The extraction of water bodies in densely built-up areas is often surrounded by complex background environments, with shadow regions caused by high-rise buildings in high-resolution remote sensing images being one of the most serious challenges in water body recognition research. Convolutional neural networks (CNNs) have significant research value in capturing spatial structures in images. Compared to other deep learning models, CNNs require fewer parameters and computational resources while effectively extracting local features, achieving satisfactory segmentation performance. However, in the existing high-resolution remote sensing images, the color and shape of shadow regions exhibit high similarity to water bodies. The use of single-scale structures and shared weights severely hinders the CNN model’s ability to accurately distinguish and extract water bodies under strong interference conditions. To address these issues, this letter proposes a lightweight CNN method (MSAttU-Net) to overcome the interference of urban shadow regions in large-scale high-resolution remote sensing images. First, a lightweight multibranch deep convolution module is constructed to expand the model’s receptive field and enhance its feature extraction capability. Second, a parallel attention mechanism module (P-Att) is introduced, consisting of parallel spatial and channel attention mechanisms. These are designed to improve the focus on water boundary and shape features as well as corresponding spectral information, reducing the interference from shadows and other noise in the images. Finally, a$1\times 1$convolution layer is used to generate pixel-level classification results. The proposed method’s performance is compared with that of contemporary CNN networks, including U-Net, Seg-Net, Res-Net, and Dense-Net, popular CNN networks, such as DeeplabV3+, HR-Net, and SegFormer, and the state-of-the-art (SOTA) networks, such as TransUnet, SwinUnet, and DS-TransUnet. The results indicate that the proposed model not only maintains a lightweight and efficient structure but also demonstrates exceptional capability in water body recognition and effectively overcoming shadow region interference.

For circular polarization transmitting linear polarization receiving (CTLR) compact polarimetric (CP) synthetic aperture radar (SAR) data, the volume scattering power proportion derived through CP decomposition, such as the$m\text {-}\alpha $decomposition algorithm, is typically overestimated. To address this issue, this study initially presents a theoretical analysis of the reason behind the overestimation of the volume scattering power proportion. The theoretical analysis reveals that the assumption “the volume scattering power proportion is$1\text {-}m$” employed by the$m-\alpha $decomposition indeed leads to an overestimation, where m represents the degree of polarization. Subsequently, a novel and smaller form of the volume scattering power proportion has been discovered, namely ($1\text {-}m)^{2}$. Based on this finding, a modified$m\text {-}\alpha $decomposition algorithm has been proposed. Experiments were conducted using two fully polarimetric SAR images and a CP SAR image acquired by E-SAR, GF-3, and RISAT. The experimental results demonstrate that: 1) ($1\text {-}m)^{2}$is statistically closer to the actual volume scattering power proportion than$1\text {-}m$; 2) the decomposition performance of the modified$m\text {-}\alpha $decomposition algorithm surpasses that of the other six compact decomposition algorithms; and 3) employing the new volume scattering power proportion ($1\text {-}m)^{2}$effectively mitigates the issue of volume scattering power overestimation in CP decomposition.

In this study, Sentinel-1 image data with all-weather observation characteristics and Sentinel-2 image data with medium and high spatial and temporal resolution were used to explore the optimal feature scheme suitable for coastal wetland classification. The optimal feature combination scheme will be put into the UNet network and applied to the mangrove classification in the coastal area of Shenzhen. In addition, we added DCN structure to the model, which can better extract mangrove features compared with traditional methods. The experimental results showed that the mangrove area in Shenzhen showed an overall increasing trend in the past four years, which proved that the local mangrove restoration process had a certain effect.

To support the operational response for ships in distress and oil spills, a space-air-sea-ground integrated monitoring network-based forecasting system was constructed. A three-layered structure of the framework was designed, including sensing layer, network layer and application layer. The observations are collected by space-air-sea-ground sensors, followed with the transmission by the network layer. These observations are received and processed, and are then combined with the forecasting. The coverage, availability and reliability of various observations are discussed. The uncertainty in forecasting and the approach to improve its performance are studied. The system was applied to the uncontrolled ship and the following oil spill from Sanchi accident occurred in East China sea in 2018. The space-bore synthetic aperture radar (SAR) observations for ship and oil spill are verified by air-borne SAR observations and on-site observations. The accuracy of the forecasting trajectory is improved by integrating more observations. The uncertainty in the forecasting is accounted for by an ensemble of the available wind and current forcing, in order to improve the reliability of the conclusions. The monitoring and forecasting play a complementary role, which have improved the support to maritime transportation emergency response.

With the acceleration of urbanization, the impact of human activities on the ecological landscape pattern has become more and more serious. The contradiction between population, resources and ecological environment become more noticeable. The monitoring and evaluation of urban ecological pattern is of great significance for sustainable development, and provides decision-making basis for urban construction department on ecological construction and urban and rural planning.The ecological corridor between the ecological control lines is a region with relatively severe changes. The establishment of an ecological corridor is important for landscape ecological planning, and it is an important measure to solve the landscape fragmentation caused by the current human activities and the numerous environmental problems.In this paper, we use high-resolution remote sensing satellite data, combined with the ecological community classification method of projection pursuit, taking Shenzhen as an example, effectively construct the ecological corridor landscape index, analyze the corridor function, and evaluate the importance of various ecological corridors. The research results provide a scientific guide for urban planning and ecological protection.

HY-2B satellite is launched on 25thOct, 2018 at Taiyuan satellite launch center. It carried four main payloads: radar altimeter, microwave scatterometer, scanning microwave radiometer, and corrected microwave radiometer. HY-2B microwave scatterometer (HY-2B/SCAT) is a pencil-beam rotating scatterometer, which is simillar to HY-2A microwave scatterometer (HY-2A/SCAT). HY-2B satellite is in the same orbit of HY-2A, and about 30 min ahead of HY-2A. The HY-2B microwave scatterometer started to work on 30thOctober, after days of testing. The performance of HY-2B/SCAT become stable since 14th, Nov. This paper provied some preliminary results of HY-2B/SCAT data, such as pulse power DN value, sigma0, retrieved sea surface wind field.

Taking Yongle Atoll of Xisha Islands as the research area, the information extraction of reef landforms is studied by using the characteristics of HY-1C satellite wide-band, wide-spectrum and short revisit period. The calculation of CZI band histogram and signal-to-noise ratio shows that the images signal to noise ratio in the four bands of CZI of HY-1C satellite is 0.84 and the coverage value of the blue band is 28.53, which is the most obvious in the island landform, while the information of red band is not so obvious about the island reef. The payload CZI can express the information of coral reefs, and unsupervised classification method can be used to obtain the information of reefs, but the information of underwater reef flats is easy to be misjudged. In order to make full use of the band information of the HY-1C satellite, the weights of each band to the reef information expression are established by using the analytic hierarchy process (AHP). Based on the weight composite image, the information of reefs is extracted by supervised classification method, which will lead to effective extraction of information of natural islands, sandy beaches, underwater reef flats, hidden sand, gullies and so on. By consistency test, the Kappa coefficient can reach 89.97%, which can meet the requirements of large-scale and high-frequency island reef survey on the basis of medium-resolution remote sensing images.

How to extract oil spill information accurately with full polarization SAR data is the current problem, Polarization decomposition is one of the effective ways to improve the accuracy of oil spill information detection. Based on the polarization decomposition parameter entropy H, scattering Angle and anti-entropy A, this paper analyzes polarization decomposition parameters and carries out extraction of oil spill information. In the light of the similar characteristics of oil spill in entropy H and scattering angle parameters, platform and ship is analyzed, which bring the false of oil spill, and various indexes are constructed. From scattering mechanism and test results, established the index of the oil spill information extraction, combined with the oil spill features, this paper proposes a simple and effective information automatic extraction method of oil spill, The accuracy is about 71.4%, which can meet the needs of oil spill operation monitoring.

Plant community is a significant content in the ecosystem. Traditional investigation method for plant community is mainly based on field sampling, which is limited by the data acquisition from complex terrain areas. In contrast, high-resolution remote sensing technique provides a convenient way to quickly access data in a large area. higher dimensional information is needed to distinguish more fine features. To overcome the shortcomings derived from the high dimensional features, which is caused by related data increasing, we choose the algorithm of projection pursuit learning network (PPLN) along with field samples of typical plant communities to realize a fast classification on the vegetation in the east of Shenzhen. Then, in the experiment, the spectral and texture information extracted from Pléiades images, and the terrain interpolated from topographic map are selected and used to build high dimensional features, which is crucial to the vegetation classification using remote sensing images. The learning network for projection pursuit is applied to discriminating the typical communities in both plantation and natural secondary forest in the study area. Compared with Maximum-likelihood classification (MLC) and Support Vector Machine (SVM), PPLN can achieve more accurate results for plant community classification. As a conclusion, the plant community classification with PPLN meets the requirements of the investigation project, achieves the quick updating of some basic information related to forest resources, and looks forward to involve in some other ecological research as well.

This paper analyzes land use dynamic changes during latest 10 years in Huabei region based on RS and GIS. Huabei region includes four provinces (Hebei, Shanxi, Shandong and Henan), two cities (Beijing, Tianjing) and one municipality of Inner Mongolia. This region is Chinese center of politics, economy and culture, also important food supplies base. So the study of Huabei region is very significant. Using 1990, 1995 and 2000 TM images as a primary data source and processing by atmosphere and geometric correction, we get two dynamic coverages (1990-1995 and 1995-2000) by visual interpreting under MGE environment. Then we select Huabei region dynamic coverages. In ARC/INFO GRID, these coverages are changed into 100 m*100 m grid format. In the past 10 years, the farmland is increasing, especially in dry land; forest and grassland is decreasing and urban increases rapidly. Farmland shifting urban is the most land change; Secondly, grassland shifting farmland has a bigger proportion. According to land use zone, Huabei locates in two zones: one is huanghuaihai farmland shifting urban, which shows dry land is changing into county; The other is ecotone between agriculture and animal husbandry, which focus grassland shifting farmland in inner Mongolia. The past 10 years can be divided into two periods of time (1990-1995 and 1995-2000). Comparing the two periods of time, in huanghuaihai farmland shifting urban, the decrease of farmland and increase of urban in 1990-1995 is faster than that in 1995-2000; in the ecotone between agriculture and animal husbandry, the velocity of farmland increase in 1990-1995 is evidently greater than that in 1995-2000. And the ecotone between agriculture and animal husbandry has more obvious changes.

This paper analyses grassland dynamics in China from 1995 to 2000 under different aridity based on remote sensing (RS) and a geographic information system (GIS) to discover the rule in it. The results show that the amount of grassland is reduced to 5.49/spl times/10/sup 4/ hm/sup 2/. There is heavy grassland degradation in the arid region, especially at low cover grass. The main change is becoming farmland and grassland and grass resource having different degrees of degeneration. The main reason of grassland changing into farmland is population pressure; grassland degradation is caused by over grazing, etc. Because grassland lies in the west and north of China, its area reduction and grass cover decrease will lead to a worse north China environment. Moreover the grassland decrease will restrict regional economical development.

We monitor dynamic of china grassland from 1995 to 2000 by using TM datum based RS and GIS technology. The datum are extracted from LANDSAT TM image. The task of image classification is mainly taken on by experts with the help of relief map, navigation photo etc, thus grassland coverage could be acquired. With the high and middle cover grassland area increasing, but the area of low cover grassland is much decreasing. The area of west china grassland is decreasing, such as Shanxi,Qinghai,Gansu province etc, especially inner Mongolia and Xinjiang. There exists huge gap between west china and east china in grassland change. The change degree of west china grassland is great than east china's. Human activities have great impact on grassland change. The main shifting is farmland and urban, which shows economy gap between west china and east china. Meanwhile, there is heavy degradation in grassland change, especially in west china.

While farmland less is recognized as a global farmland resource problem, little is known on a wide scale about the relationships between farmland and altitude. This study analyzes the dynamic distribution of Chinese farmland from mid-1980s to 2000 for different altitudes. Farmland dynamic coverage is obtained by visual interpreting mid-1980s and 2000 TM images under MGE environment and other data. All data are changed into 100m*100m grid format. Then we overlay it with DEM data with scale 1:250000 in ARC/INFO GRID module. During the last 15 years, some people think that farmland in China has been reduced drastically with increasing population pressure and agricultural activities. This paper announces that in some districts the farmland was reduced, yet in some other districts the farmland was enhanced. For paddy field, the area below 100 meters is reduced. From 100 to 200 meters, the area is increased with great speed. From 200 to 500 meters and from 1000 to 1500, the area is becoming bigger although the range is small. From 500 to 1000 meters and above 1500 meters, the area is, almost unchanged. For dry land, the area below 100 meters is reduced no more than the paddy field's. Above 100 meters, the area is increased. From 200 to 500 meters and from 1500 to 2000 meters, the range of increased area is great. Except that, the change is not obvious.

Using 1980s and 2000 TM as a primary data source and processing by atmosphere and geometric correction, we get dynamic coverage by visual interpreting under MGE environment. Then we select Inner Mongolia grassland dynamic coverage. In GRID, this coverage is changed into 100 m*100 m as a mask. According to the conditions of study area, we choose slope, aridity, soil erosion etc as environment background factors. We get environment background coverage under mask coverage. Finally, we combine the grassland coverage and every environment background coverage under GRID. The shifting farmland and grassland is main change of grassland in Inner Mongolia, whereas the shifting urban less, moreover grassland degradation is becoming serious. Grassland change fastens on several degrees of environment index because of region law restrict and transition characteristic, which lies the change value getting its max at middle index and min at both of end. What the grassland change happens cover the good environment, which shows the nature limit. The most bigness change area of grassland is high cover grassland and the most smallness is low cover grassland. With the degree of grassland cover decreasing, the grassland degradation is getting more serious.

This paper studies on dynamics of Chinese grassland resources during 1995 and 2000 under different aridity supported by GIS and RS based on TM images. We get the grassland dynamic coverage under MGE environment by contrasting 1995 and 2000 TM images. The results show there is an obvious zonal distribution under different aridity; grassland is changed to farmland in high cover grassland, especially at 4,5,6 degree which mainly distributes in west and north of China; grassland was replaced by urban areas at each aridity and grassland degradation. The change area between grassland changed into farmland and grassland is about same, but shifting into farmland shows the grassland decrease; a lot of grassland is changed into forest. With the aridity degree increasing, the degradation becomes serious, especially at 4,5 degree. But at I degree, the main change is that grassland changed to forest. The urban takes place of grassland in each aridity. But the mainly change is becoming farmland and grassland and grass resource having different degree degeneration. The main reason of grassland changing into farmland is population pressure; grassland degradation is caused by over graze etc.