Hyperspectral Data Research Articles

Learning Unified Anchor Graph for Joint Clustering of Hyperspectral and LiDAR Data.

The joint clustering of multimodal remote sensing (RS) data poses a critical and challenging task in Earth observation. Although recent advances in multiview subspace clustering have shown remarkable success, existing methods become computationally prohibitive when dealing with large-scale RS datasets. Moreover, they neglect intrinsic nonlinear and spatial interdependencies among heterogeneous RS data and lack generalization ability for out-of-sample data, thereby restricting their applicability. This article introduces a novel unified framework called anchor-based multiview kernel subspace clustering with spatial regularization (AMKSC). It learns a scalable anchor graph in the kernel space, leveraging contributions from each modality instead of seeking a consensus full graph in the feature space. To ensure spatial consistency, we incorporate a spatial smoothing operation into the formulation. The method is efficiently solved using an alternating optimization strategy, and we provide theoretical evidence of its scalability with linear computational complexity. Furthermore, an out-of-sample extension of AMKSC based on multiview collaborative representation-based classification is introduced, enabling the handling of larger datasets and unseen instances. Extensive experiments on three real heterogeneous RS datasets confirm the superiority of our proposed approach over state-of-the-art methods in terms of clustering performance and time efficiency. The source code is available at https://github.com/AngryCai/AMKSC.

Early Detection of Rubber Tree Powdery Mildew by Combining Spectral and Physicochemical Parameter Features

Powdery mildew significantly impacts the yield of natural rubber by being one of the predominant diseases that affect rubber trees. Accurate, non-destructive recognition of powdery mildew in the early stage is essential for the cultivation management of rubber trees. The objective of this study is to establish a technique for the early detection of powdery mildew in rubber trees by combining spectral and physicochemical parameter features. At three field experiment sites and in the laboratory, a spectroradiometer and a hand-held optical leaf-clip meter were utilized, respectively, to measure the hyperspectral reflectance data (350–2500 nm) and physicochemical parameter data of both healthy and early-stage powdery-mildew-infected leaves. Initially, vegetation indices were extracted from hyperspectral reflectance data, and wavelet energy coefficients were obtained through continuous wavelet transform (CWT). Subsequently, significant vegetation indices (VIs) were selected using the ReliefF algorithm, and the optimal wavelengths (OWs) were chosen via competitive adaptive reweighted sampling. Principal component analysis was used for the dimensionality reduction of significant wavelet energy coefficients, resulting in wavelet features (WFs). To evaluate the detection capability of the aforementioned features, the three spectral features extracted above, along with their combinations with physicochemical parameter features (PFs) (VIs + PFs, OWs + PFs, WFs + PFs), were used to construct six classes of features. In turn, these features were input into support vector machine (SVM), random forest (RF), and logistic regression (LR), respectively, to build early detection models for powdery mildew in rubber trees. The results revealed that models based on WFs perform well, markedly outperforming those constructed using VIs and OWs as inputs. Moreover, models incorporating combined features surpass those relying on single features, with an overall accuracy (OA) improvement of over 1.9% and an increase in F1-Score of over 0.012. The model that combines WFs and PFs shows superior performance over all the other models, achieving OAs of 94.3%, 90.6%, and 93.4%, and F1-Scores of 0.952, 0.917, and 0.941 on SVM, RF, and LR, respectively. Compared to using WFs alone, the OAs improved by 1.9%, 2.8%, and 1.9%, and the F1-Scores increased by 0.017, 0.017, and 0.016, respectively. This study showcases the viability of early detection of powdery mildew in rubber trees.

Mapping Foliar C, N, and P Concentrations in An Ecological Restoration Area with Mixed Plant Communities Based on LiDAR and Hyperspectral Data

Interactions between carbon (C), nitrogen (N), and phosphorus (P), the vital indicators of ecological restoration, play an important role in signaling the health of ecosystems. Rapidly and accurately mapping foliar C, N, and P is essential for interpreting community structure, nutrient limitation, and primary production during ecosystem recovery. However, research on how to rapidly map C, N, and P in restored areas with mixed plant communities is limited. This study employed laser imaging, detection, and ranging (LiDAR) and hyperspectral data to extract spectral, textural, and height features of vegetation as well as vegetation indices and structural parameters. Causal band, multiple linear regression, and random forest models were developed and tested in a restored area in northern China. Important parameters were identified including (1), for C, red-edge bands, canopy height, and vegetation structure; for N, textural features, height percentile of 40–95%, and vegetation structure; for P, spectral features, height percentile of 80%, and 1 m foliage height diversity. (2) R2 was used to compare the accuracy of the three models as follows: R2 values for C were 0.07, 0.42, and 0.56, for N they were 0.20, 0.48, and 0.53, and for P they were 0.32, 0.39, and 0.44; the random forest model demonstrated the highest accuracy. (3) The accuracy of the concentration estimates could be ranked as C > N > P. (4) The inclusion of LiDAR features significantly improved the accuracy of the C concentration estimation, with increases of 22.20% and 47.30% in the multiple linear regression and random forest models, respectively, although the inclusion of LiDAR features did not notably enhance the accuracy of the N and P concentration estimates. Therefore, LiDAR and hyperspectral data can be used to effectively map C, N, and P concentrations in a mixed plant community in a restored area, revealing their heterogeneity in terms of species and spatial distribution. Future efforts should involve the use of hyperspectral data with additional bands and a more detailed classification of plant communities. The application of this information will be useful for analyzing C, N, and P limitations, and for planning for the maintenance of restored plant communities.

Mud Spectral Characteristics from the Lusi Eruption, East Java, Indonesia Using Satellite Hyperspectral Data

Imaging spectroscopy allows us to identify surface materials by analyzing the spectra resulting from the light–material interaction. In this preliminary study, we analyze a pair of hyperspectral cubes acquired by PRISMA (on 20 April 2021) and EO1- Hyperion (on 4 July 2015) over the Indonesian Lusi mud eruption. We show the potential suitability of using the two sensors for characterizing the mineralogical features in demanding “wet and muddy” environments such as Lusi. We use spectral library reflectance spectra like Illite Chlorite from the USGS spectral library, which are known to be associated with Lusi volcanic products, to identify minerals. In addition, we have measured the reflectance spectra and composition of Lusi sampled mud collected in November 2014. Finally, we compare them with reflectance spectra from EO1-Hyperion and PRISMA. The use of hyperspectral sensors at improved SNR, such as PRISMA, has shown the potential to determine the mineral composition of Lusi PRISMA data, which allowed the distinction of areas with different turbidities as well. Artifacts in the VNIR spectral region of the L2 PRISMA reflectance product were found, suggesting that future work needs to take into account an independent atmospheric correction rather than using the L2D PRISMA product.

Characterizing Stalagmite Composition using Hyperspectral Imaging

Stalagmites offer nearly continuous records of past climate in continental settings at high temporal resolution. The climatic records preserved in stalagmites are commonly investigated by examining compositional characteristics such as mineralogy, organic content, and lamination patterns. These proxies provide valuable insights into the environmental conditions during stalagmite formation. However, the methods used to obtain information about these proxies are relatively destructive. This study uses hyperspectral imaging, a non-contact technique, to identify mineral composition, organic matter content, and laminations in stalagmite. It is the first wide spectrum imaging analysis in speleothem research, using both visible–near infrared and shortwave infrared wavelengths. Results obtained from hyperspectral imaging were compared by point spectral analysis using an ASD spectroradiometer and a grayscale profile along the growth axis of the stalagmite. Petrographic observation of thin sections and X-ray diffraction (XRD) analyses on selected stalagmite layers were performed to cross-validate the hyperspectral data. A travertine sample was also used to replicate the method on calcite. To automate mineral identification, a machine learning algorithm was developed to map spatial distribution and quantify relative proportions of minerals across the sample. Our findings are in good agreement with traditionally used methods of mineral identification, i.e. XRD and petrography, aiding in the interpretation of paleoclimate proxies, and offer a spatial guide for UTh dating analyses. It also provides insight for future investigations of stalagmite using hyperspectral data and classification through machine learning algorithms.

Rapid determination of residual pefloxacin in mutton based on hyperspectral imaging and data fusion

Non-destructive detection of veterinary drug residues in meat products is critical for ensuring food safety and human health. The feasibility of using visible near-infrared (Vis-NIR) and near-infrared (NIR) hyperspectral imaging (HSI) system combined with data fusion for the prediction of pefloxacin residues in mutton was investigated in this study. A partial least squares regression optimization (PLSR) model was developed by multivariate data processing methods. The results showed that the low-level fusion (LLF) produced better results with R2P = 0.907 and root mean square error of prediction (RMSEP) = 0.462 as compared to individual data blocks. Furthermore, intermediate-level fusion (ILF) based on iterative retention of informative variables (IRIV) algorithm showed the best results with R2P = 0.940 and RMSEP = 0.375. Finally, the visualized distributions of Vis-NIR and NIR based on the optimal model combination were mapped. The results have demonstrated that a combination of HSI with data fusion may be applied to rapidly and non-destructively detect pefloxacin residues in mutton.

Detection of sweet corn seed viability based on hyperspectral imaging combined with firefly algorithm optimized deep learning

Detection of sweet corn seed viability based on hyperspectral imaging combined with firefly algorithm optimized deep learning

Exploring the Performance of Linear and Nonlinear Models of Time-of-Flight Secondary Ion Mass Spectrometry Spectra.

Multivariate statistical tools and machine learning (ML) techniques can deconvolute hyperspectral data and control the disparity between the number of samples and features in materials science. Nevertheless, the importance of generating sufficient high-quality sample replicates in training data cannot be overlooked, as it fundamentally affects the performance of ML models. Here, we present a quantitative analysis of time-of-flight secondary ion mass spectrometry (ToF-SIMS) spectra of a simple microarray system of two food dyes using partial least-squares (PLS, linear) and random forest (RF, nonlinear) algorithms. This microarray was generated by a high-throughput sample preparation and analysis workflow for fast and efficient acquisition of quality and reproducible spectra via ToF-SIMS. We drew insights from the bias-variance trade-off, investigated the performances of PLS and RF regression models as a function of training data size, and inferred the amount of data needed to construct accurate and reliable regression models. In addition, we found that the spectral concatenation of positive and negative ToF-SIMS spectra improved the model performances. This study provides an empirical basis for future design of high-throughput microarrays and multicomponent systems, for the purpose of analysis with ToF-SIMS and ML.

3U CubeSat-Based Hyperspectral Remote Sensing by Offner Imaging Hyperspectrometer with Radially-Fastened Primary Elements

This paper presents findings from a spaceborne Earth observation experiment utilizing a novel, ultra-compact hyperspectral imaging camera aboard a 3U CubeSat. Leveraging the Offner optical scheme, the camera’s hyperspectrometer captures hyperspectral images of terrestrial regions with a 200 m spatial resolution and 12 nanometer spectral resolution across a 400 to 1000 nanometer wavelength range, covering 150 channels in the visible and near-infrared spectrums. The hyperspectrometer is specifically designed for deployment on a 3U CubeSat nanosatellite platform, featuring a robust all-metal cylindrical body of the hyperspectrometer, and a coaxial arrangement of the optical elements ensures optimal compactness and vibration stability. The performance of the imaging hyperspectrometer was rigorously evaluated through numerical simulations prior to construction. Analysis of hyperspectral data acquired over a year-long orbital operation demonstrates the 3U CubeSat’s ability to produce various vegetation indices, including the normalized difference vegetation index (NDVI). A comparative study with the European Space Agency’s Sentinel-2 L2A data shows a strong agreement at critical points, confirming the 3U CubeSat’s suitability for hyperspectral imaging in the visible and near-infrared spectrums. Notably, the ISOI 3U CubeSat can generate unique index images beyond the reach of Sentinel-2 L2A, underscoring its potential for advancing remote sensing applications.

Comparison between Hyperspectral and Multispectral Retrievals of Suspended Sediment Concentration in Rivers

Remote sensing (RS) is often employed to estimate suspended sediment concentration (SSC) in rivers, and the availability of hyperspectral imagery enhances the effectiveness of RS-based water quality monitoring due to its high spectral resolution. Yet, the necessity of hyperspectral imagery for SSC estimation in rivers has not been fully validated. This study thus compares the performance of hyperspectral RS with that of multispectral RS by conducting field-scale experiments in shallow rivers. In the field experiments, we measured radiance from a water body mixed with suspended sediments using a drone-mounted hyperspectral sensor, with the sediment and riverbed types considered as controlling factors. We retrieved the SSC from UAV imagery using an optimal band ratio analysis, which successfully estimated SSC distributions in the sand bed conditions with both multispectral and hyperspectral data. In the vegetated bed conditions, meanwhile, the prediction accuracy decreased significantly due to the temporally varying bottom reflectance associated with the random movement of vegetation caused by near-bed turbulence. This is because temporally inhomogeneous bottom reflectance distorts the relationship between the SSC and total reflectance. Nevertheless, the hyperspectral imaging exhibited better prediction accuracy than the multispectral imaging, effectively extracting optimal spectral bands sensitive to back-scattered reflectance from sediments while constraining the bottom reflectance caused by the vegetation-covered bed.

Utilising LANDHYPERNET data products over a deciduous broadleaf forest to validate Sentinel-2 and Landsat surface reflectance products

This paper demonstrates the use of a novel, autonomous hyperspectral surface reflectance data collected at Wytham Woods, United Kingdom (WWUK) as part of the LANDHYPERNET network for the validation of multispectral data from Sentinel-2, Landsat 8 and Landsat 9. The deployment of the HYPSTAR instrument at the site and the corresponding quality control of the data products is described. In addition, a methodology based upon metrological principles is outlined showing the propagation of uncertainties from the LANDHYPERNET and satellite data products to enable conformity testing of the satellite products using the satellite mission requirements. A total of 9 matchups are found for satellite validation at the site, where there is a cloud-free satellite scene and a corresponding LANDHYPERNET sequence, which has passed all quality checks, within two hours of the overpass. An analysis of the impact of the spatial variability of the site is presented and can account for up to 40% of the uncertainty associated with the in-situ surface reflectance data. There is no systematic bias in the Bottom-Of-Atmosphere reflectance data obtained from the LANDHYPERNET data in comparison to the satellite data. In the best case, differences of less than 2% are found for certain spectral bands. However, in the worst cases, relatively large differences are found which exceed 100%, this is affected by the relatively low reflectance values found in the visible bands. These differences could be caused by the spatial and temporal mismatch between the in-situ and satellite measurement, or due to shadowing caused by the flux tower. Further data quality control and assurance is needed to best choose data sets suitable for satellite validation. Incorporating a Bidirectional Reflectance Distribution Function model into the processing chain for the forest canopy is recommended. Overall, although there are areas to further characterise, the site provides a useful benchmark for which to develop techniques for validation of satellite surface reflectance products over a challenging environment.

Inversion of coastal cultivated soil salt content based on multi-source spectra and environmental variables

Soil salinization seriously hinders the development of efficient ecological agriculture in coastal areas. The use of Landsat, Sentinel series and hyperspectral data is an ideal way for assessing soil salinity indicators. However, environmental data (e.g. climate, terrain and parent material) are important factors for estimating such indicators. It is necessary to find the advantages and limitations of a combination of satellite images, hyperspectral data and environmental variables (ENVI) for assessing soil salinity accurately. Various data or their combinations ([I] remote sensing [RS], i.e. bands and salinity indices of Landsat 9 and Sentinel 2; [II] ENVI, including soil attributes, climate and topography; and [III] RS + ENVI) were used to construct the salinity inversion model using random forest (RF) and extremely randomized trees (ERT) for cultivated areas in the coastal plain of Dongtai City, China. The hyperspectral data were also resampled to match the range of the image bands. RF performed better than ERT for all types of analyzed data, and RS + ENVI exhibited the best performance for Sentinel 2 (R2 = 0.86). Compared with the RS data alone, Landsat 9 and Sentinel 2 provided higher salinity simulations (41% and 126%, respectively) after combination with ENVI, and salinity mapping was closer to the actual soil salinity measurements. The variables of slope, salinity index (SIT), difference index and SIT had the highest contribution in Landsat 9, Sentinel 2 and resampled hyperspectrum based on Landsat 9 and Sentinel 2, respectively. In conclusion, RS + ENVI based on Sentinel 2 data is the recommended approach for monitoring the salt content of coastal cultivated soil.

Unlocking Patterns in Hyperspectral Data: Reinforcement Learning Approach with Binary Entropy for Image Classification

This work presents a new method for classifying hyperspectral images that combines the binary entropy technique with a Reinforcement Learning (RL) based approach. With their abundance of spectral information, hyperspectral images are an invaluable tool for remote sensing applications. The difficulty, though, is in accurately categorizing each pixel in these pictures into binary classes, like different kinds of land cover. To tackle this problem, our strategy formulates it as a Reinforcement Learning task in which an agent must learn how to determine the best thresholds for the binary entropy method. Through a reward function that promotes accurate classifications, the agent receives feedback. After preprocessing the hyperspectral data, we deploy the RL agent for real-time image classification after training and validating it. Our approach shows potential for automating thresholding and improving classification.

On the impact of soil texture on local scale organic carbon quantification: From airborne to spaceborne sensing domains

Soil organic carbon (SOC) distribution and interaction with light is influenced by soil texture parameters (clay, silt and sand), which makes SOC prediction complicated, especially in samples with considerable pedological variability. Hence, understanding the relationship between SOC and soil texture is important within the context of SOC prediction using remote sensing data. The main objective of this study was to find the impact of soil texture on the performance of local SOC prediction models that were developed on Sentinel-2 (S2) multispectral and CASI/SASI (CS) hyperspectral airborne data as the main predictor variables. One approach to that objective was to lowering the texture variance by stratification of the samples. Therefore, soil samples collected from four agricultural sites in the Czech Republic were segregated based on the i) site-based and ii) texture-based stratification strategies. Random forest (RF) models were then developed on all stratified classes with and without considering the soil texture parameters as predictor variables and results were compared with those obtained by the RF models developed on the non-stratified (NS) samples. Both stratification strategies provided more homogeneous classes, which enhanced the accuracy of SOC prediction, compared to using the NS samples. In addition, the texture-based RF models yielded higher accuracy predictions than the site-based ones. Except sand, adding texture parameters to the main predictors improved accuracy of the models, so that the highest prediction performance was obtained by a texture-based model developed on clay added CS data. Overall, texture-based stratification could significantly enhance the SOC prediction, when the texture parameters were added to the S2 and CS data as the main predictor variables.

Dark-object subtraction atmosphere correction for water body information extraction in Zhuhai-1 hyperspectral imagery

The atmospheric correction of hyperspectral data stands as a fundamental step in quantitative applications, crucial for the accurate analysis of hyperspectral information. Zhuhai-1 hyperspectral data, characterized by its high spatial and spectral resolution, holds substantial potential and advantages for the quantification of water body information. Nonetheless, the adoption of more precise physical models for atmospheric correction often demands extensive satellite and ground environmental parameters, which pose practical challenges in applying physical models The Dark Object Subtraction (DOS), leveraging the intrinsic spectral characteristics of the imagery, offers an efficient alternative for achieving improved atmospheric correction results tailored to the data and study area. In this context, this study presents a Dark Object Subtraction for Water body information extraction (DOSW), specifically designed to advance the quantification of water body information in Zhuhai-1 hyperspectral data. The proposed method is rigorously evaluated by comparing the correction results from the Foshan region and Feilaixia Reservoir with standard and measured spectra of typical objects. The results demonstrate the accuracy of DOSW in atmospheric correction, with correlation coefficients exceeding 0.7 when compared to standard spectra for three representative objects. Notably, DOSW achieves exceptional accuracy in water body correction, achieving a correlation coefficient of 0.95 and an RMSE of 0.002 in the Feilaixia Reservoir, and a correlation coefficient of 0.72 and an RMSE of 0.005 in the Foshan region. Overall, the results underscore the efficacy of DOSW in accurately addressing atmospheric correction challenges to Zhuhai-1 hyperspectral data, effectively meeting the requirements of hyperspectral quantification applications.

Nondestructive Detection of Sunflower Seed Vigor and Moisture Content Based on Hyperspectral Imaging and Chemometrics

Sunflower is an important crop, and the vitality and moisture content of sunflower seeds have an important influence on the sunflower’s planting and yield. By employing hyperspectral technology, the spectral characteristics of sunflower seeds within the wavelength range of 384–1034 nm were carefully analyzed with the aim of achieving effective prediction of seed vitality and moisture content. Firstly, the original hyperspectral data were subjected to preprocessing techniques such as Savitzky–Golay smoothing, standard normal variable correction (SNV), and multiplicative scatter correction (MSC) to effectively reduce noise interference, ensuring the accuracy and reliability of the data. Subsequently, principal component analysis (PCA), extreme gradient boosting (XGBoost), and stacked autoencoders (SAE) were utilized to extract key feature bands, enhancing the interpretability and predictive performance of the data. During the modeling phase, random forests (RFs) and LightGBM algorithms were separately employed to construct classification models for seed vitality and prediction models for moisture content. The experimental results demonstrated that the SG-SAE-LightGBM model exhibited outstanding performance in the classification task of sunflower seed vitality, achieving an accuracy rate of 98.65%. Meanwhile, the SNV-XGBoost-LightGBM model showed remarkable achievement in moisture content prediction, with a coefficient of determination (R2) of 0.9715 and root mean square error (RMSE) of 0.8349. In conclusion, this study confirms that the fusion of hyperspectral technology and multivariate data analysis algorithms enables the accurate and rapid assessment of sunflower seed vitality and moisture content, providing robust tools and theoretical support for seed quality evaluation and agricultural production practices. Furthermore, this research not only expands the application of hyperspectral technology in unraveling the intrinsic vitality characteristics of sunflower seeds but also possesses significant theoretical and practical value.

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.

A novel hierarchical approach to insight to spectral characteristics in surface water of karst wetlands and estimate its non-optically active parameters using field hyperspectral data

Wetlands cover only around 6 % of the Earth's land surface, and are recognized as one of the three major ecosystems, alongside forests and oceans. The ecological structure and function of karst wetlands are unique due to the influence of geologic structure. At present, the unclear spectral morphology of surface water in karst wetlands poses a significant challenge in remote sensing estimation of non-optically active water quality parameters (NAWQPs). This study proposed a novel multi-scale spectral morphology feature extraction (MSFE) method to insight to spectral characteristics in surface water of karst wetlands, and further screen the sensitive features of NAWQPs. Then we constructed three remote sensing inversion strategies for NAWQPs (TN, TP, NH3_N, DO), including direct estimation, indirect estimation, and auxiliary estimation. Finally, we constructed a novel pH-based hierarchical analysis framework (pH_HA) to thoroughly explore the influence of alkalinity-biased characteristics of karst water on the spectral domain of NAWQPs and its estimation accuracy using in-situ hyperspectral data, respectively. We found that the spectral characteristics of karst waters at the first reflectance peak (580 nm) differed significantly from other water body types. The MSFE successfully captured the sensitive spectral domains for NAWQPs, and focused on between 500 and 600 nm and 900–960 nm. The sensitive features captured by MSFE improved estimation accuracy of NAWQPs (R2 >0.9). Direct estimation presented more stable performance compared to the auxiliary estimation (average RMSE of 0.366 mg/L), and the auxiliary estimation model further improved the retrieval accuracy of TN compared to direct estimation model (R2 increasing from 0.43 to 0.56). The novel hierarchical framework clearly revealed the notable changes in the sensitive spectral domains of NAWQPs under different pH values, and enabled more precise determination of spectral subdomains of NAWQPs, and identified the optimal spectral features. The pH_HA framework effectively improved the estimation accuracy of NAWQPs (R2 increased from 0.514 to over 0.9), and the estimation accuracies (R2) of four NAWQPs were all more than 0.9 when the pH value was over 8.5. Our works provide an effective approach for monitoring water quality in karst wetlands.

Transfer Learning-Based Hyperspectral Image Classification Using Residual Dense Connection Networks

The extraction of effective classification features from high-dimensional hyperspectral images, impeded by the scarcity of labeled samples and uneven sample distribution, represents a formidable challenge within hyperspectral image classification. Traditional few-shot learning methods confront the dual dilemma of limited annotated samples and the necessity for deeper, more effective features from complex hyperspectral data, often resulting in suboptimal outcomes. The prohibitive cost of sample annotation further exacerbates the challenge, making it difficult to rely on a scant number of annotated samples for effective feature extraction. Prevailing high-accuracy algorithms require abundant annotated samples and falter in deriving deep, discriminative features from limited data, compromising classification performance for complex substances. This paper advocates for an integration of advanced spectral–spatial feature extraction with meta-transfer learning to address the classification of hyperspectral signals amidst insufficient labeled samples. Initially trained on a source domain dataset with ample labels, the model undergoes transference to a target domain with minimal samples, utilizing dense connection blocks and tree-dimensional convolutional residual connections to enhance feature extraction and maximize spatial and spectral information retrieval. This approach, validated on three diverse hyperspectral datasets—IP, UP, and Salinas—significantly surpasses existing classification algorithms and small-sample techniques in accuracy, demonstrating its applicability to high-dimensional signal classification under label constraints.

Detection of Emerging Stress in Trees Using Hyperspectral Indices as Classification Features

This research presents a classification methodology for the detection of new or emerging stress in trees using indices derived from hyperspectral data and tests whether existing hyperspectral indices are effective when used as the classification features for this problem. We tested six existing indices—Water Band Index (WBI), Gitelson–Merzlyak B Index (GMb), Normalized Phaeophytization Index (NPQI), Combined Carotenoid/Chlorophyll Ratio Index (CCRI), Photochemical Reflectance Index (PRI), and Red-Edge Chlorophyll Index (CIre)—along with a seventh Test Index—generated as a composite of PRI and Cire—as classification features. Analysis was conducted using data collected from trees with and without emerald ash borer (EAB) infestation to develop a methodology that could be adapted to measure emerging stress from other pathogens or invasive pests in other tree species. Previous work has focused specifically on the identification of damage or stress symptoms caused by a specific pathogen. In this study, we adapted that work to develop a system of classification that can be applied to the identification of stress symptoms from a range of sources, measurable in trees based on spectral response and, in some cases, detectable prior to the onset of visible symptoms that can be measured through human observation. Our data indicate that existing indices derived from hyperspectral data are effective as classification features when measuring spectral responses indicative of emerging stress in trees.