GF-1 Images Research Articles

Spatiotemporal Point–Trace Matching Based on Multi-Dimensional Feature Fuzzy Similarity Model

Identifying ships is essential for maritime situational awareness. Automatic identification system (AIS) data and remote sensing (RS) images provide information on ship movement and properties from different perspectives. This study develops an efficient spatiotemporal association approach that combines AIS data and RS images for point–track association. Ship detection and feature extraction from the RS images are performed using deep learning. The detected image characteristics and neighboring AIS data are compared using a multi-dimensional feature similarity model that considers similarities in space, time, course, and attributes. An efficient spatial–temporal association analysis of ships in RS images and AIS data is achieved using the interval type-2 fuzzy system (IT2FS) method. Finally, optical images with different resolutions and AIS records near the waters of Yokosuka Port and Kure are collected to test the proposed model. The results show that compared with the multi-factor fuzzy comprehensive decision-making method, the proposed method can achieve the best performance (F1 scores of 0.7302 and 0.9189, respectively, on GF1 and GF2 images) while maintaining a specific efficiency. This work can realize ship positioning and monitoring based on multi-source data and enhance maritime situational awareness.

Aboveground biomass inversion of forestland in a Jinsha River dry-hot valley by integrating high and medium spatial resolution optical images: A case study on Yuanmou County of Southwest China

It is crucial to develop a comprehensive method for estimating the aboveground biomass (AGB) of trees, shrubs, grasslands, and sparse tree areas in ecologically fragile dry, hot valley regions with vertical zonation. Multi-source remote-sensing data can fulfill this requirement, providing help in monitoring the health of ecosystems and providing a basis for regional biodiversity conservation and restoration. Sentinel-2A satellite imagery was used to classify the forests, shrubs, and grasslands in Yuanmou County, Chuxiong Yi Autonomous Prefecture, Yunnan Province, China. The Gaofen-2 satellite (GF-2) was used to extract the canopy width and calculate tree biomass in the valley-type savanna region. These data were combined with remote-sensing factors and measured survey data, and random forest (RF) and extreme gradient boosting (XGBoost) models were used to estimate the biomass. Using GF-2 images to segment sparse tree areas effectively reduced the overestimation of low-resolution remote-sensing images, enabling the AGB of sparse trees to be accurately estimated. The biomass estimations based on the Sentinel-2A images attained coefficient of determination (R2) values of 0.45 and 0.47 for the forest, 0.55 and 0.61 for the shrubs, and 0.32 and 0.37 for the grasslands using RF and XGBoost models, respectively, demonstrating variable effectiveness across vegetation types. In addition, the XGBoost model was more robust than the RF model for all three vegetation types. Our methodology provides scientific support for the sustainable development of ecologically fragile dry, hot valleys and savanna areas.

Comparison of Algorithms and Optimal Feature Combinations for Identifying Forest Type in Subtropical Forests Using GF-2 and UAV Multispectral Images

The composition and spatial distribution of tree species are pivotal for biodiversity conservation, ecosystem productivity, and carbon sequestration. However, the accurate classification of tree species in subtropical forests remains a formidable challenge due to their complex canopy structures and dense vegetation. This study addresses these challenges within the Jiangxi Lushan National Nature Reserve by leveraging high-resolution GF-2 remote sensing imagery and UAV multispectral images collected in 2018 and 2022. We extracted spectral, texture, vegetation indices, geometric, and topographic features to devise 12 classification schemes. Utilizing an object-oriented approach, we employed three machine learning algorithms—Random Forest (RF), k-Nearest Neighbor (KNN), and Classification and Regression Tree (CART)—to identify 12 forest types in these regions. Our findings indicate that all three algorithms were effective in identifying forest type in subtropical forests, and the optimal overall accuracy (OA) was more than 72%; RF outperformed KNN and CART; S12 based on feature selection was the optimal feature combination scheme; and the combination of RF and Scheme S12 (S12) yielded the highest classification accuracy, with OA and Kappa coefficients for 2018-RF-S12 of 90.33% and 0.82 and OA and Kappa coefficients for 2022-RF-S12 of 89.59% and 0.81. This study underscores the utility of combining multiple feature types and feature selection for enhanced forest type recognition, noting that topographic features significantly improved accuracy, whereas geometric features detracted from it. Altitude emerged as the most influential characteristic, alongside significant variables such as the Normalized Difference Greenness Index (NDVI) and the mean value of reflectance in the blue band of the GF-2 image (Mean_B). Species such as Masson pine, shrub, and moso bamboo were accurately classified, with the optimal F1-Scores surpassing 89.50%. Notably, a shift from single-species to mixed-species stands was observed over the study period, enhancing ecological diversity and stability. These results highlight the effectiveness of GF-2 imagery for refined, large-scale forest-type identification and dynamic diversity monitoring in complex subtropical forests.

Dirty road extraction from GF-2 images by semi-supervised deep learning method for arid and semiarid regions of southern Mongolia

ABSTRACT The uncontrolled proliferation of natural roads in arid regions has exacerbated regional land degradation and desertification, presenting substantial challenges to their accurate mapping owing to their dynamic and obscure features. Moreover, the high cost of data annotation restricts the availability of comprehensively labelled datasets, which are essential for advanced remote sensing processing and natural road detection. This study dedicated to implement a semi-supervised deep learning method for dirty road extraction in southern Mongolia. A new thematic semantic segmentation dataset of natural roads was established firstly to address scarcity of annotation datasets this region. A semi-supervised UniMatch structure was designed consequently. Operating with high-resolution GaoFen-2 images, this approach minimises the need for extensive manual annotation, achieving an IOU of 73.51% and MIOU of 86.37%. This method significantly reduces labour and time costs associated with manual and fully supervised methods. These observations provide a valuable data source and methodology for addressing natural road expansion in arid regions. They can aid governments in evaluating transportation infrastructure in remote areas, and analysing dirty road traffic impact on environment.

Comparison of Extraction accuracy of Sugarcane from different resolution satellite images using Deep lab V3+ Mode

Abstract. Sugarcane is an annual or perennial persistent rooted tropical and subtropical herb that grows in tropical and subtropical regions. As China's production ranks among the world's leading, sugarcane industry is an important part of agricultural economy in China. As the largest sugarcane production center in China, Guangxi is one of the most suitable areas for sugarcane cultivation in China and even in the world. Sugarcane industry, as an agricultural advantageous industry in Guangxi, not only has a significant image to the national economy of the region, but also is closely related to the issue of security of national sugar supply. Continuous cropping of sugarcane is very common in Guangxi, which is very helpful for the concentration selection of sugarcane samples. The wide application of satellite remote sensing monitoring technology has become an indispensable means of natural resources monitoring. Using optical satellite remote sensing image to identify and extract sugarcane planting areas is of great significance to quickly and conveniently grasp the information of sugarcane distribution and yield. In this paper, the precision of sugarcane extraction from GF1 and GF2 satellite images is analyzed by using deeplab V3 + model, the effect of optical remote sensing images with different resolution on sugarcane extraction accuracy was studied to provide better data support for dynamic monitoring of sugarcane planting.

A construction waste landfill dataset of two districts in Beijing, China from high resolution satellite images

Construction waste is unavoidable in the process of urban development, causing serious environmental pollution. Accurate assessment of municipal construction waste generation requires building construction waste identification models using deep learning technology. However, this process requires high-quality public datasets for model training and validation. This study utilizes Google Earth and GF-2 images as the data source to construct a specific dataset of construction waste landfills in the Changping and Daxing districts of Beijing, China. This dataset contains 3,653 samples of the original image areas and provides mask-labeled images in the semantic segmentation domains. Each pixel within a construction waste landfill is classified into 4 categories of the image areas, including background area, vacant landfillable area, engineering facility area, and waste dumping area. The dataset contains 237,115,531 pixels of construction waste and 49,724,513 pixels of engineering facilities. The pixel-level semantic segmentation labels are provided to quantify the construction waste yield, which can serve as the basic data for construction waste extraction and yield estimation both for academic and industrial research.

Assessing Forest-Change-Induced Carbon Storage Dynamics by Integrating GF-1 Image and Localized Allometric Growth Equations in Jiangning District, Nanjing, Eastern China (2017–2020)

Forest and its dynamics are of great significance for accurately estimating regional carbon sequestration, emissions and carbon sink capacity. In this work, an efficient framework that integrates remote sensing, deep learning and statistical modeling was proposed to extract forest change information and then derive forest carbon storage dynamics during the period 2017 to 2020 in Jiangning District, Nanjing, Eastern China. Firstly, the panchromatic band and multi-spectral bands of GF-1 images were fused by using four different methods; Secondly, an improved Mask-RCNN integrated with Swin Transformer was devised to extract forest distribution information in 2020. Finally, by using the substitution strategy of space for time in the 2017 Forest Management and Planning Inventory (FMPI) data, local carbon density allometric growth equations were fitted by coniferous forest and broad-leaved forest types and compared, and the optimal fitting was accordingly determined, followed by the measurements of forest-change-induced carbon storage dynamics. The results indicated that the improved Mask-RCNN synergizing with the Swin Transformer gained an overall accuracy of 93.9% when mapping the local forest types. The carbon storage of forest standing woods was calculated at 1,449,400 tons in 2020, increased by 14.59% relative to that of 2017. This analysis provides a technical reference for monitoring forest change and lays a data foundation for local agencies to formulate forest management policies in the process of achieving dual-carbon goals.

Extraction of Hani terraces based on Sentinel-2 and GF-2 images in Honghe prefecture, Yunnan province

Monitoring Hani terraces quickly and accurately using remote sensing technology is crucial for the protecting World Cultural Heritage Sites. However, single remote sensing image is affected by the mutual constraints of temporal and spatial resolution, making it difficult to concurrently integrate key phenological and spatial information for accurate extraction. In this study, GF-2 and Sentinel-2 images are used to extract terraces based on objected-based image analysis. Firstly, the spatial and phenological features of objects were obtained by multi-resolution segmentation using GF-2 image. Secondly, the optimal spatial and key phenological features were optimized by recursive feature elimination cross-validation and separation index, respectively. Finally, all optimized features were adopted to extract terraces using random forest (RF) and support vector machine (SVM) classifiers, respectively. Comparing deep learning and traditional machine learning methods, the proposed method using RF achieved the highest accuracy with Kappa coefficient and overall accuracy of 89.45 and 94.73%, respectively.

SSMM-DS: A semantic segmentation model for mangroves based on Deeplabv3+ with swin transformer

<p>Mangrove wetlands play a crucial role in maintaining species diversity. However, they face threats from habitat degradation, deforestation, pollution, and climate change. Detecting changes in mangrove wetlands is essential for understanding their ecological implications, but it remains a challenging task. In this study, we propose a semantic segmentation model for mangroves based on Deeplabv3+ with Swin Transformer, abbreviated as SSMM-DS. Using Deeplabv3+ as the basic framework, we first constructed a data concatenation module to improve the contrast between mangroves and other vegetation or water. We then employed Swin Transformer as the backbone network, enhancing the capability of global information learning and detail feature extraction. Finally, we optimized the loss function by combining cross-entropy loss and dice loss, addressing the issue of sampling imbalance caused by the small areas of mangroves. Using GF-1 and GF-6 images, taking mean precision (mPrecision), mean intersection over union (mIoU), floating-point operations (FLOPs), and the number of parameters (Params) as evaluation metrics, we evaluate SSMM-DS against state-of-the-art models, including FCN, PSPNet, OCRNet, uPerNet, and SegFormer. The results demonstrate SSMM-DS's superiority in terms of mIoU, mPrecision, and parameter efficiency. SSMM-DS achieves a higher mIoU (95.11%) and mPrecision (97.79%) while using fewer parameters (17.48M) compared to others. Although its FLOPs are slightly higher than SegFormer's (15.11G vs. 9.9G), SSMM-DS offers a balance between performance and efficiency. Experimental results highlight SSMM-DS's effectiveness in extracting mangrove features, making it a valuable tool for monitoring and managing these critical ecosystems.</p>

Research on Estimating and Evaluating Subtropical Forest Carbon Stocks by Combining Multi-Payload High-Resolution Satellite Data

Forest carbon stock is an important indicator reflecting the structure of forest ecosystems and forest quality, and an important parameter for evaluating the carbon sequestration capacity and carbon balance of forests. It is of great significance to study forest carbon stock in the context of current global climate change. To explore the application ability of multi-loaded, high-resolution satellite data in the estimation of subtropical forest carbon stock, this paper takes Huangfu Mountain National Forest Park in Chuzhou City as the study area, extracts remote sensing features such as spectral features, texture features, backscattering coefficient, and other remote sensing features based on multi-loaded, high-resolution satellite data, and carries out correlation analyses with the carbon stock of different species of trees and different age groups of forests. Regression models for different tree species were established for different data sources, and the optimal modeling factors for multi-species were determined. Then, three algorithms, namely, multiple stepwise regression, random forest, and gradient-enhanced decision tree, were used to estimate carbon stocks of multi-species, and the predictive ability of different estimation models on carbon stocks was analyzed using the coefficient of determination (R2) and the root mean square error (RMSE) as indexes. The following conclusions were drawn: for the feature factors, the texture features of the GF-2 image, the new red edge index of the GF-6 image, the radar intensity coefficient sigma, and radar brightness coefficient beta of the GF-3 image have the best correlation with the carbon stock; for the algorithms, the random forest and gradient-boosting decision tree have the better effect of fitting and predicting the carbon stock of multi-tree species, among which gradient-boosting decision tree has the best effect, with an R2 of 0.902 and an RMSE of 10.261 t/ha. In summary, the combination of GF-2, GF-3, and GF-6 satellite data and gradient-boosting decision tree obtains the most accurate estimation results when estimating forest carbon stocks of complex tree species; multi-load, high-resolution satellite data can be used in the inversion of subtropical forest parameters to estimate the carbon stocks of subtropical forests. The multi-loaded, high-resolution satellite data have great potential for application in the field of subtropical forest parameter inversion.

Suaeda salsa spectral index for Suaeda salsa mapping and fractional cover estimation in intertidal wetlands

Suaeda Salsa (S. salsa), with short and red-purplish plants, is a typical pioneer saltmarsh species in the intertidal wetlands of temperate East Asia. It has important ecological, economic, and recreational values. In the past few decades, S. salsa has severely degraded in coastal China, which has brought widespread attention from regional and local governments. As a result, extensive S. salsa restoration projects have been initiated in recent years. It is urgently needed to develop satellite-based methods for both S. salsa mapping and fractional cover (FC) estimation because degradation and recovery of S. salsa are manifested by changes in both area and plant cover. However, accurate mapping and FC estimation of S. salsa are challenging because (1) S. salsa in intertidal areas have low FC and (2) heterogeneous soil backgrounds in wetlands greatly impact the spectral reflectance observed by satellites. To address these issues, this study proposed a new Suaeda Salsa Spectral Index (SSSI) to support accurate detection and FC estimation of S. salsa. The SSSI was designed based on the laboratory spectral measurements by considering variations in wetland soil moisture and by taking advantage of the reddish color of S. salsa. It consists of two components, one of which utilized blue, green and red bands to separate S. salsa from green vegetation, and the other component utilized a modification of the Soil Adjusted Vegetation Index (SAVI) to reduce the impact of soil background and maintain a linear relationship with S. salsa FC. SSSI was then applied on Sentinel-2/GF-1 images over the Yellow River Delta (YRD) and Liao River Delta (LRD), China. Based on SSSI, a simple thresholding approach was used to identify S. salsa, and a linear regression model was used to estimate FC. With reference datasets provided from field investigations, Unmanned Aerial Vehicle multispectral images and high-spatial resolution satellite images, our results show that the SSSI was able to detect low-coverage S. salsa (FC > 20 % in YRD and FC > 10 % in LRD), and the S. salsa maps had an overall accuracy over 94%. The SSSI-FC models achieved good estimation accuracies (R2 = 0.77 ∼ 0.86, RMSE = 7.55 % ∼ 9.79 %). Compared to the Normalized Difference Vegetation Index (NDVI) and SAVI, SSSI alleviated the impacts from soil backgrounds and provided better S. salsa FC estimations, particularly for low-coverage S. salsa. SSSI has great potential in supporting continuous monitoring of S. salsa dynamics and evaluating the effectiveness of S. salsa restoration projects.

Spatiotemporal imagery selection for full coverage image generation over a large area with HFA-Net based quality grading

ABSTRACT Remote sensing images often need to be merged into a larger mosaic image to support analysis on large areas in many applications. However, the performance of the mosaic imagery may be severely restricted if there are many areas with cloud coverage or if these images used for merging have a long-time span. Therefore, this paper proposes a method of image selection for full coverage image (i.e. a mosaic image with no cloud-contaminated pixels) generation. Specifically, a novel High-Frequency-Aware (HFA)-Net based on Swin-Transformer for region quality grading is presented to provide a data basis for image selection. Spatiotemporal constraints are presented to optimize the image selection. In the temporal dimension, the shortest-time-span constraint shortens the time span of the selected images, obviously improving the timeliness of the image selection results (i.e. with a shorter time span). In the spatial dimension, a spatial continuity constraint is proposed to select data with better quality and larger area, thus improving the radiometric continuity of the results. Experiments on the GF-1 images indicate that the proposed method reduces the averages by 76.1% and 38.7% in terms of the shortest time span compared to the Improved Coverage-oriented Retrieval algorithm (MICR) and Retrieval Method based on Grid Compensation (RMGC) methods, respectively. Moreover, the proposed method also reduces the residual cloud amount by an average of 91.2%, 89.8%, and 83.4% when compared to the MICR, RMGC, and Pixel-based Time-series Synthesis Method (PTSM) methods, respectively.

Applicability study of four atmospheric correction methods in the remote sensing of lake water color

Due to the complexity of spectral characteristics for inland lake water, high-precision atmospheric correction methods play an essential role in remote sensing. This research conducted atmospheric correction on the Tiande lake zone in Zhengzhou, China based on Zhuhai-1, Sentinel-2, Planet, and GF-2 images using four methods (QUAC, Dark Subtract, Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes (FLAASH) and 6S). In doing so, water reflectance can be extracted and compared with the data measured from a ground-based spectrometer. The analysis indicates that the FLAASH method has best applicability to Zhuhai-1 and Sentinel-2 images; while 6S method shows best applicability to Planet and GF-2 images. The comparison of single-band images indicates that the four atmospheric correction approaches used in different images are proven to be applicable to construction of sensitive wavebands of a water body inversion model in the Tiande lake zone. The correction results of four types of images prove that FLAASH and 6S are more applicable to lake water color remote sensing inversion.

An effective atmospheric correction method for the wide swath of Chinese GF-1 and GF-6 WFV images on lands

Accurate land surface reflectance plays an important role in the accurate inversion of surface parameters, and atmospheric correction plays a decisive role in obtaining accurate reflectance. For GF-1 WFV and GF-6 WFV images, there are two major issues to be addressed, including the spectral differences between nadir with far off-nadir pixels and the spatial variability of atmospheric components for wide imaging. Therefore, this study focuses on these two issues using the Sensor Invariant Atmospheric Correction (SIAC) method. Our results reveal that the SIAC approach improves the correlation accuracy from 0.8868 to 0.9173 for GF-1 WFV image compared with Sentinel-2 reflectance, from 0.9530 to 0.9620 for GF-6 WFV image compared with the results using FLAASH model. For alleviating wide-swathed anisotropy, the directional imaging angle is calculated with the result ranging from 5.6450° to 33.7497°. Furthermore, the atmospheric components have been inversed pixel by pixel with obvious spatial variation. And the correlation of inversed aerosol optical thickness (AOT) and total column water vapor (TCWV) with a spatial resolution of 500 m TCWV with measured results of AERONET (AErosol RObotic NETwork) observation stations are 0.9175 and 0.4442, respectively. These results reveal that the atmospheric correction method works well, which is effective for the wide swath of Chinese GF-1 WFV and GF-6 WFV images on land.

Scale Effect of Land Cover Classification from Multi-Resolution Satellite Remote Sensing Data.

Land cover data are important basic data for earth system science and other fields. Multi-source remote sensing images have become the main data source for land cover classification. There are still many uncertainties in the scale effect of image spatial resolution on land cover classification. Since it is difficult to obtain multiple spatial resolution remote sensing images of the same area at the same time, the main current method to study the scale effect of land cover classification is to use the same image resampled to different resolutions, however errors in the resampling process lead to uncertainty in the accuracy of land cover classification. To study the land cover classification scale effect of different spatial resolutions of multi-source remote sensing data, we selected 1 m and 4 m of GF-2, 6 m of SPOT-6, 10 m of Sentinel-2, and 30 m of Landsat-8 multi-sensor data, and explored the scale effect of image spatial resolution on land cover classification from two aspects of mixed image element decomposition and spatial heterogeneity. For the study area, we compared the classification obtained from GF-2, SPOT-6, Sentinel-2, and Landsat-8 images at different spatial resolutions based on GBDT and RF. The results show that (1) GF-2 and SPOT-6 had the best classification results, and the optimal scale based on this classification accuracy was 4-6 m; (2) the optimal scale based on linear decomposition depended on the study area; (3) the optimal scale of land cover was related to spatial heterogeneity, i.e., the more fragmented and complex was the space, the smaller the scale needed; and (4) the resampled images were not sensitive to scale and increased the uncertainty of the classification. These findings have implications for land cover classification and optimal scale selection, scale effects, and landscape ecology uncertainty studies.

Improvement and application of UNet network for avoiding the effect of urban dense high-rise buildings and other feature shadows on water body extraction

ABSTRACT Finding a means to extract water body information efficiently and accurately from high-resolution remote sensing images has been an important research direction in the field of water body extraction in recent years. However, shadows from buildings and other obstacles interfere with the accuracy of water body extraction. To address this problem, this paper proposes a neural network method incorporating an attention mechanism for water body extraction. This paper is based on the U-Net convolutional neural network and adds the squeeze-and-excitation module of SENet, an attention mechanism, to the downsampling process of the U-Net network. The module weights the feature maps so that the network focuses more on the features of the water body information and thus reduces attention to the shadow features from buildings and other features, thus improving the accuracy of image segmentation. The dropout and batch normalization layers are also added to improve the generalization ability and stability of the model. In this paper, a water extraction network SE-CU-Net model is presented to overcome the shadowing effect from buildings and other features. Using GF-2 images of Jiangsu province as the data source, the recognition results of this paper are compared with Dense-Net, Res-Net, Seg-Net, U-net, SVM, and RF. Through the comparison experiments, the model of this paper can not only better overcome the influence of shadows from buildings and other features, but it also has a stronger recognition ability and recognition effect. The average ASCR, Precision, mIoU, OA, F1-Score and kappa coefficients in the three tested areas reached 98.27%, 97.17%, 89.33%, 98.2%, 89.3% and 0.883, respectively, with significantly higher accuracy than the other six classical methods, verifying the effectiveness of the model in overcoming the influence of shadows from buildings and other features in water body extraction research.

DLRW: Dual-Link Weight Random Walk Model for Aquaculture Boundary Extraction by Single-Polarized SAR Imagery

Coastal aquaculture is undertaken in shallow and usually sheltered waters along the coast, delineated by aquaculture ponds. Illegal usage of coastal aquaculture can lead to conflicts with local communities and environmental problems. Thus, it is necessary to extract the aquaculture boundary to monitor the expansion of coastal aquaculture to the sea. However, it is challenging for most existing algorithms to extract the aquaculture boundary for synthetic aperture radar (SAR) images under a high incident angle (>30 degree) with horizontal transmitted and received (HH) or vertical transmitted and received (VV) polarization. The difficulties come from the following: (1) seawater can be seen on both sides of such boundaries, (2) the contrast of such boundaries is uneven, and (3) the backscattering coefficients in some parts of such boundaries are low. In this paper, a novel dual-link weight random walk (DLRW)-based method is proposed to extract such boundaries. The proposed DLRW is composed of an automatic seed points generation strategy, and the establishment and solving of a random walk model with the dual-link weight. By a coarse-to-fine procedure, DLRW is used to extract the aquaculture boundaries in the whole imagery. Sentinel-1 and GF-3 images in Dalian and Liaodong Bay, China have been used in experiments. Mean offset (MO), root mean square error (RMSE), Overlapped, accuracy within one pixel (WOP), and accuracy within two pixels (WTP) have been used to evaluate the performance with existing methods. Experimental results have demonstrated the proposed DLRW-based method outperforms existing methods in the extraction on aquaculture boundaries. Under the low tide, the DLRW-based method is better than the other two methods with MO, RMSE, Overlapped, WOP, and WTP by at least 5.75 pixels, 10.43 pixels, 2.88%, 11.09%, and 18.04%, respectively. Under the high tide, the DLRW-based method is superior to the other two methods with MO, RMSE, and WTP by at least 3.8 pixels, 10.5 pixels, and 6.3%. In addition, the proposed DLRW-based method has a good ability to extract the shoreline with bedrock, ports, and silt. Therefore, the proposed DLRW-based method can be of great value to coastal aquaculture monitoring, coastal mapping, and other coastal applications.

Research on SUnet Winter Wheat Identification Method Based on GF-2

Introduction: Winter wheat plays a crucial role in ensuring food security and sustainable agriculture. Accurate identification and recognition of winter wheat in remote sensing images are essential for monitoring crop growth and yield estimation. In recent years, attention-based convolutional neural networks have shown promising results in various image recognition tasks. Therefore, this study aims to explore the application of attention-based convolutional neural networks for winter wheat identification on GF-2 high-resolution images and propose improvements to enhance recognition accuracy. Method: This study built a multi-band winter wheat sample dataset based on GF-2 images. In order to highlight the characteristics of winter wheat, this study added two bands, NDVI and NDVIincrease, to the dataset and proposed a SUNet network model. In this study, the batch normalization layer was added to the basic structure of the UNet convolutional network to speed up network convergence and improve accuracy. In the jump phase, shuffle attention was added to the shallow features extracted from the coding structure for feature optimization and spliced with the deep features extracted by upsampling. The SUNet made the network pay more attention to the important features to improve winter wheat recognition accuracy. In order to overcome the sample imbalance problem, this study used the focus loss function instead of the traditional cross-entropy loss function. Result: The experimental data show that its mean intersection over union, overall classification accuracy, recall, F1 score and kappa coefficient are 0.9514, 0.9781, 0.9707, 0.9663 and 0.9501, respectively. The results of these evaluation indicators are better than those of other comparison methods. Compared with the UNet, the evaluation indicators have increased by 0.0253, 0.0118, 0.021, 0.0185, and 0.0272, respectively. Conclusion: The SUNet network can effectively improve winter wheat recognition accuracy in multi-band GF-2 images. Furthermore, with the support of a cloud platform, it can provide data guarantee and computing support for winter wheat information extraction.

Combination Strategies of Variables with Various Spatial Resolutions Derived from GF-2 Images for Mapping Forest Stock Volume

Spectral features (SFs) and texture features (TFs) extracted from optical remote sensing images can capture the structural composition and growth information of forests, and combining remote sensing variables with a few ground measurement samples is a common method for mapping forest stock volume (FSV). However, the accuracy of mapping FSV using optical images with a high spatial resolution (one meter or sub-meters) is often lower than medium resolutions (larger than 10 m) using the same types of features and approaches. To overcome the limitations of high spatial resolution images in mapping FSV, down-scaled images with spatial resolution ranging from 1 to 30 m were obtained by GF-2 image to interpret the relationships between spatial resolutions of features and the accuracy of mapping FSV, and combination strategies of variables with various spatial resolutions were proposed to improve the accuracy of mapping FSV. The results show that the spatial resolution of features significantly affects the performance of employed models in estimating FSV, the sensitivity between SFs and FSV gradually increases with the decreasing of spatial resolution, and the optimal spatial resolutions of two types of features (SFs and TFs) are not synchronized in mapping forest FSV. After using combination strategies of variables with various spatial resolutions, the accuracy of mapping FSV is significantly higher than those derived from variable sets with the same spatial resolutions. It is proved that TFs derived from GF-2 images have great potential to improve the accuracy of mapping FSV, and the contribution of features depends on the approaches of extracting and combination strategies.

A Study on Spatial Distribution Extraction of Tidal Inundated Mangroves Based on High and Low Tide Level Images

A majority of mangroves are located in the coastal intertidal zone and are subject to tidal periodic inundation. However, the previous vegetation indices used for extracting the spatial distribution of mangroves were not able to effectively extract submerged mangroves, and the applicability of the vegetation indices used on different spatial resolution images obtained from different sensors was not verified. In this study, a new vegetation index, namely the intertidal mangrove identification indices (IMIIs), was proposed, based on GF-2 images of high and low tide levels. Meanwhile, other commonly used vegetation indices were also extracted. All the vegetation indices were used to extract the spatial distribution of mangroves under tidal inundation, and applicability tests of the vegetation indices were conducted on Sentinel-2 images in three different regions. It was found that the IMIIs proposed based on GF-2 images of high and low tide levels can extract submerged mangroves relatively well, and the spatial distribution extraction results of mangroves are better than those of other vegetation indices, with IMII2 outperforming IMII1. At the same time, IMIIs have good applicability in medium resolution Sentinel-2 images, and there are relatively large differences in the extraction results of mangrove spatial distribution among different vegetation indices in areas with significant impact of tidal inundation. Among all vegetation indices, the extraction results of IMIIs are relatively superior. In most cases, multi variables collaborative application can improve the accuracy of mangrove spatial distribution extraction results. Based on the results of this study, it was concluded that the IMIIs proposed in this study can accurately extract the spatial distribution of mangroves inundated by tides from both medium- and high-resolution images, providing accurate basic data for effective management and scientific protection of mangrove resources.