High accuracy and time synchronous aerosol optical depth (AOD) is essential for atmospheric correction (AC) of medium and high spatial resolution (MHSR) remote sensing data. However, existing high-resolution AOD retrieval methods often rely on sparsely distributed ground-based measurements, which limits their capacity to resolve fine-scale spatial heterogeneity and consequently constrains retrieval performance. To address this limitation, we propose a framework that takes GF-1 top-of-atmosphere (TOA) reflectance as input, where the model is first pre-trained using MCD19A2 as Pseudo-labels, with high-confidence samples weighted according to their spatial consistency and temporal stability, and then fine-tuned using Aerosol Robotic Network (AERONET) observations. This approach enables improved retrieval accuracy while better capturing surface variability. Validation across multiple regions demonstrates strong agreement with AOD measurements, achieving the correlation coefficient (R) of 0.941 and RMSE of 0.113. Compared to models without pretraining, the proportion of AOD retrievals within EE improves by 13%. While applied to AC, the corrected surface reflectance also shows strong consistency with in situ observations (R > 0.93, RMSE < 0.04). The proposed Trans-AODnet significantly enhances the accuracy and reliability of AOD inputs for AC of high-resolution wide-field sensors (e.g., GF-WFV), offering robust support for regional environmental monitoring and exhibiting strong potential for broader remote sensing applications.

Cloud detection in satellite imagery plays a pivotal role in achieving high-accuracy retrieval of biophysical parameters and subsequent remote sensing applications. Although numerous methods have been developed and operationally deployed, their accuracy over challenging surfaces—such as snow-covered mountains, saline–alkali lands in deserts or Gobi regions, and snow-covered surfaces—remains limited. Additionally, the efficiency of collecting training samples for prevalent deep learning-based methods heavily relies on large-scale pixel-level annotations, which are both time-consuming and labor-intensive. To address these challenges, we propose a Texture-Enhanced Network that integrates an object-oriented dynamic threshold pseudo-labeling method and a texture-feature-enhanced attention module to enhance both the efficiency of deep learning methods and detection accuracy over challenging surfaces. First, an object-oriented dynamic threshold pseudo-labeling approach is developed by leveraging object-oriented principles and adaptive thresholding techniques, enabling the efficient collection of large-scale labeled samples for challenging surfaces. Second, to exploit the spatial continuity of clouds, cross-channel correlations, and their distinctive texture features, a texture-feature-enhanced attention module is designed to improve feature discrimination for challenging positive and negative samples. Extensive experiments on a Chinese GaoFen satellite imagery dataset demonstrate that the proposed method achieves state-of-the-art performance.

Satellite-derived aerosol optical depth (AOD) products from MODIS and VIIRS sensors are vital for monitoring global aerosol distributions. However, inconsistencies in quality control algorithms and spatial resolution introduce errors that complicate validation processes and reduce the accuracy of satellite-to-ground comparisons. This study proposes the “optimal” spatial matching method to minimize these errors and enable a more accurate evaluation of retrieval algorithm performance. Using AERONET ground observations from 2012 to 2021, MODIS and VIIRS AOD products were systematically validated with three spatial matching methods—“direct”, “average”, and “optimal”. Results demonstrate that the “optimal” method consistently outperformed the other methods by selecting pixel values. The study highlights significant quality control disparities across AOD products and demonstrates that high-resolution products, with purer pixels, achieve superior accuracy under the “optimal” method. These insights provide valuable guidance for optimizing dataset applications and refining aerosol retrieval algorithms.

The Qilian Mountain Area (QMA) serves as a crucial ecological barrier and strategic water conservation zone in China. Recent years have seen heightened social attention to environmental issues within the QMA, underscoring the need for accurate and continuous land cover maps to support ecological monitoring, analysis, and forecasting. This paper presents the QMA_LC30 dataset, which includes 9 land cover categories and spans the period from 1990 to 2020, with updates every 5 years. The dataset primarily utilizes 30 m Landsat series data and features: 1) High precision, achieved through a geographical division and hierarchical classification decision tree approach, complemented by visual interpretation. 2) Robust consistency, ensured by a change detection method based on a benchmark map. The QMA_LC30 dataset undergoes rigorous accuracy validation, achieving an overall accuracy of over 0.92 for all 7 periods of land cover maps. Compared to GlobeLand30, ESA WorldCover, ESRI 2020 Land Cover, FROM_GLC30, and GLC_FCS30, QMA_LC30 demonstrates the highest consistency with remote sensing images.

Long time series of annual land cover with fine spatio-temporal resolutions play a crucial role in studying environmental climate change, biophysical modeling, carbon cycling models, and land management. Despite a strong consistency exhibited by several publicly available medium to fine resolution global land cover datasets, significant discrepancies exist at the regional scale; moreover, only every 5/10 year land cover were available. Consequently, high-quality annual land cover datasets before 2000 are unavailable in China. In this study, we proposed a deep learning-based method by integrating multiple remote sensing data from different platforms with historical high spatial resolution land cover datasets (CNLUCC) to derive the 30 m annual land cover maps from 1980 to 1990 for Qilian Mountain. First, the super-resolution generative adversarial network models for upscaling the 5.5 km AVHRR NDVI to 250 m were established by employing the AVHRR and MODIS NDVI data with the same year as input, and the early time series AVHRR NDVI data were subsequently upscaled to 250 m through the above models. Second, the breaks for the additive seasonal and trend (BFAST) change detection algorithm was applied to the upscaled time series NDVI data to detect the change time of different land cover types. Third, the CNLUCC data in 1980 and 1990 were updated to annual land cover datasets from 1980 to 1990 and the annual mapping results provided insights into the dynamic processes of urbanization, deforestation, water bodies, and farmland from 1980 to 1990. Finally, comprehensive analysis and validation were carried out for evaluation and an overall accuracy of 77.26% for the land cover product in 1986 was achieved.

Accurate and timely extraction and evaluation of sandy land are essential for ecological environmental protection; it is urgent to do the research to support the sustainable development goals (SDGs) of Land Degradation Neutrality. This study used Sentinel-1 Synthetic Aperture Radar (SAR) data and Landsat 8 OLI multispectral data as the main data sources. Combining the rich spectral information from optical data and the penetrating advantages of radar data, a feature-level fusion method was employed to unveil the intrinsic nature of vegetative cover and accurately identify sandy land. Simultaneously, leveraging the results obtained from training with measured data, a comprehensive desertification assessment model was proposed, which combines multiple indicators to achieve a thorough evaluation of sandy land. The results showed that the method based on feature-level fusion achieved an overall accuracy of 86.31% in sandy land detection in Gansu Province, China. The integrated multi-indicator model C22_C/FVC is the ratio of correlation texture features of VH to vegetation cover based on which sandy land can be classified into three categories. When C22_C/FVC is less than 2.2, the pixel is classified as fixed sandy land. Pixels of semi-fixed sandy land have an indicator value between 2.2 and 5.2. Shifting sandy land has values greater than 5.2. Results showed that shifting sandy land and semi-fixed sandy land are the predominant types in Gansu Province, with 85,100 square kilometers and 87,100 square kilometers, respectively. The acreage of fixed sandy land was the least, 51,800 square kilometers. The method presented in this paper is robust for the detection and evaluation of sandy land from satellite imageries, which can potentially be applied for conducting high-resolution and large-scale detection and evaluation of sandy land.

Vegetation plays a fundamental role within terrestrial ecosystems, serving as a cornerstone of their functionality. Presently, these crucial ecosystems face a myriad of threats, including deforestation, overgrazing, wildfires, and the impact of climate change. The implementation of remote sensing for monitoring the status and dynamics of vegetation ecosystems has emerged as an indispensable tool for advancing ecological research and effective resource management. This study takes a comprehensive approach by integrating ecosystem monitoring indicators and aligning them with the objectives of SDG15. We conducted a thorough analysis by leveraging global 500 m resolution products for vegetation Leaf Area Index (LAI) and land cover classification spanning the period from 2016 to 2020. This encompassed the calculation of annual average LAI, identification of anomalies, and evaluation of change rates, thereby enabling a comprehensive assessment of the global status and transformations occurring within major vegetation ecosystems. In 2020, a discernible rise in the annual Average LAI of major vegetation ecosystems on a global scale became evident when compared to data from 2016. Notably, the ecosystems demonstrating a slight increase in area constituted the largest proportion (34.23%), while those exhibiting a significant decrease were the least prevalent (6.09%). Within various regions, such as Eastern Europe, Central Africa, and South Asia, substantial increases in both forest ecosystem area and annual Average LAI were observed. Furthermore, Eastern Europe and Central America recorded significant expansions in both grassland ecosystem area and annual average LAI. Similarly, regions experiencing notable growth in both cropland ecosystem areas and annual average LAI encompassed Southern Africa, Northern Europe, and Eastern Africa.

Grasslands represent the largest ecosystem in China, accurate and efficient extraction of its integrated vegetation cover (IVC) plays a crucial role in supporting policy decisions. This study presented a method for grassland monitoring via IVC derived from high-resolution satellite data. Taking the multispectral data of Gaofen-1 (GF-1) and Gaofen-6 (GF-6) with 16 m resolution as the main data source, vegetation cover of six representative regions was assessed based on mixed-pixel decomposition model. Using grassland vegetation cover and ratio of grassland area, the IVC in each site was calculated and verified against ground-measured sample data. The results showed that the IVC of grassland was closely related to vegetation habitat driven by regional hydrothermal regime. Yichang grassland, dominated with warm-temperate shrub tussock type, had the highest IVC (80.06 %) due to its favorable hydrothermal conditions. For the main grassland types in Hulunbuir and Gansu Province (temperate meadow steppe and temperate typical steppe), the IVC was 79.38 % and 58.46 %, respectively. In both Xilin-Gol and Nagqu, vegetation cover decreased gradually from east to west, and the IVC was merely 42.83 % and 42.61 %, respectively. Both regions are endowed with less hydrothermal resources to different degrees. Alxa, with a predominately temperate desert landscape, had the lowest IVC of 15.58 % where precipitation is extremely scarce. Based on the grass species of measured samples, the dominant species and biodiversity of different grassland types in Gansu Province and Hulunbuir Municipality of Inner Mongolia Autonomous Region were analyzed. The results showed that the meadow grassland has the richest biodiversity. The temperate mountain meadows in Gansu Province have a high species diversity, with a total of 90 grass species, and the lowland meadows in Hulunbuir have a total of 49 grass species. This study utilizes high-resolution data to conduct largescale vegetation monitoring, which is a viable alternative for efficient assessment of steppe ecology.

Photosynthetically Active Radiation（PAR） is an important input of vegetation productivity models, and also a key parameter of terrestrial ecosystem models and biogeochemical models. The accuracy and availability of current global or regional products are still insufficient to better understanding Earth system. China has launched series of Gaofen（GF） Earth observation satellites and provide the possibility of high spatial resolution PAR products retrieval. In this paper, a new method based on a parametric model for remote sensing inversion of PAR was proposed. The surface albedo products and the aerosol optical depth products were retrieved from GF-1 satellites, the cloud optical thickness products were retrieved from Himawari-8 and FY-4 satellites. Under clear sky conditions, the attenuation of PAR by aerosol and Rayleigh scattering is mainly considered. The influence of cloud on incident radiation is mainly considered for cloudy skies, and the calculation is based on the Mie scattering theory of spherical particles. Surface received direct PAR for rugged surfaces were calculated with the input of incident angle, the slope and the aspect. The enhancement or attenuation effect of the scattered radiation were retrieved using the sky view factor the horizontal surface received diffuse radiation. The PAR products were compared and verified using the continuous observation data of the ground stations collected from the Hebei Huailai, the Heihe River Basin Surface Process Comprehensive Observation Network and Ganyansuo in Chengdu. The correlation coefficient, mean bias error and the root mean square error between the two datasets were 0.87, 1.56 W/m2 and 16.14 W/m2, respectively. The spatial resolution of the input atmospheric parameters（sub-satellite point 1 km） and the surface parameter resolution（16 m） of the PAR products have a large spatial scale difference. The atmospheric parameters with the resolution of 50 m provided by the GF-4 satellite will be used to further improve the spatiotemporal accuracy of GF PAR products, and more extensive and in-depth verification analysis will be carried out in our future study.

The Fraction of absorbed Photosynthetically Active Radiation（FPAR） is one of the key parameters in the light use efficiency model of the carbon cycle. High-spatiotemporal-resolution data have been provided for the inversion of quantitative remote sensing products since the launch of GF satellites. The FPAR products derived from GF satellite data provide precise and accurate input parameters for the analysis and evaluation of the ecosystem’s carbon cycle. In this study, a deep learning algorithm was developed to retrieve FPAR over China based on the simulated data of the radiative transfer model. The inputs are surface reflectance, cloud detection, and land cover products of GF-1 satellite data, whereas the output is FPAR. The FPAR product has a spatial resolution of 16 m and a temporal resolution of 10 days.This method uses the SAIL model to simulate output canopy FPAR and reflectance under various input variables, such as solar and observing angles and atmospheric conditions. The FPAR inversion model of GF-1 satellite data was obtained using a deep belief network.The long-term crop and grassland FPAR observation data in Huailai and Heihe were used to compare and validate the FPAR products, with a root mean square error of 0.15 and 0.17, respectively. The inversed FPAR is in good agreement with the measured FPAR in the low values,but lower than the measured FPAR in the high values. The radiative transfer model, the representativeness of the simulated data, and the preprocessing（calibration and geometric and atmospheric correction） of the GF-1 satellite data inevitably introduce some biases in the inversion process. This method uses the multidimensional atmospheric and surface variables as the input and the simulated vegetation canopy by the radiative transfer model parameters as the output. The simulated dataset, used as the training samples for deep learning, makes up for the errors in the deep learning training process caused by the insufficient number of training samples and incomplete observation data.The input of the inversion is only the surface reflectance product with the information of the sun angle and the observation angle. It lessens the difficulty of obtaining input parameters, reduces the influence of the error transmission of the input parameters, and is conducive to the realization of the commercial production of the product. The high FPAR is mainly distributed in the northeast, north, central, east, southwest,and south parts of China. The interannual variation of the FPAR time series, combined with the vegetation growing cycle and phenology, is high in spring and summer and low in autumn and winter.

Land surface albedo is a critical parameter in radiation and energy budget. Using GF satellite data to produce the land surface albedo is beneficial for local-scale environmental monitoring.The challenge beneath the albedo estimation from the GF satellite data is the inadequate angular information, which complicates the BRDF inversion and the albedo derivation based on BRDF. We use the high spatial-and-temporal-resolution priori-knowledge BRDF database obtained from coarse spatial resolution multiangular information to help describe the GF BRDF features. Then, the GF albedo is estimated from the derived GF BRDF. The algorithm is applied in GF-1 data to generate the land surface albedo product in China. First, this algorithm and the production are introduced briefly. Then, the spatial-temporal features are evaluated by qualitative analysis and quantitative validation. In the validation, a long time series of field-measured albedo from the sites of different land covers is used. It includes the cropland（maize） in the Daman site from the Heihe remote sensing test site located in the northwest of China, the forest（Chaenomeles,metasequoia, Chinese pine） in the Huailai test remote sensing site located in the north of China, and the grass in the Dongbei remote sensing test site located in the northeast of China. These sites would be covered by bare soil or snow in winter. In this study, we preliminarily evaluate the algorithm feasibility in albedo production and product precision.The time series comparisons of the field measurements and the GF product present good agreement for different sites over 1 year to 2years. For over 1-or 2-year time-continuous comparisons, the land surface status is changed driven by the phenology（vegetation growing cycle）. Thus, this finding reveals the feasibility of the algorithm based on the spatial-temporal distributed BRDF a priori knowledge. The total root mean square error is 0.05, with a relative accuracy of 80.24%, which meets the application requirement.Therefore, this algorithm is feasible for the albedo estimation from the GF data. The validation results show a good agreement between the field measurements and the product. However, the remote sensing common products from GF satellite data have not been initiated long enough. Thus, evaluating the GF satellite data is still needed. Besides the algorithm itself, the albedo accuracy is directly affected by the land surface reflectance product’s precision, which may introduce uncertainties from the geometric and radiometric calibration, atmospheric correction, and even cloud production. Therefore, much work should be done to evaluate this product and clarify the effects of those factors.In this way, the algorithm and albedo production can be improved.

Fractional Vegetation Cover（FVC） is a critical parameter for monitoring vegetation growth status. Remote sensing effectively generates FVC at a large scale. However, the spatial resolution of the existing FVC products at the global scale is more than 300 m. The major limitation of the FVC produced from high-spatial-resolution satellite images is the lack of effective observations, mainly due to a small range of view and long periods of revisit time for satellite images with 30 m or higher spatial resolutions. The Chinese GaoFen No. 1satellite（GF-1） wide-field view data with 16 m spatial resolution and 4-day revisit time provide an available data resource for FVC extraction. The objective of this study is to assess the quality of the 16 m/10-day FVC product based on GF-1 images from 2018 to 2020.The assessment of the GF-1 FVC product was accomplished through direct validation with ground measurements and indirect validation with the GEOV3 FVC product. Two FVC products were postprocessed with the same temporal（month） and spatial（300 m）resolution to compare GF-1 FVC with 16 m/10-day and GEOV3 FVC with 300 m/10-day. A total of 32 ground measurements（including 18ground measurements for crops and 14 ground measurements for forest） throughout the growing season at the middle reach of Heihe River Basin, the Jingyuetan station, and the Saihanba plantation forestry farm were used to validate the FVC product in China. The indirect validation was evaluated by the spatial and temporal continuity with missing values and the product consistency with GEOV3 FVC.The percentage of the annual missing value lower than 70% accounted for 88% of the main land in China. During the growing season,the percentage of the annual missing value lower than 73.68% approached 82.73%. According to different inversion algorithms and input products, the percentage of the average missing value of forest types（＞20%） was higher than that of nonforest types, such as crops and grassland（＜10.6%）. The GF-1 FVC agreed well with GEOV3 FVC for the nonforest type based on the homogeneous samples in China from January to December 2019. The direct validation results indicated that the accuracy for the FVC product achieved by the GF-1 FVC product is reasonable compared with the ground measurements（R2 = 0.57, root mean square error = 0.12, BIAS =-0.03） in China. Moreover, it is better than the accuracy achieved by the GEOV3 FVC product, particularly for forest type.In conclusion, the GF-1 FVC product of China with 16 m/10-day resolution reflects the seasonal characteristics of vegetation well.Moreover, the GF-1 FVC product with high spatial and temporal resolutions meets the requirements of vegetation monitor at the regional scale.

Following the success of MODIS, several widely used algorithms have been developed for different satellite sensors to provide global aerosol optical depth (AOD) products. Despite the progress made in improving the accuracy of satellite-derived AOD products, the presence of sub-pixel clouds and the corresponding cloud shadows still significantly degrade AOD products. This is due to the difficulty in identifying sub-pixel clouds, as they are hardly identified, which inevitably leads to the overestimation of AOD. To overcome these conundrums, we proposed an improved deep learning network for retrieving AOD from remote sensing imagery focusing on sub-pixel clouds especially and we call it the Sub-Pixel AOD network (SPAODnet). Two specific improvements considering sub-pixel clouds have been made; a spatial adaptive bilateral filter is applied to top-of-atmosphere (TOA) reflectance images for removing the noise induced by sub-pixel clouds and the corresponding shadows at the first place and channel attention mechanism is added into the convolutional neural network to further emphasize the relationship between the uncontaminated pixels and the ground measured AOD from AERONET sites. In addition, a compositive loss function, Huber loss, is used to further improve the accuracy of retrieved AOD. The SPAODnet model is trained by using ten AERONET sites within Beijing-Tianjin-Hebei (BTH) region in China, along with their corresponding MODIS images from 2011 to 2020; Subsequently, the trained network is applied over the whole BTH region and the AOD images over the BTH region from 2011 similar to 2020 are retrieved. Based on a comprehensive validation with ground measurements, the MODIS products, and the AOD retrieved from the other neural network, the proposed network does significantly improve the overall accuracy, the spatial resolution, and the spatial coverage of the AOD, especially for cases with sub-pixel clouds and cloud shadows.

叶面积指数(leaf area index,LAI)是研究植被生态系统结构和功能的核心参数之一,遥感是获取大范围动态LAI的一个主要技术手段.但目前国际上没有高分辨率的LAI标准化产品,本研究利用高分一号(GF-1)宽幅相机高时空分辨率的特点,基于三维随机辐射传输模型生产了MuSyQ(Multi-source data Synergized Quantitative remote sensing production system)高分系列中国地区2018–2020年16米/10天分辨率的标准化LAI产品01版.本产品可为中国地区植被变化分析、农林业示范应用、生态环境监测提供可靠的数据支撑.

植被指数(Vegetation Index,VI)是植被遥感研究和应用的最重要参数之一.目前标准化的区域或全球范围的高分辨率植被指数产品较少.本文针对高分一号(GF1)宽幅相机高时空分辨率的特点,基于植被指数合成算法生产了中国2018–2020年MuSyQ高分16米/10天分辨率的归一化植被指数(NDVI)产品.本产品可用于监测中国区域植被的结构、物候特征,分析生化理化参数的季节、年际及长期的变化等,为中国地区植被变化分析、农林业应用、生态环境监测提供可靠的数据支撑.

植被覆盖度(fractional vegetation cover,FVC)是衡量地表植被状况的重要指标之一.卫星遥感是获取大范围动态FVC的主要技术手段.但目前国际上并没有高分辨率的FVC标准化产品,本文利用高分一号(GF-1)宽幅相机高时空分辨率的特点,针对森林类型基于孔隙率方法、针对非森林类型基于归一化植被指数(NDVI)像元二分法生产了多源协同定量遥感产品生产与服务系统(MuSyQ)高分系列中国2018–2020年16米/10天FVC产品.本产品为中国植被遥感监测提供数据支撑.

Analysis Ready Data (ARD) has been greatly recommended by the Committee on Earth Observation Satellites (CEOS) for simplifying and fostering long time series analysis at large scale with minimum additional user effort. Landsat ARD has been successfully made and widely used for large scale analysis. Subsequently, the Chinese satellite data similar to Landsat data have been processed and will be processed into ARDs to promote the use of the Chinese satellite data. At the first stage of the mission, the 4 Wide Field Viewing (WFV) data on GaoFen 1 (GF1) covering the whole of China and the surrounding areas have been processed into ARD. The ARD is provided as standard tiles under a common and unified projection with per pixel quality assurance and metadata for tracing back and further processing data, which are finally stored into a Hierarchical Data File (HDF); furthermore, all spectral bands are georegistered and radiometrically cross-calibrated as top of atmosphere (TOA) reflectance and are atmospherically corrected as surface reflectance (SR). Therefore, the ARD can be further used easily to produce land cover and land cover change maps and retrieve geophysical and biophysical parameters.