The TECIS (Terrestrial Ecosystem Carbon Inventory Satellite), launched in August 2022, achieves high-resolution stereo monitoring of atmospheric clouds and aerosols through multibeamLiDAR and multispectral cameras. Traditional algorithms struggle with accuracy and robustness in vertical layer retrieval under complex conditions. Here, we propose TECIS-CASNet, a universal framework for atmospheric layer identification, integrating TECIS and CALIOP with deep learning transformer theories. To demonstrate its advantage, we applied it to analyze the spatiotemporal distribution of cloud, aerosol, and dust in the Beijing-Tianjin-Hebei (BTH) region of China, where cloud-aerosol variability is high due to topography, climate, and human activity. The TECIS-CASNet improved classification by approximately 15% compared with traditional algorithms, especially under low signal-to-noise ratio and other complex situations. Furthermore, it achieved 95%accuracy with absolute accuracy of 0.01 in optical depth inversion. The framework identified dust transport from central Inner Mongolia (linked to potential deforestation), significantly affecting near-ground air quality. The TECIS-CASNet has great potential for satellite LiDAR data processing and climate change.

Aerosols emitted by wildfires play a crucial role in the global climate system and regional air quality. Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) can detect the vertical structure of atmospheric clouds and aerosols globally. While traditional layer classification algorithms can effectively differentiate between aerosol and cloud layers, they typically rely on predefined thresholds and rules, which lack sensitivity to weaker details in the signal. This reduces the accuracy and reliability of the classification. Therefore, in this study, we have proposed a framework for the three-dimensional monitoring of wildfire aerosols (Wildfire Aerosol Discrimination-SwinUNet, WAD-SNet), combining transformer architecture with CALIPSO satellite data. Using the typical wildfire events in Australia in 2022 as a case study, we analyzed the spatiotemporal variations and causes of wildfire aerosols. After pixel denoising, WAD-SNet achieved an accuracy of 93.18% in cloudaerosol classification with CALIPSO data under multiple or complex conditions. Compared with the traditional UNet model, it demonstrates an improvement of over 10% in recall under low signal-to-noise ratio, low-level edge, and near-surface scenarios. High temperatures, low humidity, and reduced precipitation significantly increase the risk of wildfires in Australia, leading to an increase in aerosol concentrations. By tracking the diffusion path of smoke aerosols in New South Wales, the dynamic changes of the wildfire can be analyzed. This study achieves accurate classification of CALIPSO data under complex conditions and enables effective tracking of smoke aerosols, thereby offering practical contributions to LiDAR data processing and wildfire monitoring.

Masked image modeling (MIM), a common self-supervised learning (SSL) technique, has been extensively studied for remote sensing (RS) image processing. Nevertheless, its effectiveness for hyperspectral imagery (HSI) remains underexplored due to the distinct data structures and high dimensionality. This article aims to provide a detailed understanding of MIM from different perspectives of representation learning and statistical analysis for HSI classification tasks. Our study reveals that the MIM paradigm injects inductive bias in the attention mechanism of the transformer model, which is advantageous for capturing the local discrepancies between the spectra. We also show that MIM can increase the diversity of the attention heads in every layer, which is beneficial for the model in extracting more discriminative features from different spectral bands. The similarity of representations from various layers further proves this. Furthermore, our investigation highlights how MIM introduces a dynamic perspective to spectral representations, enabling the model to learn more robust and discriminative features. The final numerical experiments indicate that a moderate mask ratio can enhance the performance of downstream tasks. This suggests that designing a more targeted masking strategy might be necessary to achieve higher and more stable gains in downstream task performance. Without bells and whistles, the vanilla MIM improves the overall classification accuracy by an average of 2.69% over its supervised learning (SL) counterpart. We hope that our findings can advance the understanding of MIM in HSI and inspire the design of a more stable SSL paradigm for HSI processing.

Inspired by certain optimization solvers, the deep unfolding network (DUN) usually inherits a multi-phase structure for image compressive sensing (CS). However, in existing DUNs, the message transmission within and between phases still faces two issues: 1) the roughness of transmitted information, e.g., the low-dimensional representations. 2) the inefficiency of transmitted policy, e.g., simply concatenating deep features. In this paper, by unfolding the Proximal Gradient Descent (PGD) algorithm, a novel gradient guided DUN (G2 -DUN) for image CS is proposed, in which a gradient map is delicately introduced within each phase for providing richer informational guidance at both intra-phase and inter-phase levels. Specifically, corresponding to the gradient descent (GD) of PGD, a gradient guided GD module is designed, in which the gradient map can adaptively guide step size allocation for different textures of input image, realizing a content-aware gradient updating. On the other hand, corresponding to the proximal mapping (PM) of PGD, a gradient guided PM module is developed, in which the gradient map can dynamically guide the exploring of deep textural priors in multi-scale space, achieving the dynamic perception of the proposed deep model. By introducing the gradient map, the proposed message transmission system not only facilitates the informational communication between different functional modules within each phase, but also strengthens the inferential cooperation among cascaded phases. Extensive experiments manifest that the proposed G2 -DUN outperforms existing state-of-the-art CS methods.

A study has been conducted on the effectiveness assessment methods of high-orbit infrared remote sensing satellites, and by analyzing the difficulties in evaluating the effectiveness of the complex star-ground system of the “human-in-the-loop”, an assessment criterion centered on the degree of mission accomplishment has been proposed. Drawing on the concept of equipment technology maturity and grading, and combining practical experience, an efficiency assessment model has been established around the construction of mission scenarios of different grades, and a class of assessment processes and assessment methods have been developed and provided as samples. A calculation method based on system reliability, repairability and availability is proposed for the comprehensive assessment of mission completion, which can improve the current assessment method in practical application. A generic quantitative method for evaluating the effectiveness of the system based on the unfulfilled or unintended tasks is investigated, which can effectively reflect the bottleneck capacity of the system and support the subsequent optimization and improvement of the system.

Hyperspectral images (HSIs) have been widely used in Earth observation because they contain continuous and detailed spectral information which is beneficial for the fine-grained diagnosis of the land cover. In the past few years, convolutional neural network (CNN)-based methods show limitations in modeling spectral-wise long-range dependences. Recently, transformer-based deep learning methods are proposed and have shown superiority in modeling the continuous representation of the spectral signatures because the self-attention (SA) mechanism has a global receptive field. Due to the special tokenization of the transformer-based methods, the redundant tokens contained in spectral embeddings are always involved in SA operation. Redundant tokens do not positively contribute to classification. Specifically, the overlapped group-wise tokenization approach may aggravate the Hughes phenomenon and impose additional computations. To address this issue, a lightweight spatial–spectral pyramid transformer (SSPT) framework is proposed to efficiently extract the spatial–spectral features of HSI by progressively reducing redundant tokens in an end-to-end manner. In particular, a token reduction (TR) method is proposed to decide which tokens will be involved by computing and comparing token attentiveness between spectral embeddings and the class token. In addition, for those tokens that are defined as redundant information, a token compensation mechanism is proposed to automatically extract supplementary information for classification. Extensive experiments on three standard datasets quantitatively show the superiority of our methods, and the ablation experiments qualitatively prove our hypothesis about the feature distribution in transformer architecture.

Hyperspectral images (HSIs) contain spatially structured information and pixel-level sequential spectral attributes. The continuous spectral features contain hundreds of wavelength bands and the differences between spectra are essential for achieving fine-grained classification. Due to the limited receptive field of backbone networks, convolutional neural networks (CNNs)-based HSI classification methods show limitations in modeling spectral-wise long-range dependencies with fixed kernel size and a limited number of layers. Recently, the self-attention mechanism of transformer framework is introduced to compensate for the limitations of CNNs and to mine the long-term dependencies of spectral signatures. Therefore, many joint CNN and Transformer architectures for HSI classification have been proposed to obtain the merits of both networks. However, these architectures make it difficult to capture spatial–spectral correlation and CNNs distort the continuous nature of the spectral signature because of the over-focus on spatial information, which means that the transformer can easily encounter bottlenecks in modeling spectral-wise similarity and long-range dependencies. To address this problem, we propose a neighborhood enhancement hybrid transformer (NEHT) network. In particular, a simple 2D convolution module is adopted to achieve dimensionality reduction while minimizing the distortion of the original spectral distribution by stacked CNNs. Then, we extract group-wise spatial–spectral features in a parallel design to enhance the representation capability of each token. Furthermore, a feature fusion strategy is introduced to increase subtle discrepancies of spectra. Finally, the self-attention of transformer is employed to mine the long-term dependencies between the enhanced feature sequences. Extensive experiments are performed on three well-known datasets and the proposed NEHT network shows superiority over state-of-the-art (SOTA) methods. Specifically, our proposed method outperforms the SOTA method by 0.46%, 1.05% and 0.75% on average in overall accuracy, average accuracy and kappa coefficient metrics.

This paper is concerned with the problem of attitude-orbit tracking control for flexible spacecraft. A relative attitude-orbit-structure integrated dynamics model is derived for flexible spacecraft, where environmental disturbances and parameter uncertainty are considered as lumped disturbance. And the relative position and attitude of the spacecraft are described by the exponential coordinates of SE(3). Since the modal variables are not measurable, a modal observer is proposed to obtain the state estimation related to elastic vibration. Then, a composite control technique is proposed for attitude-orbit tracking of flexible spacecraft under lumped disturbance by combining a state observer of modal parameter and nonlinear disturbance observer with an asymptotic tracking control. The vibration mode information and the lumped disturbance are estimated and compensated by the modal observer and the nonlinear disturbance observer, respectively, in the feedback link. The stability of the composed control approach consisting of the asymptotic tracking control and multi-observer observer is guaranteed through Lyapunov method. The simulation results validate the composite control technique can effectively enhance disturbance attenuation ability, robust dynamics performance and the desired relative attitude tracking accuracy of a flexible spacecraft with multiple disturbances and parameter uncertainty.

ZY1-02D is a Chinese hyperspectral satellite, which is equipped with a visible near-infrared multispectral camera and a hyperspectral camera. Its data are widely used in soil quality assessment, mineral mapping, water quality assessment, etc. However, due to the limitations of CCD design, the swath of hyperspectral data is relatively smaller than multispectral data. In addition, stripe noise and collages exist in hyperspectral data. With the contamination brought by clouds appearing in the scene, the availability is further affected. In order to solve these problems, this article used a swath reconstruction method of a spectral-resolution-enhancement method using ResNet (SRE-ResNet), which is to use wide swath multispectral data to reconstruct hyperspectral data through modeling mappings between the two. Experiments show that the method (1) can effectively reconstruct wide swaths of hyperspectral data, (2) can remove noise existing in the hyperspectral data, and (3) is resistant to registration error. Comparison experiments also show that SRE-ResNet outperforms existing fusion methods in both accuracy and time efficiency; thus, the method is suitable for practical application.