Spatial Spectral Characteristics Research Articles

MSTSENet: Multiscale Spectral–Spatial Transformer with Squeeze and Excitation network for hyperspectral image classification

Hyperspectral image (HSI) classification pertains to the task of assigning a single label to each pixel by analyzing its spectral–spatial characteristics. Convolutional Neural Networks (CNNs) have garnered significant attention on account of their remarkable performance in feature representation. However, these approaches possess a restricted capacity to acquire highly similar spectral features. Recently, Attention-based approaches have been devised as a means to surmount the limitations inherent in CNNs. In this paper, we address a novel architecture for spectral–spatial feature extraction and HSI classification. The framework efficiently amalgamates the robustness and efficacy of three modern backbone networks, i.e., Multiscale CNN, Squeeze and Excitation (SE), and Transformer named MSTSENet. Initially, the multiscale convolution module integrates three branches of 3D convolution layers, each employing distinct kernel sizes, facilitating multiscale and multi-resolution feature extraction. Subsequently, the SE module enhances the inter-channel relationship by adaptively recalibrating the feature weight. The strategic fusion of the SE module with multiscale CNN strengthens deep feature extraction while introducing a minimal increment in overall parameters. Lastly, the Transformer module orchestrates information aggregation across different spectral–spatial regions, accurately modeling long-range contextual dependencies and capturing dominant feature representations. To evaluate the model performance, comprehensive experiments have been carried out on widely used benchmark HSI datasets. The overall accuracy of 98.74%, 99.83%, and 99.98% is achieved over the Indian Pines, Pavia University, and Salinas Valley datasets, respectively. The code of this work will be accessible at https://github.com/irfan01000/MSTSENet.

Tip-leakage-flow excited unsteadiness and associated control

Tip leakage flow in turbomachinery inherently generates intense unsteady features, named self-excited unsteadiness, which significantly affects the operating stability, aerodynamic efficiency, and noise but has not been well understood. A zonalized large eddy simulation is employed for a linear cascade, with wall-modeled large eddy simulation active only in the tip region. The simulation is well validated with advantages demonstrated for effectively reducing the computational cost while maintaining an equivalent prediction accuracy in the region of interest. The time-averaged and spatial-spectral characteristics of tip leakage vortex (TLV) structures are systematically discussed. The self-excited unsteady processes of TLV include the tip gap separation, the tip leakage and jet-mainstream interaction, the primary tip leakage vortex (PTLV) wandering motion, and the induced separation near end wall. The Spectral Proper Orthogonal Decomposition (SPOD) is used to examine the dominant frequencies and their coherent structures. It is found that these unsteady features change from a single high frequency to multiple lower frequencies due to the PTLV breakdown. The SPOD and correlation analyses reveal that the self-excited unsteadiness originates initially from unsteady vortex separation in the tip gap and is then fed by the interactions between the tip leakage jet and mainstream. The associated unsteady fluctuations are convected along the tip leakage jet trajectory, causing the wandering motion of PTLV core. Based on the revealed unsteadiness sources, a micro-offset tip design is proposed and shown to be an effective solution to reducing the tip flow unsteadiness. This work improves the understanding of tip-leakage-flow dynamics and informs the control of the associated unsteady fluid oscillation and noise.

Mayfly algorithm-based semi-supervised band selection with enhanced bitonic filter for spectral-spatial hyperspectral image classification

ABSTRACT Hyperspectral imaging effectively distinguishes land cover classes with discriminative spectral-spatial characteristics. However, hyperspectral image (HSI) classification encounters three significant challenges: the curse of dimensionality, the scarcity of training samples, and the necessity to incorporate spatial information within the classification process. The large number of redundant and irrelevant spectral bands in HSI can negatively impact the classification performance. Furthermore, the annotation process for training samples is expensive and time-consuming. To address these challenges, this work presents a novel semi-supervised approach for hyperspectral image dimensionality reduction using the Mayfly Algorithm (MA). The proposed method aims to preserve the most informative spectral bands while leveraging both labelled and unlabelled samples in the process. The MA algorithm effectively balances exploration and exploitation strategies, enhancing population diversity and mitigating challenges such as premature convergence and local optima. Additionally, the inclusion of structural variation and thresholding (SVT) in the Bitonic filter enables the incorporation of spatial features during the classification phase. This improves the separability of pixels belonging to different objects and leads to significant improvements in classification performance. Finally, two machine learning classifiers, namely Random Forest (RF) and Support Vector Machine (SVM), are applied at the pixel level for hyperspectral image classification. Extensive experimental results on three real hyperspectral datasets demonstrate the superiority of the proposed approach compared to state-of-the-art algorithms like Harmony Search (HS), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and more with an average improvement of 3.2%.

Deep clustering using 3D attention convolutional autoencoder for hyperspectral image analysis

Deep clustering has been widely applicated in various fields, including natural image and language processing. However, when it is applied to hyperspectral image (HSI) processing, it encounters challenges due to high dimensionality of HSI and complex spatial-spectral characteristics. This study introduces a kind of deep clustering model specifically tailed for HSI analysis. To address the high dimensionality issue, redundant dimension of HSI is firstly eliminated by combining principal component analysis (PCA) with t-distributed stochastic neighbor embedding (t-SNE). The reduced dataset is then input into a three-dimensional attention convolutional autoencoder (3D-ACAE) to extract essential spatial-spectral features. The 3D-ACAE uses spatial-spectral attention mechanism to enhance captured features. Finally, these enhanced features pass through an embedding layer to create a compact data-representation, and the compact data-representation is divided into distinct clusters by clustering layer. Experimental results on three publicly available datasets validate the superiority of the proposed model for HSI analysis.

Markedly Enhanced Analysis of Mass Spectrometry Images Using Weakly Supervised Machine Learning.

Supervised and unsupervised machine learning algorithms are routinelyapplied to time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging data and, more broadly, to mass spectrometry imaging (MSI). These algorithms have accelerated large-scale, single-pixel analysis, classification, and regression. However, there is relatively little research on methods suited for so-called weakly supervised problems, where ground-truth class labels exist at the image level, but not at the individual pixel level. Unsupervised learning methods are usually applied to these problems. However, these methods cannot make use of available labels. Here a novel method specifically designed for weakly supervised MSI data is presented. A dual-stream multiple instance learning (MIL) approach is adapted from computational pathology that reveals the spatial-spectral characteristics distinguishing different classes of MSI images. The method uses an information entropy-regularized attention mechanism to identify characteristic class pixels that are then used to extract characteristic mass spectra. This work provides a proof-of-concept exemplification using printed ink samples imaged by ToF-SIMS. A second application-oriented study is also presented, focusing on the analysis of a mixed powder sample type. Results demonstrate the potential of the MIL method for broader application in MSI, with implications for understanding subtle spatial-spectral characteristics in various applications and contexts.

Modeling the spatial-spectral characteristics of plants for nutrient status identification using hyperspectral data and deep learning methods.

Sustainable fertilizer management in precision agriculture is essential for both economic and environmental reasons. To effectively manage fertilizer input, various methods are employed to monitor and track plant nutrient status. One such method is hyperspectral imaging, which has been on the rise in recent times. It is a remote sensing tool used to monitor plant physiological changes in response to environmental conditions and nutrient availability. However, conventional hyperspectral processing mainly focuses on either the spectral or spatial information of plants. This study aims to develop a hybrid convolution neural network (CNN) capable of simultaneously extracting spatial and spectral information from quinoa and cowpea plants to identify their nutrient status at different growth stages. To achieve this, a nutrient experiment with four treatments (high and low levels of nitrogen and phosphorus) was conducted in a glasshouse. A hybrid CNN model comprising a 3D CNN (extracts joint spectral-spatial information) and a 2D CNN (for abstract spatial information extraction) was proposed. Three pre-processing techniques, including second-order derivative, standard normal variate, and linear discriminant analysis, were applied to selected regions of interest within the plant spectral hypercube. Together with the raw data, these datasets were used as inputs to train the proposed model. This was done to assess the impact of different pre-processing techniques on hyperspectral-based nutrient phenotyping. The performance of the proposed model was compared with a 3D CNN, a 2D CNN, and a Hybrid Spectral Network (HybridSN) model. Effective wavebands were selected from the best-performing dataset using a greedy stepwise-based correlation feature selection (CFS) technique. The selected wavebands were then used to retrain the models to identify the nutrient status at five selected plant growth stages. From the results, the proposed hybrid model achieved a classification accuracy of over 94% on the test dataset, demonstrating its potential for identifying nitrogen and phosphorus status in cowpea and quinoa at different growth stages.

Hybrid Convolutional Network Combining Multiscale 3D Depthwise Separable Convolution and CBAM Residual Dilated Convolution for Hyperspectral Image Classification

In recent years, convolutional neural networks (CNNs) have been increasingly leveraged for the classification of hyperspectral imagery, displaying notable advancements. To address the issues of insufficient spectral and spatial information extraction and high computational complexity in hyperspectral image classification, we introduce the MDRDNet, an integrated neural network model. This novel architecture is comprised of two main components: a Multiscale 3D Depthwise Separable Convolutional Network and a CBAM-augmented Residual Dilated Convolutional Network. The first component employs depthwise separable convolutions in a 3D setting to efficiently capture spatial–spectral characteristics, thus substantially reducing the computational burden associated with 3D convolutions. Meanwhile, the second component enhances the network by integrating the Convolutional Block Attention Module (CBAM) with dilated convolutions via residual connections, effectively counteracting the issue of model degradation. We have empirically evaluated the MDRDNet’s performance by running comprehensive experiments on three publicly available datasets: Indian Pines, Pavia University, and Salinas. Our findings indicate that the overall accuracy of the MDRDNet on the three datasets reached 98.83%, 99.81%, and 99.99%, respectively, which is higher than the accuracy of existing models. Therefore, the MDRDNet proposed in this study can fully extract spatial–spectral joint information, providing a new idea for solving the problem of large model calculations in 3D convolutions.

Ensembles of spectral-spatial convolutional neural network models for classifying soil types in hyperspectral images

The paper presents a study of various approaches to the classification of soil covers based on neural network algorithms using hyperspectral remote and proximal sensing of the Earth. The spectral distributions were recorded in the laboratory using an Offner imaging scanning hyperspectrometer. Spectral-spatial characteristics of nine soil samples from various parts of a farming land in the Samara region were experimentally studied. Using a method of energy dispersion microanalysis, the correspondence between the hyperspectral data and the chemical composition of the samples taken was established. Based on the data obtained, a neural network-aided classification of soil samples was implemented depending on the content of constituent elements such as carbon and calcium. A normalized spectral-spatial convolutional neural network was used as a classifier. As a result of the work, an approach to the classification of high-resolution hyper-spectral images based on the refinement of a multiclass convolutional neural network using an ensemble of binary classifiers is proposed. It is shown that the classification of soil samples by carbon and calcium content is carried out with an accuracy of 0.96.

Spatial Spectral Characteristics of Partial Discharge with Different Electrode Models

In this paper, the spatial spectral characteristics of partial discharge (PD) under different electrode models are mainly studied. In the initial corona discharge stage, the emission spectrum is mainly emitted by the N2(C3IIu→B3IIg) energy level transition of the N2 second positive band system. The spectrum is in the ultraviolet range of 294–436 nm, and its main peak is at 337 nm. The streamer discharge stage spectrum is mainly emitted by the energy level transition of the second positive band system of N2, N+, NO, and O+ and the first positive band system of N2(B3IIg→A3Σu+). In the gap of different polarity electrodes, the ultraviolet spectrum content near the positive polarity is more abundant. The UV spectra ranges are 202–225 nm and 229–292 nm, respectively. The discharge of the needle–sphere system is more intense in visible light and near-infrared light, with peaks at 500 nm and 777 nm, respectively. In addition, the PD process based on the finite element method is simulated by COMSOL Multiphysics software. The simulation results show that the distribution of high-energy electron density varies with the electrode spacing and discharge model. The influence of particle energy level transition on the spatial spectral characteristics of PD is verified. This work provides important insights and possibilities for future fluorescent fiberoptic sensing and positioning for spatial PD detection and positioning using spectral characteristic peaks as detection quantities or excitations.

A Fast and Accurate Prediction of Distortions in DCT-Based Lossy Image Compression

Since the number of acquired images and their size have the tendency to increase, their lossy compression is widely applied for their storage, transfer, and dissemination. Simultaneously with providing a relatively large compression ratio, lossy compression produces distortions that are inevitably introduced and have to be controlled. The properties of these distortions depend on several factors such as image properties, the coder used, and a parameter that controls compression, which is different for particular coders. Then, one has to set a parameter that controls compression individually for an image to be compressed to provide image quality appropriate for a given application, and it is often desirable to do this quickly. Iterative procedures are usually not fast enough, and therefore fast and accurate procedures for providing a desired quality are needed. In the paper, such a procedure for two coders based on discrete cosine transform is proposed. This procedure is based on a prediction of mean square errors for a given quantization step using a simple analysis of image complexity (local activity in blocks). The statistical and spatial–spectral characteristics of distortions introduced by DCT-based coders are analyzed, and it is shown that they depend on the quantization step and local content. Generalizing the data for sets of grayscale test images and quantization step values, it is shown that the MSE can be easily predicted. These predictions are accurate enough and can be used to set the quantization step properly, as verified by experiments performed using more than 300 remote sensing and conventional optical images. The proposed approach is applicable to the lossy compression of grayscale images and the component-wise compression of multichannel data.

MSCANet: multiscale context information aggregation network for Tibetan Plateau lake extraction from remote sensing images

ABSTRACT Qinghai-Tibet Plateau lakes are important carriers of water resources in the ‘Asian’s Water Tower’, and it is of great significance to grasp the spatial distribution of plateau lakes for the climate, ecological environment, and regional water cycle. However, the differences in spatial-spectral characteristics of various types of plateau lakes, and the complex background information of plateau both influence the extraction effect of lakes. Therefore, it is a great challenge to completely and effectively extract plateau lakes. In this study, we proposed a multiscale contextual information aggregation network, termed MSCANet, to automatically extract Plateau lake regions. It consists of three main components: a multiscale lake feature encoder, a feature decoder, and a Multicore Pyramid Pooling Module (MPPM). The multiscale lake feature encoder suppressed noise interference to capture multiscale spatial-spectral information from heterogeneous scenes. The MPPM module aggregated the contextual information of various lakes globally. We applied the MSCANet to the lake extraction of the Qinghai-Tibet Plateau based on Google data; additionally, comparative experiments showed that the MSCANet proposed had obvious improvement in lake detection accuracy and morphological integrity. Finally, we transferred the pre-trained optimal model to the Landsat-8 and Sentinel-2A dataset to verify the generalization of the MSCANet.

Low-Rank Constrained Attention-Enhanced Multiple Spatial–Spectral Feature Fusion for Small Sample Hyperspectral Image Classification

Hyperspectral images contain rich features in both spectral and spatial domains, which bring opportunities for accurate recognition of similar materials and promote various fine-grained remote sensing applications. Although deep learning models have been extensively investigated in the field of hyperspectral image classification (HSIC) tasks, classification performance is still limited under small sample conditions, and this has been a longstanding problem. The features extracted by complex network structures with large model size are redundant to some extent and prone to overfitting. This paper proposes a low-rank constrained attention-enhanced multiple feature fusion network (LAMFN). Firstly, factor analysis is used to extract very few components that can describe the original data using covariance information to perform spectral feature preprocessing. Then, a lightweight attention-enhanced 3D convolution module is used for deep feature extraction, and the position-sensitive information is supplemented using a 2D coordinate attention. The above widely varying spatial–spectral feature groups are fused through a simple composite residual structure. Finally, low-rank second-order pooling is adopted to enhance the convolutional feature selectivity and achieve classification. Extensive experiments were conducted on four representative hyperspectral datasets with different spatial–spectral characteristics, namely Indian Pines (IP), Pavia Center (PC), Houston (HU), and WHU-HongHu (WHU). The contrast methods include several advanced models proposed recently, including residual CNNs, attention-based CNNs, and transformer-based models. Using only five samples per class for training, LAMFN achieved overall accuracies of 78.15%, 97.18%, 81.35%, and 87.93% on the above datasets, which has an improvement of 0.82%, 1.12%, 1.67%, and 0.89% compared to the second-best model. The running time of LAMFN is moderate. For example, the training time of LAMFN on the WHU dataset was 29.1 s, and the contrast models ranged from 3.0 s to 341.4 s. In addition, ablation experiments and comparisons with some advanced semi-supervised learning methods further validated the effectiveness of the proposed model designs.

Grouped Multi-Attention Network for Hyperspectral Image Spectral-Spatial Classification

Deep learning has been a powerful tool for hyperspectral image (HSI) classification. However, it is still an open issue to effectively learn highly discriminative features from the HSI, due to the high-dimensionality and complex spectral-spatial characteristics. To settle this issue, we propose a new band-grouping guided multi-attention module for the performance promotion of spectral-spatial feature learning. First, based on the fact of high relevance between adjacent spectral bands and low dependencies across long-range ones, all the spectral bands are adaptively divided into multiple non-overlapping groups where relevant bands are included. The advantage is to reduce the spectral dimension and data complexity when processing and analyzing each group. Then, a multi-attention mechanism, which not only explore the intra-group salient information but also propagate the inter-group difference information, is embedded into the convolutional neural networks to learn group-specific spectral-spatial features. By emphasizing useful spectral/spatial information and squeezing useless information with attention mechanism, the severability of learned features is enhanced. Based on this module, a spectral-spatial classification network is built, named by grouped multi-attention network (GMA-Net). The GMA-Net contains a two-branch architecture, i.e., pixel-wise spectral feature learning and patch-wise spectral-spatial feature learning. Via fusing the features from two branches, the complementary and discriminative features provided by pixel-wise and patch-wise learning manner can be integrated to further boost classification performance. Experimental results demonstrate that the proposed method is superior than several state-of-the-art approaches. Codes are available at: https://github.com/luting-hnu.

Spatial spectral characteristics of forward scattered light from wake bubbles

To study the spatial spectrum characteristics of scattered light from a laser illuminated bubble curtain in the wake, the Monte Carlo model based on the single-bubble Mie scattering theory was used. The propagation process of each photon in the wake bubble group underwater was tracked, and the coordinates of the photon position reaching the receiving plane were recorded. The effects of propagation distance, bubble size, and bubble number density on the full-width at half-maximum (FWHM) of spatial spectrum of forward scattered light from wake bubbles were investigated. The results show that with the increase of the transmission distance, the bubble size and bubble number density increase, and the FWHM of the spatial spectrum decreases. This feature of spatial spectrum can be used as one of the criteria for ship wake identification.

TPPI: A Novel Network Framework and Model for Efficient Hyperspectral Image Classification

Hyperspectral image (HSI) classification is the most vibrant research field in the hyperspectral community, aiming to assign each pixel in the image to one certain land cover category based on its spectral or spectral-spatial characteristics. Recently, some spectral-spatial–feature deep learning–based convolutional neural networks have been proposed and demonstrated remarkable classification performance. However, these networks are time consuming when facing a real HSI in practical application. The trained model must be forwarded independently across m × m crops of the image in strides of 1 pixel. In this article, an efficient and practical network was proposed for HSI classification that can take an HSI as an input instance and directly output a dense pixel-level classification map. First, a novel mechanism, training based on pixels and prediction based on images (TPPI ), is proposed and formulated. Second, some basic rules that should be obeyed during network design and implementation are given. Finally, following the basic rules, three TPPI -Nets are derived and demonstrated based on state-of- the-art classification networks. Experimental results on three public data sets show that the proposed TPPI-Net can not only obtain higher classification accuracy than the existing DCNN-based methods but also greatly reduce the computational complexity of HSI classification.

Deep Autoencoder for Hyperspectral Unmixing via Global-Local Smoothing

Hyperspectral unmixing is to decompose the mixed pixels into pure spectral signatures (endmembers) and their proportions (abundances). Recently, deep learning-based methods have been applied to enhance the representation ability of unmixing models by extracting joint spatial–spectral characteristics of the hyperspectral data. However, most deep learning based-unmixing methods usually conduct global smoothing by convolutions on the whole hyperspectral imagery, which may ignore the variations within the imagery and result in oversmoothing. In this article, we propose a deep network for hyperspectral unmixing based on a new global–local smoothing autoencoder (GLA). GLA is an unsupervised model, which aims at exploring the local homogeneity and the global self-similarity of hyperspectral imagery. The proposed GLA network mainly includes two modules: a Local Continuous conditional random field Smoothing (LCS) module and a global recurrent smoothing (GRS) module. In LCS, we propose a conditional random field-based smoothing strategy to describe the joint spatial–spectral information within a local homogeneity region, which also reduces the risk of abundance maps boundary blurry. In GRS, we follow the self-similarity assumption for hyperspectral imagery and develop a recurrent neural network structure to exploit potential long-distance dependency relationships among pixels. The GLA is compared with several state-of-the-art unmixing methods on both real and synthetic data, and the abundance estimation results indicate that our method is promising. We will publish the code of GLA if this article has the honor to be accepted.

Deep learning reveals personalized spatial spectral abnormalities of high delta and low alpha bands in EEG of patients with early Parkinson’s disease

Objective. Parkinson’s disease (PD) is one of the most common neurodegenerative diseases, and early diagnosis is crucial to delay disease progression. The diagnosis of early PD has always been a difficult clinical problem due to the lack of reliable biomarkers. Electroencephalogram (EEG) is the most common clinical detection method, and studies have attempted to discover the EEG spectrum characteristics of early PD, but the reported conclusions are not uniform due to the heterogeneity of early PD patients. There is an urgent need for a more advanced algorithm to extract spectrum characteristics from EEG to satisfy the personalized requirements. Approach. The structured power spectral density with spatial distribution was used as the input of convolutional neural network (CNN). A visualization technique called gradient-weighted class activation mapping was used to extract the optimal frequency bands for identifying early PD. Based on the model visualization, we proposed a novel quantitative index of spectral characteristics, spatial-mapping relative power (SRP), to detect personalized abnormalities in the spatial spectral characteristics of EEG in early PD. Main results. We demonstrated the feasibility of applying CNN to identify the patients with early PD with an accuracy of 99.87% ± 0.03%. The models indicated the characteristic frequency bands (high-delta (3.5–4.5 Hz) and low-alpha (7.5–11 Hz) frequency bands) that are used to identify the early PD. The SRP of these two characteristic bands in early PD patients was significantly higher than that in the control group, and the abnormalities were consistent at the group and individual levels. Significance. This study provides a novel personalized detection algorithm based on deep learning to reveal the optimal frequency bands for identifying early PD and obtain the spatial frequency characteristics of early PD. The findings of this study will provide an effective reference for the auxiliary diagnosis of early PD in clinical practice.

Multi-Scale Feature Mapping Network for Hyperspectral Image Super-Resolution

Hyperspectral Image (HSI) can continuously cover tens or even hundreds of spectral segments for each spatial pixel. Limited by the cost and commercialization requirements of remote sensing satellites, HSIs often lose a lot of information due to insufficient image spatial resolution. For the high-dimensional nature of HSIs and the correlation between the spectra, the existing Super-Resolution (SR) methods for HSIs have the problems of excessive parameter amount and insufficient information complementarity between the spectra. This paper proposes a Multi-Scale Feature Mapping Network (MSFMNet) based on the cascaded residual learning to adaptively learn the prior information of HSIs. MSFMNet simplifies each part of the network into a few simple yet effective network modules. To learn the spatial-spectral characteristics among different spectral segments, a multi-scale feature generation and fusion Multi-Scale Feature Mapping Block (MSFMB) based on wavelet transform and spatial attention mechanism is designed in MSFMNet to learn the spectral features between different spectral segments. To effectively improve the multiplexing rate of multi-level spectral features, a Multi-Level Feature Fusion Block (MLFFB) is designed to fuse the multi-level spectral features. In the image reconstruction stage, an optimized sub-pixel convolution module is used for the up-sampling of different spectral segments. Through a large number of verifications on the three general hyperspectral datasets, the superiority of this method compared with the existing hyperspectral SR methods is proved. In subjective and objective experiments, its experimental performance is better than its competitors.

CNN-Based Super-Resolution of Hyperspectral Images

Single-image super-resolution (SISR) techniques attempt to reconstruct the finer resolution version of a given image from its coarser version. In the SISR of hyperspectral data sets, the simultaneous consideration of spectral bands is crucial for ensuring the spectral fidelity. However, the high spectral resolution of these data sets affects the performance of conventional approaches. This research proposes the design of 3-D convolutional neural network (CNN)-based SISR architectures that can map the spatial-spectral characteristics of hypercubes to a finer spatial resolution. The proposed approaches facilitate the simultaneous optimization of sparse codes and dictionaries with regard to the super-resolution objective. Our main hypothesis is that the consideration of spectral aspects is essential for the spatial enhancement of hyperspectral images. Also, we propose that the regularized deconvolution of a coarser-scale hypercube, using learned 3-D filters, yields the required high-resolution version. Based on these hypotheses, a convolution-deconvolution framework is proposed to super-resolve the hypercubes in parallel with the reconstruction of a set of regularizing features. Novel sparse code optimization sub-networks proposed in this article give better performance than the existing strategies. The endmember similarities and hyperspectral image prior are considered while designing the proposed loss functions. In order to improve the generalizability, a collaborative spectral unmixing strategy is employed to refine the spectral base of the super-resolved result. The spatial-spectral accuracy of the super-resolved hypercubes, in terms of the validity of regularizing features and endmembers, is explored to devise an optimal ensemble strategy. The experiments, over different data sets, confirm better accuracy of the proposed frameworks compared to the prominent approaches.

Theoretical analysis of the influence of spatial-spectral characteristics of a quartz surface on the field contrast during photochemical polishing

A method of photochemical subnano-polishing of a quartz surface covered with NaClO solution is considered when the lighting is produced from the quartz side at an angle that provides the total internal reflection of light. It was found the use of the effect of total internal reflection of light significantly enhances the electric field near the quartz surface with a sinusoidal profile (about three times) compared with direct illumination of such a surface under the normal incidence of light from the side of the solution. It has also been shown that for a random profile with a Gaussian correlation function at the initial stage of polishing, the etching of the components of the profile spatial spectrum located near the maximum of the spectral function derivative, as well as in the frequency region having resonance with the incident wave, occurs most intensively.