Waveband Combinations Research Articles

Interpretable machine learning study of a collector based on combined twisted-tape and wavy-tape inserts

Nowadays, the efficiency of air collectors for solar thermal applications is still low, and many researchers tend to use machine learning to predict and model the performance of thermal systems, but most of the existing machine learning methods are uninterpretable, which poses a challenge for machine learning applications. In this paper, a new collector insert with enhanced heat transfer in the form of a combination of wave and helical twisted bands is firstly designed for performance test experiments using solar air collectors. Then, based on the test data, three mutually interpretable machine learning methods, PDP, ALE, and SHAP, are explored for predictive studies of collector performance. The results show that the average efficiency of the collector with inserted structure increases by 19.71 %, 12.25 %, and 17.53 % at inlet flow rates of 2.1 m/s, 3.3 m/s, and 4.5 m/s, respectively. The highest collector efficiency was achieved with a wave plate length of 360 mm, a helical twist ratio of 5.14, and an inlet flow rate of 4.5 m/s. Understanding how much the input affects the output through the interpretability of SHAP proves the value of interpretable machine learning, which is useful in guiding the modification of the collector structure.

Quantitative determination of oxides in cement raw meal based on near-infrared spectroscopy and hybrid feature selection strategy

Determining the content of components in cement raw meal is vital in Portland cement manufacturing. Near-infrared spectroscopy (NIRS)enables rapid, safe, and accurate quantitative analysis of the primary constituents of cement raw meal (CaO, SiO2, Al2O3, and Fe2O3), thereby assisting the cement industry in reducing the time delay in raw meal proportioning control and enhancing the quality of the raw meal. This study employed a hybrid feature selection strategy to identify effective feature points in the NIRS of raw meal samples. Effective feature points from the raw meal were integrated with partial least squares (PLS) to develop a regression model. Initially, NIRS data from raw meal samples were obtained using a Fourier NIR spectrometer. Subsequently, sample set partitioning based on joint X-Y distance (SPXY) was utilized to divide the samples into a calibration set (70 samples) and a validation set (22 samples). Next, A backward interval partial least squares (BiPLS) approach, along with various preprocessing algorithms, was then employed to initially screen the optimal waveband combinations of the NIRS. Within these combinations, effective feature points were further identified using competitive adaptive reweighted sampling (CARS), variable combined population analysis (VCPA) and weighted fusion variable space shrinkage approach (WFVSSA). Finally, we developed and compared PLS models based on the full spectrum and three hybrid feature selection methods. The results demonstrated that.WFVSSA offers a comprehensive assessment of wavelength importance, effectively preserving feature points while eliminating redundant information. BiPLS-WFVSSA-PLS outperformed BiPLS-CARS-PLS and BiPLS-VCPAPLS on the validation set, with R2, RMSEP, and RPD values of 0.8676, 0.1431, and 2.8129 for CaO; 0.9212, 0.1216, and 3.6461 for SiO2; 0.9198, 0.0607, and 3.5618 for Al2O3; and 0.8717, 0.0166, and 2.8614 for Fe2O3, respectively. These findings underscore the superior accuracy and stability of BiPLS-WFVSSA-PLS in determining cement raw meal component contents.

Multidimensional high-temperature field measurement method for flame based on near infrared radiation spectrum of water vapor

The temperature distribution is an important parameter in the design and optimization of :various engine types, and this paper begins by analyzing the temperature sensitivities of different waveband combinations. Based on an evaluation of the effects of self-absorption phenomena on the temperature measurement accuracy, a multidimensional temperature measurement method based on the integrated ratio of the intensity of the water vapor broadband radiation spectra is proposed. To address the multidimensional temperature inversion problem, the practicality of a nonlinear reconstruction approach is evaluated, and a multiple linear iteration algorithm is proposed. In addition, validation experiments are performed in the form of methane/oxygen laminar flame temperature measurements in combination with parallel rotating beam spectroscopy, and the results show that the method exhibits temperature measurement resolution of 10 K. The method proposed and developed in this work provides a new experimental concept for high-temperature measurements and is expected to provide reliable multidimensional temperature data for combustion chambers and plumes in engine ground experiments.

A new multispectral index for canopy nitrogen concentration applicable across growth stages in ryegrass and barley

Accurately monitoring Canopy Nitrogen Concentration (CNC) is a prerequisite for precision nitrogen (N) fertiliser management at the farm scale with carbon and N budgeting across the landscape and ecosystems. While many spectral indices have been proposed for CNC monitoring, their applicability and accuracy are often adversely affected by confounding factors such as aboveground biomass (AGB), crop type, growth stages, and environmental conditions, limiting their broader application and adoption; with AGB being one of the most dominant signals and confounding factors at canopy scale. The confounding effect can become more challenging as AGB is also physiologically linked with CNC across the growth stages. Additionally, the interplay between index form, selection of optimal wavebands and their bandwidths remains poorly understood for CNC index design. This study proposes robust and cost-effective 2- and 4-waveband multispectral (MS) CNC indices applicable across a wide range of crop conditions. We collected 449 canopy reflectance spectra (400–980 nm) together with corresponding CNC and AGB measurements across four growth stages of ryegrass (winter and summer), and five growth stages of barley (winter-spring) in Victoria, Australia, in 2018 and 2019. All possible waveband (400–980 nm) combinations revealed that the best combination varied between seasons and crop types. However, the visible spectrum, particularly the blue region, presented high and consistent performance. Bandwidths of 10–40 nm outperformed either very narrow (2 nm) or very broad bandwidths (80 nm). The newly developed 2-waveband index (416 and 442 nm with 10-nm bandwidth; R2 = 0.75 and NRMSE = 0.2) and 4-waveband index (512, 440, 414 and 588 nm with 40-nm bandwidth; R2 = 0.81 and NRMSE = 0.17) exhibited the best performance, while validation with an independent dataset (from a different growing period to those used in the model development) obtained NRMSE values of 0.25 and 0.24, respectively. The 4-waveband index provides enhanced performance and permits use of broader bandwidths than its 2-waveband counterpart.

Predicting key soil properties from Vis-NIR spectra by applying dual-wavelength indices transformations and stacking machine learning approaches

Soil visible and near-infrared (Vis-NIR) spectroscopy has been widely used for soil characterization, due to its high potential for assessing different soil properties. However, despite great successes achieved by applying the method, there is a potential for further improvement, especially regarding data (pre-) processing and modeling. In this study, we employ simple ratio indices (SRI) and normalized difference indices (NDI), calculated from all combinations of different wavebands of Vis-NIR spectra, for improving the prediction of key soil properties such as calcium carbonate content (CaCO3), cation exchange capacity (CEC), clay content (Clay), sand content (Sand), nitrogen content (N), organic carbon content (OC), and pH in CaCl2 (pH). For this, we use the topsoil physicochemical and multispectral reflectance data from the Land Use/Land Cover Area Frame Survey (LUCAS) dataset. Various machine learning techniques were employed for the modeling, including partial least squares regression (PLSR), ridge regression, principal component regression (PCR), and two stacked algorithms. Based on the results obtained, both the SRI and NDI transformations significantly improved the performance of all the models compared to the untransformed data. However, SRI was superior to NDI. The stacked model PCR-poly applied on the SRI data yielded the best prediction performances for all the soil properties. The model gave RMSE (R2) values of 25.71 (0.96), 6.89 (0.80), 5.41 (0.82), 1.11 (0.92), 21.34 (0.95), 0.35 (0.94) and 13.41 (0.73) for estimation of CaCO3, CEC, Clay, N, OC, pH and sand, respectively. The findings of this study showed that applying the SRI and NDI transformations on Vis-NIR data and employing stacked models for calibration, yield performances for soil properties prediction that are similar to those obtained by using deep learning based methods on the same dataset in previous works, while being computationally less demanding.

Optimising Multispectral Active Fluorescence to Distinguish the Photosynthetic Variability of Cyanobacteria and Algae.

This study assesses the ability of a new active fluorometer, the LabSTAF, to diagnostically assess the physiology of freshwater cyanobacteria in a reservoir exhibiting annual blooms. Specifically, we analyse the correlation of relative cyanobacteria abundance with photosynthetic parameters derived from fluorescence light curves (FLCs) obtained using several combinations of excitation wavebands, photosystem II (PSII) excitation spectra and the emission ratio of 730 over 685 nm (Fo(730/685)) using excitation protocols with varying degrees of sensitivity to cyanobacteria and algae. FLCs using blue excitation (B) and green−orange−red (GOR) excitation wavebands capture physiology parameters of algae and cyanobacteria, respectively. The green−orange (GO) protocol, expected to have the best diagnostic properties for cyanobacteria, did not guarantee PSII saturation. PSII excitation spectra showed distinct response from cyanobacteria and algae, depending on spectral optimisation of the light dose. Fo(730/685), obtained using a combination of GOR excitation wavebands, Fo(GOR, 730/685), showed a significant correlation with the relative abundance of cyanobacteria (linear regression, p-value < 0.01, adjusted R2 = 0.42). We recommend using, in parallel, Fo(GOR, 730/685), PSII excitation spectra (appropriately optimised for cyanobacteria versus algae), and physiological parameters derived from the FLCs obtained with GOR and B protocols to assess the physiology of cyanobacteria and to ultimately predict their growth. Higher intensity LEDs (G and O) should be considered to reach PSII saturation to further increase diagnostic sensitivity to the cyanobacteria component of the community.

Wavelength Selection Method Based on Absorbance Value Optimization to Near-Infrared Spectroscopic Analysis

Regarding absorption spectrum, high absorption corresponds to low light transmittance and relatively loud noise, whereas low absorption corresponds to low information content, which interferes with the modeling of spectral analysis. Appropriate absorbance level is necessary to improve spectral information content and reduces noise level. In this study, based on the selection of the upper and lower bounds of absorbance, the absorbance value optimization partial least squares (AVO-PLS) method was proposed for appropriate wavelength model selection. Near-infrared spectroscopic analysis of hyperlipidemia indicators, namely, total cholesterol (TC), and triglyceride (TG), was conducted to validate the predicted performance of AVO-PLS. Well-performed wavelength selection methods, namely, moving-window PLS (MW-PLS) of continuous type-and successive projections algorithm (SPA) of discrete type, were also conducted for comparison. The spectra were first corrected using Savitzky–Golay smoothing. Modeling was performed based on the multiple partitioning of calibration and prediction sets to avoid data over-fitting and achieve parameter stability. The selected absorbance ranged from 0.45 to 0.86 for TC and from 0.45 to 0.92 for TG, and the corresponding waveband combinations were 1,376–1,388 and 1,560–1840 nm for TC and 1,376–1,390 and 1,552–1,846 nm for TG. Among them, the waveband combination of TG covers TC’s one, and can be used for the high-precision cooperativity analysis of the two indicators. Using the independent validation samples, the RMSEP and RP of 0.164 mmol l−1 and 0.990 for TC and 0.096 mmol l−1 and 0.997 for TG were obtained by the cooperativity model. And the sensitivity and specificity for hyperlipidemia were 98.0 and 100%, respectively. These values were better than those of MW-PLS and SPA. Importantly, the proposed AVO-PLS is a novel multi-band optimization approach for improving prediction performance and applicability. This method is expected to obtain more applications.

Response of Different Band Combinations in Gaofen-6 WFV for Estimating of Regional Maize Straw Resources Based on Random Forest Classification

Maize straw is a valuable renewable energy source. The rapid and accurate determination of its yield and spatial distribution can promote improved utilization. At present, traditional straw estimation methods primarily rely on statistical analysis that may be inaccurate. In this study, the Gaofen 6 (GF-6) satellite, which combines high resolution and wide field of view (WFV) imaging characteristics, was used as the information source, and the quantity of maize straw resources and spatial distribution characteristics in Qihe County were analyzed. According to the phenological characteristics of the study area, seven classification classes were determined, including maize, buildings, woodlands, wastelands, water, roads, and other crops, to explore the influence of sample separation and test the responsiveness to different land cover types with different waveband combinations. Two supervised classification methods, support vector machine (SVM) and random forest (RF), were used to classify the study area, and the influence of the newly added band of GF-6 WFV on the classification accuracy of the study area was analyzed. Furthermore, combined with field surveys and agricultural census data, a method for estimating the quantity of maize straw and analyzing the spatial distribution based on a single-temporal remote sensing image and random forests was proposed. Finally, the accuracy of the measurement results is evaluated at the county level. The results showed that the RF model made better use of the newly added bands of GF-6 WFV and improved the accuracy of classification, compared with the SVM model; the two red-edge bands improved the accuracy of crop classification and recognition; the purple and yellow bands identified non-vegetation more effectively than vegetation, thus minimizing the “salt-and-pepper noise” of classification results. However, the changes to total classification accuracy were not obvious; the theoretical quantity of maize straw in Qihe County in 2018 was 586.08 kt, which reflects an error of only 2.42% compared to the statistical result. Hence, the RF model based on single-temporal GF-6 WFV can effectively estimate regional maize straw yield and spatial distribution, which lays a theoretical foundation for straw recycling.

Narrow-waveband spectral indices for prediction of yield loss in frost-damaged winter wheat during stem elongation

Frost during stem elongation is one of the most destructive disasters in China, which has a significant impact on the production of winter wheat. Automatic monitoring of frost injury to canopy is of vital importance to the early prediction of yield loss. This study investigated the potential of hyperspectral techniques in predicting the Percent Yield Difference (PYD) of frost-damaged winter wheat. Three artificial frost experiments were conducted to obtain hyperspectral reflectance and grain yield for winter wheat subjected to sub-freezing temperature treatments. The PYD was used to evaluate the level of frost damage. Nine new indices based on the best combination of wavelengths were selected through the contour mapping approach. All new and published indices were used to establish the linear regression models with PYD. The results showed that as the value of PYD increased, the NIR reflectance within 760–1140 nm decreased, whereas the red and SWIR reflectance increased. The most significant change was found in the NIR region, where the water absorption bands within 930–970 nm almost disappeared. The cross-validation results indicated that the three water-sensitive spectral indices NWI-2, RDSI ((R958-R545)/(R826-R545)), and NDSI ((R962-R829)/(R962+R829)) demonstrated the best prediction accuracy and outperformed the partial least square regression (PLSR) and support vector regression (SVR) models. NWI-2 and NDSI represented a relatively simple waveband combination similar to NDVI, which could be referenced for developing satellite multispectral products to predict PYD at a large spatial scale. GS and PYD range had a significant impact on the spectral indices. The prediction accuracy of PYD for a single GS improved as development advanced before heading. When the PYD value was above 10 %, no significant differences between the subfreezing treatments and the unfrosted controls was detected until the PYD value exceeded 30–40%. It was difficult to predict the relatively low PYD level due to the hybrid response of the spectral reflectance to frost damage.

Hyperspectral imaging techniques for rapid detection of nutrient content of hydroponically grown lettuce cultivars

The analyses of online quality measurements of four lettuce cultivars (Rex, Tacitus, Black Seeded Simpson, Flandria) using hyperspectral image processing techniques have been studied. Seedlings were planted in Rockwool cubes and fed for 3 weeks using hydroponic nutrient solution containing 0, 50, 100, 150, 200, 250, and 300 ppm nitrogen. The hyperspectral images of the freshly cut lettuce leaves were captured using hyperspectral camera in the wavelength range of 400–1,000 nm. The algorithm to measure nutrient levels of leaf tissues including nitrate (NO3–), calcium (Ca2+), potassium (K+), soluble solid content (SSC), pH, and total chlorophyll concentration (SPAD reading) for lettuce was developed. To locate the optimum wave band combination values, simple linear regression models with two spectral data values, namely reflectance and its first derivative, and two spectral indices, namely ratio spectral index (RSI) and normalized difference spectral index (NDSI), were found. The optimal wave bands were within 506–601 nm and 634–701 nm. The nutrient levels of NO3–, Ca2+, K+, SSC, pH, and SPAD in the leaf samples were estimated using partial least squares regression (PLSR) and principal component analysis (PCA) techniques of the four optimal wave bands. Both PLSR and PCA models produced well correlated outcome in comparison with the laboratory measured freshly cut lettuce leaves in predicting nutrient contents with R2 = 0.784–0.987.

Raman Spectral Analysis for Quality Determination of Grignard Reagent

Grignard reagent is one of the most popular materials in chemical and pharmaceutical reaction processes, and requires high quality with minimal adulteration. In this study, Raman spectroscopic technique was investigated for the rapid determination of toluene content, which is one of the common adulterants in Grignard reagent. Raman spectroscopy is the most suitable spectroscopic method to mitigate moisture and CO2 interference in the molecules of Grignard reagent. Raman spectra for the mixtures of toluene and Grignard reagent with different concentrations were analyzed with a partial least square regression (PLSR) method. The combination of spectral wavebands in the prediction model was optimized with a variables selection method of variable importance in projection (VIP). The results obtained from the VIP-based PLSR model showed the reliable performance of Raman spectroscopy for predicting the toluene concentration present in Grignard reagent with a correlation coefficient value of 0.97 and a standard error of prediction (SEP) of 0.71%. The results showed that Raman spectroscopy combined with multivariate analysis could be an effective analytical tool for rapid determination of the quality of Grignard reagent.

Applications of Vegetative Indices from Remote Sensing to Agriculture: Past and Future

Remote sensing offers the capability of observing an object without being in contact with the object. Throughout the recent history of agriculture, researchers have observed that different wavelengths of light are reflected differently by plant leaves or canopies and that these differences could be used to determine plant biophysical characteristics, e.g., leaf chlorophyll, plant biomass, leaf area, phenological development, type of plant, photosynthetic activity, or amount of ground cover. These reflectance differences could also extend to the soil to determine topsoil properties. The objective of this review is to evaluate how past research can prepare us to utilize remote sensing more effectively in future applications. To estimate plant characteristics, combinations of wavebands may be placed into a vegetative index (VI), i.e., combinations of wavebands related to a specific biophysical characteristic. These VIs can express differences in plant response to their soil, meteorological, or management environment and could then be used to determine how the crop could be managed to enhance its productivity. In the past decade, there has been an expanded use of machine learning to determine how remote sensing can be used more effectively in decision-making. The application of artificial intelligence into the dynamics of agriculture will provide new opportunities for how we can utilize the information we have available more effectively. This can lead to linkages with robotic systems capable of being directed to specific areas of a field, an orchard, a pasture, or a vineyard to correct a problem. Our challenge will be to develop and evaluate these relationships so they will provide a benefit to our food security and environmental quality.

Diffuse reflectance spectroscopy for rapid estimation of soil Atterberg limits

Conventional methods for the determination of Atterberg limits based on laboratory tests are time-consuming. Reflectance spectroscopy which is fast and cost-effective has been reported as an alternative method for estimating Atterberg limits. To assess the efficiency of the method, 60 forest soil samples were measured by visible-near infrared reflectance spectroscopy (VNIR) within the range of 350–2500 nm. The Savitzky-Golay (SG) smoothing method for spectral data was used to reduce signal noise and the first derivative reflectance (DR) was applied to accentuate the features and assemble the data for use in the modeling process. In this study, raw reflectance (R) and first derivative reflectance (DR) data were used to estimate Atterberg limits. All two-band combinations of three types of spectra (ratio index, normalized difference index and difference index) as well as PLS and PLS-BPNN were calculated to extract optimum waveband combination and calibrations between Atterberg limits and reflectance spectra. The correlation coefficients between Atterberg limits and reflectance spectra indicated both positive and negative correlation at various wavelengths across the spectrum. The highest correlation for liquid limit (r = −0.86), plastic limit (r = −0.76) and plasticity index (r = −0.7) was found at 1921, 1938 and 1913 nm, respectively. In addition, the results showed the spectral indices technique as a good method for estimating soil plasticity and improving the prediction accuracy of Atterberg limits. In the current study, PLS and PLS–BPNN were also used to develop the calibration models for estimating Atterberg limits using R and DR. The results demonstrated that the prediction accuracy of PLS-BPNN for both R and DR was higher than that of PLS. Correlation coefficients between shrinkage limit (SL) and reflectance spectra showed weak correlation, and overall reflectance had the same correlation. The results represented that this method could be used to estimate soil plasticity properties quickly, non-destructively, and with minimal sample preparation and high accuracy. These advantages may be more important, especially when a huge number of samples should be tested and analyzed within a short period of time.

Radiometric Assessment of a UAV-Based Push-Broom Hyperspectral Camera.

The use of unmanned aerial vehicles (UAVs) for Earth and environmental sensing has increased significantly in recent years. This is particularly true for multi- and hyperspectral sensing, with a variety of both push-broom and snap-shot systems becoming available. However, information on their radiometric performance and stability over time is often lacking. The authors propose the use of a general protocol for sensor evaluation to characterize the data retrieval and radiometric performance of push-broom hyperspectral cameras, and illustrate the workflow with the Nano-Hyperspec (Headwall Photonics, Boston USA) sensor. The objectives of this analysis were to: (1) assess dark current and white reference consistency, both temporally and spatially; (2) evaluate spectral fidelity; and (3) determine the relationship between sensor-recorded radiance and spectroradiometer-derived reflectance. Both the laboratory-based dark current and white reference evaluations showed an insignificant increase over time (<2%) across spatial pixels and spectral bands for >99.5% of pixel–waveband combinations. Using a mercury/argon (Hg/Ar) lamp, the hyperspectral wavelength bands exhibited a slight shift of 1-3 nm against 29 Hg/Ar wavelength emission lines. The relationship between the Nano-Hyperspec radiance values and spectroradiometer-derived reflectance was found to be highly linear for all spectral bands. The developed protocol for assessing UAV-based radiometric performance of hyperspectral push-broom sensors showed that the Nano-Hyperspec data were both time-stable and spectrally sound.

Hyperspectral band selection using genetic algorithm and support vector machines for early identification of charcoal rot disease in soybean stems

BackgroundCharcoal rot is a fungal disease that thrives in warm dry conditions and affects the yield of soybeans and other important agronomic crops worldwide. There is a need for robust, automatic and consistent early detection and quantification of disease symptoms which are important in breeding programs for the development of improved cultivars and in crop production for the implementation of disease control measures for yield protection. Current methods of plant disease phenotyping are predominantly visual and hence are slow and prone to human error and variation. There has been increasing interest in hyperspectral imaging applications for early detection of disease symptoms. However, the high dimensionality of hyperspectral data makes it very important to have an efficient analysis pipeline in place for the identification of disease so that effective crop management decisions can be made. The focus of this work is to determine the minimal number of most effective hyperspectral wavebands that can distinguish between healthy and diseased soybean stem specimens early on in the growing season for proper management of the disease. 111 hyperspectral data cubes representing healthy and infected stems were captured at 3, 6, 9, 12, and 15 days after inoculation. We utilized inoculated and control specimens from 4 different genotypes. Each hyperspectral image was captured at 240 different wavelengths in the range of 383–1032 nm. We formulated the identification of best waveband combination from 240 wavebands as an optimization problem. We used a combination of genetic algorithm as an optimizer and support vector machines as a classifier for the identification of maximally-effective waveband combination.ResultsA binary classification between healthy and infected soybean stem samples using the selected six waveband combination (475.56, 548.91, 652.14, 516.31, 720.05, 915.64 nm) obtained a classification accuracy of 97% for the infected class. Furthermore, we achieved a classification accuracy of 90.91% for test samples from 3 days after inoculation using the selected six waveband combination.ConclusionsThe results demonstrated that these carefully-chosen wavebands are more informative than RGB images alone and enable early identification of charcoal rot infection in soybean. The selected wavebands could be used in a multispectral camera for remote identification of charcoal rot infection in soybean.

Integrating aerial images for in-season nitrogen management in a corn field

Methods of determining in-season corn (Zea mays L.) nitrogen (N) requirements and yield estimates are needed for designing a resource-efficient corn production system that is both profitable and environmentally sustainable. The objectives of this study were to examine: (1) the role of spectral signatures of corn plants obtained by aerial images in examining the yield variability across various N treatments, (2) whether the images could be used to guide in-season N management decisions, and to predict in-season corn yield and corn yield loss, and (3) the influence of spatial resolution of imagery on the accuracy of corn yield prediction models. Twenty-four treatments evaluated were the combinations of eight fertilization times (at-planting (A), pre-planting (P)∗A, P∗A∗mid-season (M), P∗A∗late-season (L), PAML, AM, AL, and AML) and three at-planting N rates (11, 45, and 78 kg N ha−1). Visual and thermal images were collected from manned aircraft and geo-corrected for the analyses. Vegetation indices and ratios were derived from three waveband combinations of visual images, and they were examined in relation to yield. Two linear regression models - model 1 (based solely on imagery) and model 2 (based on imagery and information about elevation and N fertilizer application rate), were tested on their performances (in terms of coefficient of determination (R2) and root mean square error (RMSE)) for in-season corn yield prediction at four spatial resolutions (0.35, 0.5, 1, and 2 m px−1). Among individual wavebands, and vegetation indices and ratio, plant pigment ratio (PPR) at early growth stages were highly correlated to corn yield, particularly in the field that received limited N application. The correlation improved as the corn growth stage progressed, but weakened towards the end of the growing season. There were significant differences in PPR values between the treatments receiving the least and the most N application, and it was the amount of N applied at planting that created the most significant differences. The models for 0.35 to 1 m px−1 spatial resolutions did not show significant improvements in R2 over the lowest ground resolutions (2 m px−1) (differences in R2 ≤ 0.05). The model 2 showed higher R2 (up to 0.64 at tasseling stage) and lower RMSE than model 1. These results indicate that the models developed integrating spectral and spatial information from aerial imagery with the information about elevation and N application rate help improve in-season corn yield estimates under different N management practices.

Distinguishing One Year and Two Year Old Canes of Red Raspberry Plant using Spectral Reflectance

Red raspberry (Rubus idaeus) is one of the important horticultural crops around the world. Various canopy management activities such as cane pruning, bundling and tying are used in this crop to improve light distribution and air-flow through plant canopies, which will reduce pest stress and improve crop yield and quality. This operation, however, is highly labor intensive, which threatens the long-term, sustainability of the red raspberry industry as labor availability is dwindling and labor cost is increasing rapidly. Mechanized or automated pruning and bundling system could be a key to ease this problem and increase returns to the growers. First step in developing an automated pruning system is to distinguish one-year-old canes (called primocanes) and two-year-old canes (called floricanes), which could then be used by a robotic system to selectively remove floricanes from the mix of primocanes and floricanes. Floricanes and primocanes look similar in terms of color, shape and size of the canes during dormant season. Hence, a non-imaging spectroscopy method was investigated in this study to utilize spectral signature of primocanes and floricanes, which can vary between two types of canes based on their difference in moisture content and chlorophyll concentration. Forty samples of each floricanes and primocanes were collected in Nov 2017 from a plot of ‘Wakefield’ cultivar. Optimal wavebands were selected using Principal Component Analysis (PCA) and one-way ANOVA. Wavebands with the significance level of 5% were used. With a group of wavebands in the visible spectrum (596nm, 65nm, 676 nm and 716nm), primocanes and floricanes were distinguished with an accuracy of 91.7% using linear support vector machine. With a combination of wavebands from chlorophyll absorption and water absorption region (716nm, 856nm, 996nm, 1056nm, and 1396nm), a classification accuracy of 100% was achieved. Results show a promise for developing a multispectral sensor (with a few selected bands) for distinguishing between floricane and primocane. To our knowledge, this work represents the first study to compare the reflectance spectra signature to distinguish primocanes and floricanes of red raspberry plants.

PREDIKSI PARAMETER-PARAMETER BIOFISIK TANAMAN PADI DARI DATA GROunDSPECTROmETER DAN HYPERSPECTRAL PESAWAT TERBANG DENGAN MENGGUNAKAN TEKNIK PARTIAL LEAST SquARE REGRESSIOn (PLSR) DAN nORmALIzED DIFFEREnCE SPECTRAL InDEx (NDSI)

Paddy rice canopy hyperspectral was measured by using ground-based spectroradiometer and HyMap sensor onboard an airplane from 350 nm up to 2500 nm in the same timethat covered various growth stages. Coinciding with hyperspectral measurement, biophysical parameters such as leaf area index (LAI), SPAD value were measured onground during the airplane passed over area of interest (AOI). Rice yield was measured at the time of final harvesting by random selected yield (ubinan method) for each sampling area. In finding the best correlation among canopy hyperspectral reflectance with crop development, optimal individual waveband explored with involving all possible waveband combinations to obtain the best fitted two-pair waveband related to crop biophysical parameters. Normalized Difference Spectral Index (NDSI) was appliedfrom spectral transformations (obtained from optimal waveband selected by exploring all possible waveband) to improve sensitivity analysis on plant. Canopy hyperspectralprovided information about plant, soil and water background when plant canopy don’t completely cover soil surface yet. The present study was directed to examine spectralindices and establish the relationships between biophysical parameters of rice by using partial least square regression (PLSR) technique.

Hyperspectral characteristic analysis for leaf nitrogen content in different growth stages of winter wheat.

The spectral characteristics in the range of visible light and near-infrared shortwave (400-1000 nm) are analyzed using the ground measured hyperspectral data and leaf nitrogen content (LNC) data of different growth stages of winter wheat, which were acquired in 2013 and 2015. First, the quantitative models for monitoring the LNC at different growth stages of winter wheat were established using the main vegetation nitrogen spectral indices. By analyzing the simulation coefficient of the models, it is demonstrated that vegetation nitrogen spectral indices, which are calculated using these data in this study, should not be an effective quantitative estimate for winter wheat LNC. Second, a method for finding representation wavebands of hyperspectral data sensitive to the LNC of winter wheat is proposed based on the spectral correlation. Using the hyperspectral data, which were acquired in 2015 and the proposed method, the representation wavebands sensitive to the LNC of winter wheat are found. The finding results show that the representative wavebands are mainly located in the purple, red and near-infrared wavelength range, but the representative wavebands are different in different stages. The red edge effects of representative wavebands are obvious. Finally, based on the acquired representation wavebands corresponding to different growth stages of winter wheat, the quantitative models for monitoring the LNC at different growth stages of winter wheat were established using data acquired in 2015 and 2013. The modeling results show that the combination of representation wavebands found to correspond to different growth stages of winter wheat are effective and credible for monitoring the LNC. So, these research results lay the foundation for accurate quantitative monitoring of winter wheat LNC.

LEAF AREA INDEX RETRIEVED FROM THERMAL HYPERSPECTRAL DATA

Abstract. Leaf area index (LAI) is an important essential biodiversity variable due to its role in many terrestrial ecosystem processes such as evapotranspiration, energy balance, and gas exchanges as well as plant growth potential. A novel approach presented here is the retrieval of LAI using thermal infrared (8–14 μm, TIR) measurements. Here, we evaluate LAI retrieval using TIR hyperspectral data. Canopy emissivity spectral measurements were recorded under controlled laboratory conditions using a MIDAC (M4401-F) illuminator Fourier Transform Infrared spectrometer for two plant species during which LAI was destructively measured. The accuracy of retrieval for LAI was then assessed using partial least square regression (PLSR) and narrow band index calculated in the form of normalized difference index from all possible combinations of wavebands. The obtained accuracy from the PLSR for LAI retrieval was relatively higher than narrow-band vegetation index (0.54 &lt; R2 &lt; 0.74). The results demonstrated that LAI may successfully be estimated from hyperspectral thermal data. The study highlights the potential of hyperspectral thermal data for retrieval of vegetation biophysical variables at the canopy level for the first time.