on September 7, 2021, GaoFen5-02 (GF5-02) Satellite, of the new generation of Chinese hyperspectral remote sensing satellite was successfully launched. GF5-02, the successor to the GF5 satellite, was equipped with six advanced hyperspectral payloads. One of the most important payloads onboard the GF5-02 satellite, the Advanced Hyperspectral Imager (AHSI) has a spatial resolution of 30 m, 330 bands in a spectral range of 380-2500 nm. The spectral resolution of the visible-near infrared (VNIR) and shortwave infrared (SWIR) bands are better than 5 nm and 10 nm, respectively. In order to analyze the spectral performance of the GF5-02 AHSI, an on-orbit spectral calibration method that utilizes atmospheric limb observations with on-board calibration system was proposed in this paper. The on-orbit spectral calibration results were validated by atmospheric absorption features with synchronous measurements of surface reflectance and atmospheric parameters. For the GF5-02 AHSI, the shifts in the central wavelength of the Visible and Near-Infrared (VNIR) band is 0.117 nm, while the shifts in the Full Width at Half Maximum (FWHM) is 0.02 nm. In the Short-Wave Infrared (SWIR) band, these values are 0.25 nm for the central wavelength and 0.04 nm for the FWHM. The results demonstrate that the applied method is effective for on-orbit spectral calibration for GF5-02 AHSI.

Synchronization monitoring atmospheric corrector (SMAC) sensor is equipped with polarization and intensity data, providing the possibility of retrieving more accurate aerosol parameters for main sensor’s atmospheric correction. In this study, a novel aerosol retrieval algorithm based on intensity and polarization data was proposed. First, we analyze and construct the ratio relationship of different intensity and polarization channels of SMAC on different surface types and analyze the correlation between these ratios and normalized difference vegetation index (NDVI) and scattering angle (SCA). Then, for the first time, high-precision surface prior knowledge for SMAC aerosol retrieval is constructed, and then, intensity and polarization data were used to retrieve high-precision aerosol products simultaneously. These results are compared and validated with Moderate Resolution Imaging Spectroradiometer (MODIS) and ground-based observations aerosol products, and aerosol optical depth (AOD) product comparison between the SMAC and MODIS showed that they had similar spatial distribution, scattered dots of them with a Pearson correlation coefficient (R) of 0.84 and a root-mean-square error (RMSE) of 0.11. Meanwhile, their differences were also analyzed. The validation between the ground-based sites and the SAMC retrieval results also showed a good performance with R of 0.88 and RMSE of 0.10. These results revealed that the new algorithm is an effective method for retrieving reliable AOD products for the main sensor’s atmosphere correction.

The current classification systems are established from the perspective of terrain information that humans can collect on the surface, in order to meet different research purposes, research areas, research objects, or application and management requirements. The extraction of land use information contained in these distinctive classification systems mainly relies on remote sensing technology. However, due to the lack of strict connection between remote sensing technology and the current classification system and application, remote sensing technology has not been fully utilized in land use classification. Therefore, based on the multi-source remote sensing observation system’s representation of the ground in the spatiotemporal spectral dimensions and the principle of stable and classifiable of land cover, this study constructs a three-level remote sensing intelligent interpretation classification system: the first level -recognizable using "spectral characteristics ", the second level-identifiable by overlaying " temporal characteristics " or " temporal and spatial characteristics ", the third level-identifiable by overlaying "spectral physicochemical parameters". This classification system is a remote sensing intelligent interpretation product system driven by satellite remote sensing, which only includes remote sensing interpretable elements and does not mix management attributes. Taking the area of Beijing as an example, the first and second level was classified, demonstrating the feasibility of the technical approach of the classification system.

Although spatio-spectral and spatio-temporal fusion has been well explored, few efforts are made on integrating spatio-spectral-temporal features. As an intrinsic prior, low tensor-rank has been successfully taken into effect by current fusion models, most of which, however, resort to establishing an overall low-rank norm without performing factorization techniques thus have trouble capturing the latent high-order structure of hyperspectral data cube. To address that, a novel Anisotropicly Sparse (AS) tensor norm is developed to make the rank minimization a learnable process under Tucker decomposition. The AS norm enables the model to minimize the multi-linear tensor ranks if imposed on the core tensor after factorization, hence it significantly improves the model’s fusion performance. In the temporal domain, a Hadamard-product based variability descriptor is incorporated into the fusion model to map the former information to current time. Additionally, piece-wise smooth prior of the Tucker factors is employed by extra regularizers as supplement to the loss spatial information. With the Proximal Differential Matrix being developed for optimization, the proposed method reaches state-of-the-art results on both spatio-spectral and spatio-spectral-temporal fusion at low computational cost.

Aiming at easily and conveniently to acquire large-range of rice distribution, a novel rice sensitive radar index model of rice recognition using GF-3 satellite was proposed. Firstly, the characteristics of geographical environment and GF-3 data source used in the study area were analyzed. Secondly, the data preprocessing process of GF-3 satellite image was described. Thirdly, based on the analysis of the backscatter characteristics of rice in the study area, the idea of image pseudo color synthesis by constructing rice sensitive radar index band to enhance the contrast between rice information and background information was put forward. Fourthly, the CNN deep learning network model was used for the rice recognition. Finally, the extracted results were verified with the measured data and had good accuracy. The model proposed were relatively simple and easy to operate, which was also convenient for large-scale application in areas with similar geographical environment conditions.

Based on the systematic analysis of the current situation and main problems of ecological restoration in China, this paper summarized the technical flow of territorial space ecological protection and restoration project, as well as the core requirements for geospatial data. Then combined with the development status of China's natural resources Landsat and their major technical parameter characteristics, the core supporting product system of satellite remote sensing was designed, and an idea of Lifecycle stage-Theme-Scene-Element was proposed. Finally, by taking some typical cases as examples, the main application modes of the products were explained. The product system and application mode proposed can not only help the government improve the efficiency of ecological restoration management and data consistency by using remote sensing data and Hi-technologies such as artificial intelligence and quantitative remote sensing, but also help to promote widely application of China's natural resources Landsat in government management.

Recently, convolutional neural networks (CNNs) have been widely applied to hyperspectral image (HSI) classification due to their detailed representation of features. Nevertheless, the current CNN-based HSI classification methods mainly follow a patch-based learning framework. These methods are nonglobal learning methods, which not only limit the use of global information but also require a high computational cost. In this letter, an image-based global learning framework is introduced to HSI classification. Based on this framework, we propose a dual-channel convolutional network (DCCN) for HSI classification to maximize the exploitation of the global and multiscale information of HSI. The experimental results conducted on two real hyperspectral datasets indicate that our method is superior to other related methods in terms of both efficiency and accuracy for HSI classification.

Water clarity (Zsd) is a widely used quality indicator that can be estimated from remote sensing imagery. China’s newest generation Advanced HyperSpectral Imager (AHSI) onboard the ZY1-02D satellite is expected to enable accurate water clarity retrieval for inland waters, since AHSI can provide abundant band choices while its 30-m spatial resolution is advantageous for monitoring small inland water bodies. In this study, to retrieve Zsd from the ZY1-02D imagery for inland waters with varying turbidities, we propose a classification-based, semi-analytical method in which the red/blue band ratio is employed to distinguish clear to moderately turbid water and highly turbid waters. Two Quasi Analytical Approaches (QAAs), QAAv5 and QAAm14, are used to estimate the total absorption coefficient (a(λ)) and the backscattering coefficient (bb(λ)) for clear to moderately turbid water and highly turbid waters, respectively. The estimated a(λ) and bb (λ) are utilized to obtain the diffuse attenuation coefficient Kd, followed by the Zsd calculations. Compared with 70 matchups of in situ measured Zsd values (0–6.5 m), the ZY1-02D image-derived Zsd achieved an R2 of 0.98, with an average unbiased relative error and root mean square error of 29.1% and 0.52 m, respectively. In addition, the proposed method can yield Zsd with higher accuracies than that of optimized empirical models. Therefore, the ZY1-02D AHSI imagery can retrieve reliable Zsd for both clear (> 3 m) and turbid waters (0–3.0 m), thereby serving as a useful satellite data source for monitoring the water clarity of large-scale inland water bodies.

The nonoverlapped spectrum range between low spatial resolution (LR) hyperspectral (HS) and high spatial resolution (HR) multispectral (MS) images has been a fundamental but challenging problem for MS/HS fusion. The spectrum of HS data is generally 400–2500 nm, and the spectrum of MS data is generally 400–900 nm; how to obtain the high-fidelity HR HS fused image within the whole spectrum of 400–2500 nm? In this article, we proposed a band divide-and-conquer framework (BDCF) to solve the problem, by comprehensively considering spectral fidelity, spatial enhancement, and computational efficiency. First, the spectral bands of HS were divided into overlapped and nonoverlapped bands according to the spectral response between HS and MS. Then, a novel improved component substitution (CS)-based method by combing neural network was proposed to fuse the overlapped bands of LR HS. Then, a mapping-based method with the neural network was presented to construct the complicated nonlinear relationship between overlapped and nonoverlapped bands of the original LR HS data. The trained network was mapped to the fused overlapped HR HS bands to estimate the nonoverlapped HR HS bands. Experimental results on two simulated data sets and two realistic data sets of Gaofen (GF)-5 LR HS, GF-1 MS, and Sentinel-2A MS show that the proposed BDCF has superior performance in both high spectral fidelity and sharp spatial details, and it obtained competitive fusion behaviors compared with other state-of-the-art methods. Moreover, BDCF has relatively higher computational efficiency than optimal solution-based methods and deep learning-based fusion methods.

Fusing low spatial resolution (LR) hyperspectral (HS) data and high spatial resolution (HR) multispectral (MS) data aims to obtain HR HS data. However, due to bad weather and the aging of sensor equipment, HS images usually contain a lot of noise, e.g., Gaussian noise, strip noise, and mixed noise, which would make the fused image have low quality. To solve this problem, we propose the multiscale low-rank deep back projection fusion network (MLR-DBPFN). First, HS and MS are superimposed, and multiscale spectral features of the stacked image are extracted through multiscale low-rank decomposition and convolution operation, which effectively removes noisy spectral features. Second, the upsampling and downsampling network mechanisms are used to extract the multiscale spatial features from each layer of spectral features. Finally, the multiscale spectral features and multiscale spatial features are combined for network training, and the weight of the noisy spectrum features is reduced through the network feedback mechanism, which suppresses the noisy spectrum and improves the noisy HS fusion performance. Experimental results on datasets of different noise demonstrate that MLR-DBPFN has superior spatial and spectral fidelity, comparative fusion quality, and robust antinoise performance compared with state-of-the-art methods.

The Advanced Hyperspectral Imager (AHSI) is the second hyperspectral imager of China, which is also one of the most important payloads onboard the ZY1E satellite. In order to monitor the radiometric calibration status since its launch on 12 Sep. 2019, and thus provide supplementary on-board radiometric calibration, this paper conducts several vicarious radiometric calibration experiments for the ZY-1E AHSI. Five satellite observations over Dunhuang radiometric calibration site, one of the most relevant China Radiometric Calibration Sites (CRCS), were used. Surface reflectance, radiosonde data, aerosol optical depth (AOD) loading, and water vapor content were used to simulate the top of atmosphere (TOA) radiance at the entrance pupil of the satellite via MODerate resolution atmospheric TRANsmission (MODTRAN). Our results show that the vicarious radiometric calibration coefficients are relatively constant with the official coefficients: the mean relative differences are 5.55%, 5.64%, 7.02%, 5.07%, and 5.30% on 11 Jan, 17 Jan, 12 Feb, 07 May, and 23 Nov, 2021, respectively. The vicarious radiometric calibration coefficients were found in good agreement with the official ones according to the validation analysis based on different surface types, i.e., water and vegetation. Uncertainties of vicarious radiometric calibration due to AOD assumptions, AOD measurements, water vapor measurements, radiosonde data measurements, relative spectral response (RSR) shifts and surface reflectance measurements are also discussed in detail. The obtained results show that the ZY-1E AHSI exhibits good on-orbit radiometric status.

In recent years, a number of Chinese remote sensing satellites, including GF-1, GF-2, ZY-1 02C, have been launched and put into use. Compared with traditional application pattern of individual interpretation, continuous remote sensing images can support a more large scaled application in land and resources, known as the operational application. In this paper, an operational application system, which was designed and established since the year 2010, was introduced especially about its software architecture and several key regulations under complex network environment. The running of this system connect different individuals and sections to an integrate production line, supporting the producing and servicing of basic remote sensing images, senior remote sensing images, and thematic mappings of land and resources.

Infrared spectrums play an important role in the information extraction of rock and minerals. Spectrum simulation is a fundamental issue of land surface scene simulation and image simulation of remote sensing systems. Signal to Noise Ratio is regarded as an essential parameter of instrument and remote sensing image. In this study, we used MODTRAN to simulate apparent radiance and different levels of additive white Gaussian noise was added to the simulated spectrum. In the section of noise impact on object recognition, Spectral Feature Fitting was chosen to compare the fit of simulated spectra with different noise levels to reference apparent radiance spectra without noise. Relative error is also calculated for the accuracy assessment which is helpful for validation and improvement of instrument parameters.