impact of soil water content in both spectral domains was texture-dependent. In terms of predictive accuracy, MIR models were generally superior for air-dried sample material, while VNIR models fared better for uniformly moist samples. With increasing soil moisture variability, comparative estimation accuracies between individual VNIR and MIR models were dependent on the underlying dataset. VNMIR and MOA models proved beneficial and yielded the most accurate and robust predictions for SOC and clay content when soil moisture was variable, irrespective of the considered dataset (regional dataset: RMSESOC = 0.22–0.27 %, RMSECLAY = 2.67–3.14 %; field dataset: RMSESOC = 0.09–0.11 %, RMSECLAY = 0.87–1.15 %). Predictive mechanisms, as evaluated by variable importance in the projection (VIP) of PLSR models, changed substantially with variation in soil water content, especially in the MIR, where important absorption bands for SOC and clay minerals could be heavily attenuated or completely masked. Our study highlights the advantages of employing both VNIR and MIR instruments for spectral data collection on soils in field condition and the potential of integrating VNIR and MIR spectra collected at different soil moisture levels into soil spectral libraries.

Wheat leaf area index prediction using data fusion based on high-resolution unmanned aerial vehicle imagery

BackgroundLeaf Area Index (LAI) is half of the amount of leaf area per unit horizontal ground surface area. Consequently, accurate vegetation extraction in remote sensing imagery is critical for LAI estimation. However, most studies do not fully exploit the advantages of Unmanned Aerial Vehicle (UAV) imagery with high spatial resolution, such as not removing the background (soil and shadow, etc.). Furthermore, the advancement of multi-sensor synchronous observation and integration technology allows for the simultaneous collection of canopy spectral, structural, and thermal data, making it possible for data fusion.MethodsTo investigate the potential of high-resolution UAV imagery combined with multi-sensor data fusion in LAI estimation. High-resolution UAV imagery was obtained with a multi-sensor integrated MicaSense Altum camera to extract the wheat canopy's spectral, structural, and thermal features. After removing the soil background, all features were fused, and LAI was estimated using Random Forest and Support Vector Machine Regression.ResultsThe results show that: (1) the soil background reduced the accuracy of the LAI prediction of wheat, and soil background could be effectively removed by taking advantage of high-resolution UAV imagery. After removing the soil background, the LAI prediction accuracy improved significantly, R2 raised by about 0.27, and RMSE fell by about 0.476. (2) The fusion of multi-sensor synchronous observation data could achieve better accuracy (R2 = 0.815 and RMSE = 1.023), compared with using only one data; (3) A simple LAI prediction method could be found, that is, after selecting a few features by machine learning, high prediction accuracy can be obtained only by simple multiple linear regression (R2 = 0.679 and RMSE = 1.231), providing inspiration for rapid and efficient LAI prediction of wheat.ConclusionsThe method of this study can be transferred to other sites with more extensive areas or similar agriculture structures, which will facilitate agricultural production and management.

AI-DRIVEN MAIZE YIELD FORECASTING USING UNMANNED AERIAL VEHICLE-BASED HYPERSPECTRAL AND LIDAR DATA FUSION

Abstract. The increased availability of remote sensing data combined with the wide-ranging applicability of artificial intelligence has enabled agriculture stakeholders to monitor changes in crops and their environment frequently and accurately. Applying cutting-edge technology in precision agriculture also enabled the prediction of pre-harvest yield from standing crop signals. Forecasting grain yield from standing crops benefits high-throughput plant phenotyping and agriculture policymaking with information on where crop production is likely to decline. Advanced developments in the Unmanned Aerial Vehicle (UAV) platform and sensor technologies aided high-resolution spatial, spectral, and structural data collection processes at a relatively lower cost and shorter time. In this study, UAV-based LiDAR and hyperspectral images were collected during the growing season of 2020 over a cornfield near Urbana Champaign, Illinois, USA. Hyperspectral imagery-based canopy spectral & texture features and LiDAR point cloud-based canopy structure features were extracted and, along with their combination, were used as inputs for maize yield prediction under the H2O Automated Machine Learning framework (H2O-AutoML). The research results are (1) UAV Hyperspectral imagery can successfully predict maize yield with relatively decent accuracies; additionally, LiDAR point cloud-based canopy structure features are found to be significant indicators for maize yield prediction, which produced slightly poorer, yet comparable results to hyperspectral data; (2) regardless of machine learning methods, integration of hyperspectral imagery-based canopy spectral and texture information with LiDAR-based canopy structure features outperformed the predictions when using a single sensor alone; (3)the H2O-AutoML framework presented to be an efficient strategy for machine learning-based data-driven model building.

An experimental study of the alteration of basalt on the surface of Venus

Characterizing the surface of Venus has been complicated by its thick atmosphere and caustic surface conditions (~470 °C, 90 bars). Several approaches, including the collection of spectral data, thermodynamic modelling, lander missions, and surface weathering laboratory experiments have progressed our view of what lies at the surface. However, surface-atmosphere interactions remain somewhat unconstrained and interpretations of the spectral data rely on an understanding of the surface-atmosphere alteration. We used a cold-seal pressure vessel apparatus pressurized with pure CO2 gas and both synthetic and natural glassy basalts specimens to simulate chemical weathering on the surface of Venus for a duration of two weeks. The extent of alteration was described from the surface of samples to depth using Rutherford Backscatter Spectroscopy (RBS), scanning electron microscopy (SEM), and transmission electron microscopy (TEM) techniques. We describe the alteration zones of reacted basalt specimens and report an enrichment of divalent cation species at the near surfaces of basalts; Ca2+ was enriched by ~5 wt% and Fe2+ was enriched by ~1–2 wt%. The enrichment at the near surface favors the production of iron (Fe) oxide(s) and carbonates on the surfaces, which form discontinuous coatings on all reacted samples in two weeks duration. Our results aid in the interpretation of radar emissivity data by constraining which alteration products should be present on the surface and suggesting timeframes necessary for their detection. Assuming that radar emissivity is able to discern weathered basalt, especially those dominated by carbonates and/or semiconducting minerals Fe oxide(s), our results suggest that basalts at Idunn Mons in Imdr Regio previously thought to be anywhere from 2.5 million to a few years old (Smrekar et al., 2010; D'Incecco et al., 2017; Filiberto et al., 2020; Cutler et al., 2020) could instead be as young as 65,000 years to 110,000 years depending on basalt type.

Low‐cost, handheld near‐infrared spectroscopy for root dry matter content prediction in cassava

AbstractOver 800 million people across the tropics rely on cassava (Manihot esculenta Crantz) as a major source of calories. While the root dry matter content (RDMC) of this starchy root crop is important for both producers and consumers, characterization of RDMC by traditional methods is time‐consuming and laborious for breeding programs. Alternate phenotyping methods have been proposed but lack the accuracy, cost, or speed ultimately needed for cassava breeding programs. For this reason, we investigated the use of a low‐cost, handheld near‐infrared spectrometer (740–1070 nm) for field‐based RDMC prediction in cassava. Oven‐dried measurements of RDMC were paired with 21,044 scans of roots of 376 diverse genotypes from 10 field trials in Nigeria and grouped into training and test sets based on cross‐validation schemes relevant to plant breeding programs. Mean partial least squares regression model performance ranged from R2P = 0.62–0.89 for within‐trial predictions, which is within the range achieved with laboratory‐grade spectrometers in previous studies. Relative to other factors, model performance was highly affected by the inclusion of samples from the same environment in both the training and test sets. With appropriate model calibration, the tested spectrometer will allow for field‐based collection of spectral data with a smartphone for accurate RDMC prediction and potentially other quality traits, a step that could be easily integrated into existing harvesting workflows of cassava breeding programs.

In-situ manipulations of aquatic optical depth and its effect on small unoccupied aerial systems–derived spectral reflectance

The collection of spectral data with sensors fixed to various platforms (e.g., satellites, occupied aerial vehicles, and small unoccupied aerial systems (sUAS)) has allowed for the estimation of optically active constituents (OACs) common in surface waters. However, in small, complex, and optically shallow waters where multiple OACs (e.g., chlorophyll-a and total suspended solids) impact the spectral signature, these technologies have experienced significant limitations. Altering the scale at which these examinations are performed on surface waters (e.g., ponds and lakes) to mesocosm systems (37 cm in height and 30 cm in diameter) provides information on the interactions between multiple OACs and insight on the impact aquatic optical depth has on remotely sensed spectra. This field study examines optically shallow and optically deep mesocosm systems simulated in five-gallon buckets to determine the role aquatic optical depth has on developing accurate surface-water quality models. Results demonstrated an accurate representation of OACs in optically deep mesocosms compared with optically shallow mesocosms when assessed with sUAS (i.e., relative percent differences in predicted iron concentrations of −86 and 16 for optically shallow and deep waters, respectively). The interferences observed under these conditions were comparable to literature values when studying optically complex water bodies with hyperspectral data. This study provides a basis for understanding the benefits and limitations of monitoring in-situ water quality via sUAS.

Development and performance test of a vehicle-mounted total nitrogen content prediction system based on the fusion of near-infrared spectroscopy and image information

To measure the total nitrogen (TN) content of large-scale farmland soil accurately in real time and guide field fertilization, a vehicle-mounted soil TN content prediction system based on the fusion of near-infrared spectroscopy and image information was developed. A combined algorithm of uniform variable illumination (UVE) and adaptive weighted sampling (CARS) were used to select the characteristic wavelength, and the selected characteristic wavelength was used as the soil spectral information. Multiple linear regression model, partial least squares regression model, BP neural network prediction model and Catboost prediction model were chosen to predict soil TN content. After comparison, Catboost was finally selected as the final prediction model. The prediction system was composed of a mechanical part, an optical part, and a control part. The mechanical part provided space support for the prediction system, the optical part obtained the spectrum and image information of the soil, mainly including seven single-band near-infrared (NIR) filters: 945, 1045, 1200, 1300, 1450, 1535, and 1615 nm; 1450 nm is the sensitive wavelength which is used to eliminate the effect of water. The control part realized spectral data collection, image feature processing, data fusion, and the prediction of soil TN content. Soil samples were used to test the accuracy of the spectrum collection of the system. The test results showed that the highest correlation coefficient between the reflectance of the prediction system at seven sensitive wavelengths and the reflectance of the NIRQuest 512 infrared spectrometer is above 0.943. The field test results show that the R2 between the predicted soil TN content by the prediction system and the value of laboratory standard detection method is greater than 0.80 and the relative errors are less than 10%. The results also show that data fusion of spectral data and image features highlighted the common contribution of the near infrared spectrum and visible light images in the detection of soil TN content, and it can improve the prediction accuracy of the instrument. Moreover, the system can provide guidance for farmland scientific variable fertilization.

Sustainability Trait Modeling of Field-Grown Switchgrass (Panicum virgatum) Using UAV-Based Imagery.

Unmanned aerial vehicles (UAVs) provide an intermediate scale of spatial and spectral data collection that yields increased accuracy and consistency in data collection for morphological and physiological traits than satellites and expanded flexibility and high-throughput compared to ground-based data collection. In this study, we used UAV-based remote sensing for automated phenotyping of field-grown switchgrass (Panicum virgatum), a leading bioenergy feedstock. Using vegetation indices calculated from a UAV-based multispectral camera, statistical models were developed for rust disease caused by Puccinia novopanici, leaf chlorophyll, nitrogen, and lignin contents. For the first time, UAV remote sensing technology was used to explore the potentials for multiple traits associated with sustainable production of switchgrass, and one statistical model was developed for each individual trait based on the statistical correlation between vegetation indices and the corresponding trait. Also, for the first time, lignin content was estimated in switchgrass shoots via UAV-based multispectral image analysis and statistical analysis. The UAV-based models were verified by ground-truthing via correlation analysis between the traits measured manually on the ground-based with UAV-based data. The normalized difference red edge (NDRE) vegetation index outperformed the normalized difference vegetation index (NDVI) for rust disease and nitrogen content, while NDVI performed better than NDRE for chlorophyll and lignin content. Overall, linear models were sufficient for rust disease and chlorophyll analysis, but for nitrogen and lignin contents, nonlinear models achieved better results. As the first comprehensive study to model switchgrass sustainability traits from UAV-based remote sensing, these results suggest that this methodology can be utilized for switchgrass high-throughput phenotyping in the field.