Simulation of EO-1 Hyperion Data from ALI Multispectral Data Based on the Spectral Reconstruction Approach

Data simulation is widely used in remote sensing to produce imagery for a new sensor in the design stage, for scale issues of some special applications, or for testing of novel algorithms. Hyperspectral data could provide more abundant information than traditional multispectral data and thus greatly extend the range of remote sensing applications. Unfortunately, hyperspectral data are much more difficult and expensive to acquire and were not available prior to the development of operational hyperspectral instruments, while large amounts of accumulated multispectral data have been collected around the world over the past several decades. Therefore, it is reasonable to examine means of using these multispectral data to simulate or construct hyperspectral data, especially in situations where hyperspectral data are necessary but hard to acquire. Here, a method based on spectral reconstruction is proposed to simulate hyperspectral data (Hyperion data) from multispectral Advanced Land Imager data (ALI data). This method involves extraction of the inherent information of source data and reassignment to newly simulated data. A total of 106 bands of Hyperion data were simulated from ALI data covering the same area. To evaluate this method, we compare the simulated and original Hyperion data by visual interpretation, statistical comparison, and classification. The results generally showed good performance of this method and indicated that most bands were well simulated, and the information both preserved and presented well. This makes it possible to simulate hyperspectral data from multispectral data for testing the performance of algorithms, extend the use of multispectral data and help the design of a virtual sensor.

Hyperspectral Data and Machine Learning for Estimating CDOM, Chlorophyll a, Diatoms, Green Algae and Turbidity

Inland waters are of great importance for scientists as well as authorities since they are essential ecosystems and well known for their biodiversity. When monitoring their respective water quality, in situ measurements of water quality parameters are spatially limited, costly and time-consuming. In this paper, we propose a combination of hyperspectral data and machine learning methods to estimate and therefore to monitor different parameters for water quality. In contrast to commonly-applied techniques such as band ratios, this approach is data-driven and does not rely on any domain knowledge. We focus on CDOM, chlorophyll a and turbidity as well as the concentrations of the two algae types, diatoms and green algae. In order to investigate the potential of our proposal, we rely on measured data, which we sampled with three different sensors on the river Elbe in Germany from 24 June–12 July 2017. The measurement setup with two probe sensors and a hyperspectral sensor is described in detail. To estimate the five mentioned variables, we present an appropriate regression framework involving ten machine learning models and two preprocessing methods. This allows the regression performance of each model and variable to be evaluated. The best performing model for each variable results in a coefficient of determination R2 in the range of 89.9% to 94.6%. That clearly reveals the potential of the machine learning approaches with hyperspectral data. In further investigations, we focus on the generalization of the regression framework to prepare its application to different types of inland waters.

Heavy Metal Soil Contamination Detection Using Combined Geochemistry and Field Spectroradiometry in the United Kingdom

Technological advances in hyperspectral remote sensing have been widely applied in heavy metal soil contamination studies, as they are able to provide assessments in a rapid and cost-effective way. The present work investigates the potential role of combining field and laboratory spectroradiometry with geochemical data of lead (Pb), zinc (Zn), copper (Cu) and cadmium (Cd) in quantifying and modelling heavy metal soil contamination (HMSC) for a floodplain site located in Wales, United Kingdom. The study objectives were to: (i) collect field- and lab-based spectra from contaminated soils by using ASD FieldSpec^® 3, where the spectrum varies between 350 and 2500 nm; (ii) build field- and lab-based spectral libraries; (iii) conduct geochemical analyses of Pb, Zn, Cu and Cd using atomic absorption spectrometer; (iv) identify the specific spectral regions associated to the modelling of HMSC; and (v) develop and validate heavy metal prediction models (HMPM) for the aforementioned contaminants, by considering their spectral features and concentrations in the soil. Herein, the field- and lab-based spectral features derived from 85 soil samples were used successfully to develop two spectral libraries, which along with the concentrations of Pb, Zn, Cu and Cd were combined to build eight HMPMs using stepwise multiple linear regression. The results showed, for the first time, the feasibility to predict HMSC in a highly contaminated floodplain site by combining soil geochemistry analyses and field spectroradiometry. The generated models help for mapping heavy metal concentrations over a huge area by using space-borne hyperspectral sensors. The results further demonstrated the feasibility of combining geochemistry analyses with filed spectroradiometric data to generate models that can predict heavy metal concentrations.

Modelling plant species distribution in alpine grasslands using airborne imaging spectroscopy

Remote sensing using airborne imaging spectroscopy (AIS) is known to retrieve fundamental optical properties of ecosystems. However, the value of these properties for predicting plant species distribution remains unclear. Here, we assess whether such data can add value to topographic variables for predicting plant distributions in French and Swiss alpine grasslands. We fitted statistical models with high spectral and spatial resolution reflectance data and tested four optical indices sensitive to leaf chlorophyll content, leaf water content and leaf area index. We found moderate added-value of AIS data for predicting alpine plant species distribution. Contrary to expectations, differences between species distribution models (SDMs) were not linked to their local abundance or phylogenetic/functional similarity. Moreover, spectral signatures of species were found to be partly site-specific. We discuss current limits of AIS-based SDMs, highlighting issues of scale and informational content of AIS data.

Mapping Soil Alkalinity and Salinity in Northern Songnen Plain, China with the HJ-1 Hyperspectral Imager Data and Partial Least Squares Regression

In arid and semi-arid regions, identifying and monitoring of soil alkalinity and salinity are in urgently need for preventing land degradation and maintaining ecological balances. In this study, physicochemical, statistical, and spectral analysis revealed that potential of hydrogen (pH) and electrical conductivity (EC) characterized the saline-alkali soils and were sensitive to the visible and near infrared (VIS-NIR) wavelengths. On the basis of soil pH, EC, and spectral data, the partial least squares regression (PLSR) models for estimating soil alkalinity and salinity were constructed. The R² values for soil pH and EC models were 0.77 and 0.48, and the root mean square errors (RMSEs) were 0.95 and 17.92 dS/m, respectively. The ratios of performance to inter-quartile distance (RPIQ) for the soil pH and EC models were 3.84 and 0.14, respectively, indicating that the soil pH model performed well but the soil EC model was not considerably reliable. With the validation dataset, the RMSEs of the two models were 1.06 and 18.92 dS/m. With the PLSR models applied to hyperspectral data acquired from the hyperspectral imager (HSI) onboard the HJ-1A satellite (launched in 2008 by China), the soil alkalinity and salinity distributions were mapped in the study area, and were validated with RMSEs of 1.09 and 17.30 dS/m, respectively. These findings revealed that the hyperspectral images in the VIS-NIR wavelengths had the potential to map soil alkalinity and salinity in the Songnen Plain, China.

Investigating the Utility of Oblique Tree-Based Ensembles for the Classification of Hyperspectral Data

Ensemble classifiers are being widely used for the classification of spectroscopic data. In this regard, the random forest (RF) ensemble has been successfully applied in an array of applications, and has proven to be robust in handling high dimensional data. More recently, several variants of the traditional RF algorithm including rotation forest (rotF) and oblique random forest (oRF) have been applied to classifying high dimensional data. In this study we compare the traditional RF, rotF, and oRF (using three different splitting rules, i.e., ridge regression, partial least squares, and support vector machine) for the classification of healthy and infected Pinus radiata seedlings using high dimensional spectroscopic data. We further test the robustness of these five ensemble classifiers to reduced spectral resolution by spectral resampling (binning) of the original spectral bands. The results showed that the three oblique random forest ensembles outperformed both the traditional RF and rotF ensembles. Additionally, the rotF ensemble proved to be the least robust of the five ensembles tested. Spectral resampling of the original bands provided mixed results. Nevertheless, the results demonstrate that using spectral resampled bands is a promising approach to classifying asymptomatic stress in Pinus radiata seedlings.

[The use of Specim IQ, a hyperspectral camera, for plant analysis]

Важной технологией для неразрушающего мониторинга пигментного состава растений, который тесно связан с их физиологическим состоянием или заражением патогенами, является дистанционное зондирование при помощи гиперспектральных камер. В работе представлен опыт применения мобильной гиперспектральной камеры Specim IQ для исследований заболевания проростков четырех сортов пшеницы обыкновенной корневой гнилью (возбудитель – гриб Bipolaris sorokiniana Shoem.), а также для анализа мякоти клубней картофеля 82 линий и сортов. Для проростков были получены спектральные характеристики и по данным определены наиболее информативные спектральные признаки (индексы) для обнаружения корневой гнили. У проростков контрольных вариантов в видимой части спектра наблюдается возрастание отражательной способности с небольшим пиком в зеленой области (около 550 нм), затем идет понижение из-за поглощения света пигментами растений с экстремумом при длине волны около 680 нм. Анализ гистограмм значений вегетационных индексов показал, что индексы TVI и MCARI наиболее информативны для обнаружения патогена на проростках пшеницы по данным гиперспектральной съемки. Для образцов картофеля были выявлены участки спектра, соответствующие локальным максимумам и минимумам отражения. Показано, что спектры сортов картофеля имеют наибольшие различия в области длин волн 900–1000, 400–450 нм, что в первом случае может быть связано с уровнем содержания воды, а во втором – с формированием в клубнях меланина. По характеристикам спектра исследованные образцы разделились на три группы, каждая из которых содержит повышенные либо пониженные уровни интенсивности для указанных участков спектра. Кроме того, для ряда сортов были установлены минимумы в спектрах отражения, соответствующих хлорофиллу a. Результаты демонстрируют возможности камеры Specim IQ для проведения исследований гиперспектрального анализа растительных объектов.

Data Field Modeling and Spectral-Spatial Feature Fusion for Hyperspectral Data Classification

Classification is a significant subject in hyperspectral remote sensing image processing. This study proposes a spectral-spatial feature fusion algorithm for the classification of hyperspectral images (HSI). Unlike existing spectral-spatial classification methods, the influences and interactions of the surroundings on each measured pixel were taken into consideration in this paper. Data field theory was employed as the mathematical realization of the field theory concept in physics, and both the spectral and spatial domains of HSI were considered as data fields. Therefore, the inherent dependency of interacting pixels was modeled. Using data field modeling, spatial and spectral features were transformed into a unified radiation form and further fused into a new feature by using a linear model. In contrast to the current spectral-spatial classification methods, which usually simply stack spectral and spatial features together, the proposed method builds the inner connection between the spectral and spatial features, and explores the hidden information that contributed to classification. Therefore, new information is included for classification. The final classification result was obtained using a random forest (RF) classifier. The proposed method was tested with the University of Pavia and Indian Pines, two well-known standard hyperspectral datasets. The experimental results demonstrate that the proposed method has higher classification accuracies than those obtained by the traditional approaches.

Comparison of PRISMA Data with Model Simulations, Hyperion Reflectance and Field Spectrometer Measurements on 'Piano delle Concazze' (Mt. Etna, Italy)

In this work, we compare first acquisitions from the ASI-PRISMA (Agenzia Spaziale Italiana-PRecursore IperSpettrale della Missione Applicativa) space mission with model simulations, past data acquired by the Hyperion sensor and field spectrometer measurements. The test site is ‘Piano delle Concazze’ (Mt. Etna, Italy), suitable for calibration purposes due to its homogeneity characteristics. The area measures at about 0.2 km² and is composed of very homogeneous trachybasalt rich in plagioclase and olivine. Three PRISMA acquisitions, achieved on 31 July and 8 and 17 August 2019, are analyzed. Firstly, spectral profiles of PRISMA top of atmosphere (TOA) radiance are compared with MODerate resolution atmospheric TRANsmission (MODTRAN) simulations. The Pearson correlation coefficient is equal to 0.998 and 0.994 for VNIR (Visible and Near InfraRed) and SWIR (Short-Wave InfraRed) spectral ranges, respectively. PRISMA radiance overestimates values simulated by MODTRAN for all considered days, showing a mean bias of +5.22 and of +0.91 Wm⁻²sr⁻¹µm⁻¹ for VNIR and SWIR, respectively. The relative mean difference between reflectance values estimated by PRISMA and Hyperion, on the test area, is around +19%, despite the great difference in time acquisition (up to 19 years); PRISMA slightly overestimates Hyperion reflectance with an absolute mean difference of about +0.0083, within the variability of Hyperion acquisitions of ±0.0250 (corresponding to ±2 standard deviation). Finally, FieldSpec measurements also confirm the great quality of PRISMA reflectance estimations. The absolute mean difference results are around +0.0089 (corresponding to a relative error of about +21%). In the study, we investigate only the lower values of reflectance characterizing the test site. A more complete evaluation of PRISMA performances needs to consider other test sites with different optical characteristics.

[The inversion of nitrogen balance index in typical growth period of soybean based on high definition digital image and hyperspectral data on unmanned aerial vehicles]

Nitrogen balance index (NBI) is one of the important indicators for crop growth. The high and low status of nitrogen can be quickly monitored by measuring NBI, which can provide accurate information of agricultural production and management. The relationship between NBI and original spectrum and derivative spectrum of infrared and near infrared wavelength from flowering to maturity stage was analyzed based on high definition digital image and hyperspectral data on unmanned aerial vehicles. Then, the sensitive bands were selected and the vegetation indexes were calculated. The inversion models of NBI were constructed by empirical model method. The optimal inversion model was obtained by analysing the determination coefficient (R2) and the root mean square error (RMSE) of validating model. The results showed that the correlation between NBI and derivative spectral reflectance was more stronger than that between it and original spectral reflectance. All the 14 vegetation indices selected in this study, except the derivative spectral photochemical reflectance index, had significant correlation with NBI. The NBI inversion models were constructed based on those 13 vegetation indices and the accuracy was analyzed. The inversion model constructed by derivative spectral difference vegetation index had the highest accuracy, with the R2 and RMSE being 0.771 and 3.077 respectively. The soybean NBI distribution maps of the whole growing stages generated by this model could reflect the soybean growth state. Estimation of NBI using the high definition digital image and hyperspectral data obtained by unmanned aerial vehicle, as shown by our results, could be a real-time, dynamic, non-destructive and effective way to monitor the nitrogen status of soybean. It's a simple and practical method for precise management of nitrogen in soybean.

Spatially Coherent Clustering Based on Orthogonal Nonnegative Matrix Factorization

Classical approaches in cluster analysis are typically based on a feature space analysis. However, many applications lead to datasets with additional spatial information and a ground truth with spatially coherent classes, which will not necessarily be reconstructed well by standard clustering methods. Motivated by applications in hyperspectral imaging, we introduce in this work clustering models based on Orthogonal Nonnegative Matrix Factorization (ONMF), which include an additional Total Variation (TV) regularization procedure on the cluster membership matrix to enforce the needed spatial coherence in the clusters. We propose several approaches with different optimization techniques, where the TV regularization is either performed as a subsequent post-processing step or included into the clustering algorithm. Finally, we provide a numerical evaluation of 12 different TV regularized ONMF methods on a hyperspectral dataset obtained from a matrix-assisted laser desorption/ionization imaging measurement, which leads to significantly better clustering results compared to classical clustering models.

Estimation of amino acid contents in maize leaves based on hyperspectral imaging

Estimation of the amino acid content in maize leaves is helpful for improving maize yield estimation and nitrogen use efficiency. Hyperspectral imaging can be used to obtain the physiological and biochemical parameters of maize leaves with the advantages of being rapid, non-destructive, and high throughput. This study aims to estimate the multiple amino acid contents in maize leaves using hyperspectral imaging data. Two nitrogen (N) fertilizer experiments were carried out to obtain the hyperspectral images of fresh maize leaves. The partial least squares regression (PLSR) method was used to build the estimation models of various amino acid contents by using the reflectance of all bands, sensitive band range, and sensitive bands. The models were then validated with the independent dataset. The results showed that (1) the spectral reflectance of most amino acids was more sensitive in the range of 400-717.08 nm than other bands. The estimation accuracy was better by using the reflectance of the sensitive band range than that of all bands; (2) the sensitive bands of most amino acids were in the ranges of 505.39-605 nm and 651-714 nm; and (3) among the 24 amino acids, the estimation models of the β-aminobutyric acid, ornithine, citrulline, methionine, and histidine achieved higher accuracy than those of other amino acids, with the R ², relative root mean square error (RE), and relative percent deviation (RPD) of the measured and estimated value of testing samples in the range of 0.84-0.96, 8.79%-19.77%, and 2.58-5.18, respectively. This study can provide a non-destructive and rapid diagnostic method for genetic sensitive analysis and variety improvement of maize.

Detection of the stem-boring damage by pine shoot beetle (Tomicus spp.) to Yunan pine (Pinus yunnanensis Franch.) using UAV hyperspectral data

Introduction

The stem-boring damage caused by pine shoot beetle (PSB, Tomicus spp.) cuts off the transmission of water and nutrients. The aggregation of beetles during the stem-boring stage results in the rapid mortality of Yunnan pines (Pinus yunnanensis Franch.). Timely identification and precise localization of stem-boring damage caused by PSB are crucial for removing infected wood and preventing further spread of the infestation. Unmanned airborne vehicle (UAV) hyperspectral data demonstrate great potential in assessing pest outbreaks in forested landscapes. However, there is a lack of studies investigating the application and accuracy of UAV hyperspectral data for detecting PSB stem-boring damage.

Methods

In this study, we compared the differences in spectral features of healthy pines (H level), three levels of shoot-feeding damage (E, M and S levels), and the stem-boring damage (T level), and then used the Random Forest (RF) algorithm for detecting stem-boring damage by PSB.

Results

The specific canopy spectral features, including red edge (such as Dr, SDr, and D711), blue edge (such as Db and SDb), and chlorophyll-related spectral indices (e.g., MCARI) were sensitive to PSB stem-boring damage. The results of RF models showed that the spectral features of first-order derivative (FD) and spectral indices (SIs) played an important role in the PSB stem-boring damage detection. Models incorporating FD bands, SIs and a combination of all variables proved more effective in detecting PSB stem-boring damage.

Discussion

These findings demonstrate the potential of canopy spectral features in detecting PSB stem-boring damage, which significantly contributed to the prevention and management of PSB infestations.

Deep learning-enabled exploration of global spectral features for photosynthetic capacity estimation

Spectral analysis is a widely used method for monitoring photosynthetic capacity. However, vegetation indices-based linear regression exhibits insufficient utilization of spectral information, while full spectra-based traditional machine learning has limited representational capacity (partial least squares regression) or uninterpretable (convolution). In this study, we proposed a deep learning model with enhanced interpretability based on attention and vegetation indices calculation for global spectral feature mining to accurately estimate photosynthetic capacity. We explored the ability of the model to uncover the optimal vegetation indices form and illustrated its advantage over traditional methods. Furthermore, we verified that power compression was an effective method for spectral processing. Our results demonstrated that the new model outperformed traditional models, with an increase in the coefficient of determination (R2) of 0.01-0.43 and a decrease in root mean square error (RMSE) of 1.58-12.48 μmol m-2 s-1. The best performance of our model in R2 was 0.86 and 0.81 for maximum carboxylation rate (Vcmax ) and maximum electron transport rate (Jmax ), respectively. The photosynthesis-sensitive spectral bands identified by our model were predominantly in the visible range. The most sensitive vegetation indices form discovered by our model wasR e f l e c t a n c e n e a r - i n f r a r e d + R e f l e c t a n c e g r e e n / b l u e R e f l e c t a n c e n e a r - i n f r a r e d × R e f l e c t a n c e r e d . Our model provides a new framework for interpreting spectral information and accurately estimating photosynthetic capacity.

Auditory Display of Fluorescence Image Data in an In Vivo Tumor Model

Objectives: This research aims to apply an auditory display for tumor imaging using fluorescence data, discuss its feasibility for in vivo tumor evaluation, and check its potential for assisting enhanced cancer perception. Methods: Xenografted mice underwent fluorescence imaging after an injection of cy5.5-glucose. Spectral information from the raw data was parametrized to emphasize the near-infrared fluorescence information, and the resulting parameters were mapped to control a sound synthesis engine in order to provide the auditory display. Drag−click maneuvers using in-house data navigation software-generated sound from regions of interest (ROIs) in vivo. Results: Four different representations of the auditory display were acquired per ROI: (1) audio spectrum, (2) waveform, (3) numerical signal-to-noise ratio (SNR), and (4) sound itself. SNRs were compared for statistical analysis. Compared with the no-tumor area, the tumor area produced sounds with a heterogeneous spectrum and waveform, and featured a higher SNR as well (3.63 ± 8.41 vs. 0.42 ± 0.085, p < 0.05). Sound from the tumor was perceived by the naked ear as high-timbred and unpleasant. Conclusions: By accentuating the specific tumor spectrum, auditory display of fluorescence imaging data can generate sound which helps the listener to detect and discriminate small tumorous conditions in living animals. Despite some practical limitations, it can aid in the translation of fluorescent images by facilitating information transfer to the clinician in in vivo tumor imaging.

Water content estimation of conifer needles using leaf-level hyperspectral data

Water is a crucial component for plant growth and survival. Accurately estimating and simulating plant water content can help us promptly monitor the physiological status and stress response of vegetation. In this study, we constructed water loss curves for three types of conifers with morphologically different needles, then evaluated the applicability of 12 commonly used water indices, and finally explored leaf water content estimation from hyperspectral data for needles with various morphology. The results showed that the rate of water loss of Olgan larch is approximately 8 times higher than that of Chinese fir pine and 21 times that of Korean pine. The reflectance changes were most significant in the near infrared region (NIR, 780-1300 nm) and the short-wave infrared region (SWIR, 1300-2500 nm). The water sensitive bands for conifer needles were mainly concentrated in the SWIR region. The water indices were suitable for estimating the water content of a single type of conifer needles. The partial least squares regression (PLSR) model is effective for the water content estimation of all three morphologies of conifer needles, demonstrating that the hyperspectral PLSR model is a promising tool for estimating needles water content.

Spectral Similarity Measures for In Vivo Human Tissue Discrimination Based on Hyperspectral Imaging

PROBLEM

Similarity measures are widely used as an approved method for spectral discrimination or identification with their applications in different areas of scientific research. Even though a range of works have been presented, only a few showed slightly promising results for human tissue, and these were mostly focused on pathological and non-pathological tissue classification.

METHODS

In this work, several spectral similarity measures on hyperspectral (HS) images of in vivo human tissue were evaluated for tissue discrimination purposes. Moreover, we introduced two new hybrid spectral measures, called SID-JM-TAN(SAM) and SID-JM-TAN(SCA). We analyzed spectral signatures obtained from 13 different human tissue types and two different materials (gauze, instruments), collected from HS images of 100 patients during surgeries.

RESULTS

The quantitative results showed the reliable performance of the different similarity measures and the proposed hybrid measures for tissue discrimination purposes. The latter produced higher discrimination values, up to 6.7 times more than the classical spectral similarity measures. Moreover, an application of the similarity measures was presented to support the annotations of the HS images. We showed that the automatic checking of tissue-annotated thyroid and colon tissues was successful in 73% and 60% of the total spectra, respectively. The hybrid measures showed the highest performance. Furthermore, the automatic labeling of wrongly annotated tissues was similar for all measures, with an accuracy of up to 90%.

CONCLUSION

In future work, the proposed spectral similarity measures will be integrated with tools to support physicians in annotations and tissue labeling of HS images.

Hyperspectral estimation of chlorophyll content in jujube leaves: integration of derivative processing techniques and dimensionality reduction algorithms

The leaf chlorophyll content (LCC) of vegetation is closely related to photosynthetic efficiency and biological activity. Jujube (Ziziphus jujuba Mill.) is a traditional economic forest tree species. Non-destructive monitoring of LCC of jujube is of great significance for guiding agroforestry production and promoting ecological environment protection in arid and semi-arid lands. Hyperspectral data is an important data source for LCC detection. However, hyperspectral data consists of a multitude of bands and contains extensive information. As a result, certain bands may exhibit high correlation, leading to redundant spectral information. This redundancy can distort LCC prediction results and reduce accuracy. Therefore, it is crucial to select appropriate preprocessing methods and employ effective data mining techniques when analyzing hyperspectral data. This study aims to evaluate the performance of hyperspectral data for estimating LCC of jujube trees by integrating different derivative processing techniques with different dimensionality reduction algorithms. Hyperspectral reflectance data were obtained through simulations using an invertible forest reflectance model (INFORM) and measurements from jujube tree canopies. The least absolute shrinkage and selection operator (LASSO) and elastic net (EN) were employed to identify the important bands in the original spectra (OS), first derivative spectra (FD), and second derivative spectra (SD). Support vector regression (SVR) was used to establish the estimation model. The results show that compared with full-spectrum modeling, LASSO and EN algorithms are effective methods for preventing overfitting in LCC machine learning estimation models for different spectral derivatives. The LASSO/EN-based estimation models constructed using FD and SD exhibited superior R2 compared to the OS. The important band of SD can best reveal the relevant information of jujube LCC, and SD-EN-SVR is the most ideal model in both the simulated dataset (R2 = 0.99, RMSE=0.61) and measured dataset (R2 = 0.89, RMSE=0.91). Our results provided a reference for rapid and non-destructive estimation of the LCC of agroforestry vegetation using canopy hyperspectral data.

Estimation of the rice aboveground biomass based on the first derivative spectrum and Boruta algorithm

Aboveground biomass (AGB) is regarded as a critical variable in monitoring crop growth and yield. The use of hyperspectral remote sensing has emerged as a viable method for the rapid and precise monitoring of AGB. Due to the extensive dimensionality and volume of hyperspectral data, it is crucial to effectively reduce data dimensionality and select sensitive spectral features to enhance the accuracy of rice AGB estimation models. At present, derivative transform and feature selection algorithms have become important means to solve this problem. However, few studies have systematically evaluated the impact of derivative spectrum combined with feature selection algorithm on rice AGB estimation. To this end, at the Xiaogang Village (Chuzhou City, China) Experimental Base in 2020, this study used an ASD FieldSpec handheld 2 ground spectrometer (Analytical Spectroscopy Devices, Boulder, Colorado, USA) to obtain canopy spectral data at the critical growth stage (tillering, jointing, booting, heading, and maturity stages) of rice, and evaluated the performance of the recursive feature elimination (RFE) and Boruta feature selection algorithm through partial least squares regression (PLSR), principal component regression (PCR), support vector machine (SVM) and ridge regression (RR). Moreover, we analyzed the importance of the optimal derivative spectrum. The findings indicate that (1) as the growth stage progresses, the correlation between rice canopy spectrum and AGB shows a trend from high to low, among which the first derivative spectrum (FD) has the strongest correlation with AGB. (2) The number of feature bands selected by the Boruta algorithm is 19~35, which has a good dimensionality reduction effect. (3) The combination of FD-Boruta-PCR (FB-PCR) demonstrated the best performance in estimating rice AGB, with an increase in R² of approximately 10% ~ 20% and a decrease in RMSE of approximately 0.08% ~ 14%. (4) The best estimation stage is the booting stage, with R2 values between 0.60 and 0.74 and RMSE values between 1288.23 and 1554.82 kg/hm2. This study confirms the accuracy of hyperspectral remote sensing in estimating vegetation biomass and further explores the theoretical foundation and future direction for monitoring rice growth dynamics.

Small Sample Hyperspectral Image Classification Based on the Random Patches Network and Recursive Filtering

In recent years, different deep learning frameworks were introduced for hyperspectral image (HSI) classification. However, the proposed network models have a higher model complexity, and do not provide high classification accuracy if few-shot learning is used. This paper presents an HSI classification method that combines random patches network (RPNet) and recursive filtering (RF) to obtain informative deep features. The proposed method first convolves image bands with random patches to extract multi-level deep RPNet features. Thereafter, the RPNet feature set is subjected to dimension reduction through principal component analysis (PCA), and the extracted components are filtered using the RF procedure. Finally, the HSI spectral features and the obtained RPNet-RF features are combined to classify the HSI using a support vector machine (SVM) classifier. In order to test the performance of the proposed RPNet-RF method, some experiments were performed on three widely known datasets using a few training samples for each class, and classification results were compared with those obtained by other advanced HSI classification methods adopted for small training samples. The comparison showed that the RPNet-RF classification is characterized by higher values of such evaluation metrics as overall accuracy and Kappa coefficient.