An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyram...An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyramid network(FPN)structure of the original YOLOv8 mode is replaced by the generalized-FPN(GFPN)structure in GiraffeDet to realize the"cross-layer"and"cross-scale"adaptive feature fusion,to enrich the semantic information and spatial information on the feature map to improve the target detection ability of the model.Secondly,a pyramid-pool module of multi atrous spatial pyramid pooling(MASPP)is designed by using the idea of atrous convolution and feature pyramid structure to extract multi-scale features,so as to improve the processing ability of the model for multi-scale objects.The experimental results show that the detection accuracy of the improved YOLOv8 model on DIOR dataset is 92%and mean average precision(mAP)is 87.9%,respectively 3.5%and 1.7%higher than those of the original model.It is proved the detection and classification ability of the proposed model on multi-dimensional optical remote sensing target has been improved.展开更多
Yellow rust(Puccinia striiformis f.sp.Tritici,YR)and fusarium head blight(Fusarium graminearum,FHB)are the two main diseases affecting wheat in the main grain-producing areas of East China,which is common for the two ...Yellow rust(Puccinia striiformis f.sp.Tritici,YR)and fusarium head blight(Fusarium graminearum,FHB)are the two main diseases affecting wheat in the main grain-producing areas of East China,which is common for the two diseases to appear simultaneously in some main production areas.It is necessary to discriminate wheat YR and FHB at the regional scale to accurately locate the disease in space,conduct detailed disease severity monitoring,and scientific control.Four images on different dates were acquired from Sentinel-2,Landsat-8,and Gaofen-1 during the critical period of winter wheat,and 22 remote sensing features that characterize the wheat growth status were then calculated.Meanwhile,6 meteorological parameters that reflect the wheat phenological information were also obtained by combining the site meteorological data and spatial interpolation technology.Then,the principal components(PCs)of comprehensive remote sensing and meteorological features were extracted with principal component analysis(PCA).The PCs-based discrimination models were established to map YR and FHB damage using the random forest(RF)and backpropagation neural network(BPNN).The models’performance was verified based on the disease field truth data(57 plots during the filling period)and 5-fold cross-validation.The results revealed that the PCs obtained after PCA dimensionality reduction outperformed the initial features(IFs)from remote sensing and meteorology in discriminating between the two diseases.Compared to the IFs,the average area under the curve for both micro-average and macro-average ROC curves increased by 0.07 in the PCs-based RF models and increased by 0.16 and 0.13,respectively,in the PCs-based BPNN models.Notably,the PCs-based BPNN discrimination model emerged as the most effective,achieving an overall accuracy of 83.9%.Our proposed discrimination model for wheat YR and FHB,coupled with multi-source remote sensing images and meteorological data,overcomes the limitations of a single-sensor and single-phase remote sensing information in multiple stress discrimination in cloudy and rainy areas.It performs well in revealing the damage spatial distribution of the two diseases at a regional scale,providing a basis for detailed disease severity monitoring,and scientific prevention and control.展开更多
Blue carbon ecosystems,including mangroves,seagrasses,and salt marshes,play a crucial role in mitigating climate change by capturing and storing atmospheric CO_(2)at rates exceeding those of terrestrial forests.This s...Blue carbon ecosystems,including mangroves,seagrasses,and salt marshes,play a crucial role in mitigating climate change by capturing and storing atmospheric CO_(2)at rates exceeding those of terrestrial forests.This study explores the potential of HCWs(Human-Controlled Wetlands)in the Italian Venice Lagoon as an underappreciated component of the global blue carbon pool.Using GEE(Google Earth Engine),we conducted a large-scale assessment of carbon sequestration in these wetlands,demonstrating its advantages over traditional in situ methods in addressing spatial variability.Our findings highlight the significance of below-water mud sediments as primary carbon reservoirs,with a TC(Total Carbon)content of 3.81%±0.94%and a stable storage function akin to peat,reinforced by high CEC(Cation Exchange Capacity).GEE analysis identified a redoximorphic zone at a depth of 20-30 cm,where microbial respiration shifts to anaerobic pathways,preventing carbon release and maintaining long-term sequestration.The study also evaluates key factors affecting remote sensing accuracy,including tidal variations,water depth,and sky cover.The strong correlation between field-measured and satellite-derived carbon parameters(R^(2)>0.85)confirms the reliability of our approach.Furthermore,we developed a GEE-based script for monitoring sediment bioturbation,leveraging Sentinel-1 SAR(Synthetic Aperture Radar)and Sentinel-2 optical data to quantify biological disturbances affecting carbon fluxes.Our results underscore the value of HCWs for carbon sequestration,reinforcing the need for targeted conservation strategies.The scalability and efficiency of remote sensing methodologies,particularly GEE,make them essential for the long-term monitoring of blue carbon ecosystems and the development of effective climate mitigation policies.展开更多
In the Fatira(Abu Zawal)mine area,located in the northern Eastern Desert of Egypt,fieldwork and mineralogical analysis,integrated with machine learning techniques applied to Landsat-8 OLI,ASTER,and Sentinel-2 multi-sp...In the Fatira(Abu Zawal)mine area,located in the northern Eastern Desert of Egypt,fieldwork and mineralogical analysis,integrated with machine learning techniques applied to Landsat-8 OLI,ASTER,and Sentinel-2 multi-spectral imagery(MSI)data delineate gold-sulfide mineralization in altered rocks.Gold(Au)anomalies in hydrothermal breccias and quartz veins are associated with NE-oriented felsite dykes and silicified granitic rocks.Two main alteration types are identified:a pyrite-sericite-quartz and a sulfide-chlorite-carbonate assemblage,locally with dispersed free-milling Au specks.Dimensionality reduction techniques,including principal component analysis(PCA)and independent component analysis(ICA),enabled mapping of alteration types.Sentinel-2 PC125 composite images offered efficient lithological differentiation,while supervised classifications,i.e.,the support vector machine(SVM)of Landsat-8 yielded an accuracy of 88.55%and a Kappa value of 0.86.ASTER mineral indices contributed to map hydrothermal alteration mineral phases,including sericite,muscovite,kaolinite,and iron oxides.Results indicate that post-magmatic epigenetic hydrothermal activity significantly contributed to the Au-sulfide mineralization in the Fatira area,distinguishing it from the more prevalent orogenic gold deposits in the region.展开更多
The convolutional neural network(CNN)method based on DeepLabv3+has some problems in the semantic segmentation task of high-resolution remote sensing images,such as fixed receiving field size of feature extraction,lack...The convolutional neural network(CNN)method based on DeepLabv3+has some problems in the semantic segmentation task of high-resolution remote sensing images,such as fixed receiving field size of feature extraction,lack of semantic information,high decoder magnification,and insufficient detail retention ability.A hierarchical feature fusion network(HFFNet)was proposed.Firstly,a combination of transformer and CNN architectures was employed for feature extraction from images of varying resolutions.The extracted features were processed independently.Subsequently,the features from the transformer and CNN were fused under the guidance of features from different sources.This fusion process assisted in restoring information more comprehensively during the decoding stage.Furthermore,a spatial channel attention module was designed in the final stage of decoding to refine features and reduce the semantic gap between shallow CNN features and deep decoder features.The experimental results showed that HFFNet had superior performance on UAVid,LoveDA,Potsdam,and Vaihingen datasets,and its cross-linking index was better than DeepLabv3+and other competing methods,showing strong generalization ability.展开更多
INTRODUCTION.On May 1st,2024,around 2:10 a.m.,a catastrophic collapse occurred along the Meilong Expressway near Meizhou City,Guangdong Province,China,at coordinates 24°29′24″N and 116°40′25″E.This colla...INTRODUCTION.On May 1st,2024,around 2:10 a.m.,a catastrophic collapse occurred along the Meilong Expressway near Meizhou City,Guangdong Province,China,at coordinates 24°29′24″N and 116°40′25″E.This collapse resulted in a pavement failure of approximately 17.9 m in length and covering an area of about 184.3 m^(2)(Chinanews,2024).展开更多
The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no ...The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no experience to intuitively interact with RS data of multiple formats is a potential provided by this integration.However,the use of AI and AI agents to help automate RS-related tasks is still in its infancy stage,with some frameworks and interfaces built on top of well-known vision language models(VLM)such as GPT-4,segment anything model(SAM),and grounding DINO.These tools do promise and draw guidelines on the potentials and limitations of existing solutions concerning the use of said models.In this work,the state of the art AI foundation models(FM)are reviewed and used in a multi-modal manner to ingest RS imagery input and perform zero-shot object detection using natural language.The natural language input is then used to define the classes or labels the model should look for,then,both inputs are fed to the pipeline.The pipeline presented in this work makes up for the shortcomings of the general knowledge FMs by stacking pre-processing and post-processing applications on top of the FMs;these applications include tiling to produce uniform patches of the original image for faster detection,outlier rejection of redundant bounding boxes using statistical and machine learning methods.The pipeline was tested with UAV,aerial and satellite images taken over multiple areas.The accuracy for the semantic segmentation showed improvement from the original 64%to approximately 80%-99%by utilizing the pipeline and techniques proposed in this work.GitHub Repository:MohanadDiab/LangRS.展开更多
One of the crucial elements that is directly tied to the quality of living organisms is the quality of the water.How-ever,water quality has been adversely affected by plastic pollution,a global environmental disaster ...One of the crucial elements that is directly tied to the quality of living organisms is the quality of the water.How-ever,water quality has been adversely affected by plastic pollution,a global environmental disaster that has an effect on aquatic life,wildlife,and human health.To prevent these effects,better monitoring,detection,characterisation,quanti-fication,and tracking of aquatic plastic pollution at regional and global scales is urgently needed.Remote sensing tech-nology is regarded as a useful technique,as it offers a promising new and less labour-intensive tool for the detection,quantification,and characterisation of aquatic plastic pollution.The study seeks to supplement to the body of scientific literature by compiling original data on the monitoring of plastic pollution in aquatic environments using remote sensing technology,which can function as a cost saving method for water pollution and risk management in developing nations.This article provides a profound analysis of plastic pollution,including its categories,sources,distribution,chemical properties,and potential risks.It also provides an in-depth review of remote sensing technologies,satellite-derived in-dices,and research trends related to their applicability.Additionally,the study clarifies the difficulties in using remote sensing technologies for aquatic plastic monitoring and practical ways to reduce aquatic plastic pollution.The study will improve the understanding of aquatic plastic pollution,health hazards,and the suitability of remote sensing technology for aquatic plastic contamination monitoring studies among researchers and interested parties.展开更多
Strong sensitivity of satellite microwave remote sensing to the change of surface dielectric properties,as well as the insensitivity to air pollution and solar illumination effects,makes it very suitable for monitorin...Strong sensitivity of satellite microwave remote sensing to the change of surface dielectric properties,as well as the insensitivity to air pollution and solar illumination effects,makes it very suitable for monitoring freeze-thaw conditions.The freeze-thaw cycle changes in the Qinghai-Xizang Plateau have an important impact on the ecological environment and infrastructure.Based on the Scanning Multi-channel Microwave Radiometer(SMMR)and other sensors of microwave satellite,the freeze-thaw cycle data of permafrost in the Qinghai-Xizang Plateau in the past 40 years from 1981 to 2020 was obtained.The changes of soil freeze-thaw conditions in different seasons of 2020 and in the same season of 1990,2000,2010 and 2020 were compared,and the annual variation trend of soil freeze-thaw area in the four years was analyzed.Further,the linear regression analysis was carried out on the duration of soil freezing/thawing/transition and the interannual variation trend under different area conditions from 1981 to 2020.The results show that the freeze-thaw changes in different years are similar.In winter,it is mainly frozen for about 110 days.Spring and autumn are transitional periods,lasting for 170 days.In summer,it is mainly thawed for about 80 days.From 1981 to 2020,the freezing period and the average freezing area of the Qinghai-Xizang Plateau decreased at a rate of 0.22 days and 1986 km^(2) per year,respectively,while the thawing period and the average thawing area increased at a rate of 0.07 days and 3187 km^(2) per year,respectively.The research results provide important theoretical support for the ecological environment and permafrost protection of the Qinghai-Xizang Plateau.展开更多
This study presents an AI-driven Spatial Decision Support System (SDSS) aimed at transforming groundwater suitability assessments for domestic and irrigation uses in Visakhapatnam District, Andhra Pradesh, India. By e...This study presents an AI-driven Spatial Decision Support System (SDSS) aimed at transforming groundwater suitability assessments for domestic and irrigation uses in Visakhapatnam District, Andhra Pradesh, India. By employing advanced remote sensing, GIS, and machine learning techniques, groundwater quality data from 50 monitoring wells, sourced from the Central Ground Water Board (CGWB), was meticulously analysed. Key parameters, including pH, electrical conductivity, total dissolved solids, and major ion concentrations, were evaluated against World Health Organization (WHO) standards to determine domestic suitability. For irrigation, advanced metrics such as Sodium Adsorption Ratio (SAR), Kelly’s Ratio, Residual Sodium Carbonate (RSC), and percentage sodium (% Na) were utilized to assess water quality. The integration of GIS for spatial mapping and AI models for predictive analytics allows for a comprehensive visualization of groundwater quality distribution across the district. Additionally, the irrigation water quality was evaluated using the USA Salinity Laboratory diagram, providing essential insights for effective agricultural water management. This innovative SDSS framework promises to significantly enhance groundwater resource management, fostering sustainable practices for both domestic use and agriculture in the region.展开更多
Cloud detection is a critical preprocessing step in remote sensing image processing, as the presence of clouds significantly affects the accuracy of remote sensing data and limits its applicability across various doma...Cloud detection is a critical preprocessing step in remote sensing image processing, as the presence of clouds significantly affects the accuracy of remote sensing data and limits its applicability across various domains. This study presents an enhanced cloud detection method based on the U-Net architecture, designed to address the challenges of multi-scale cloud features and long-range dependencies inherent in remote sensing imagery. A Multi-Scale Dilated Attention (MSDA) module is introduced to effectively integrate multi-scale information and model long-range dependencies across different scales, enhancing the model’s ability to detect clouds of varying sizes. Additionally, a Multi-Head Self-Attention (MHSA) mechanism is incorporated to improve the model’s capacity for capturing finer details, particularly in distinguishing thin clouds from surface features. A multi-path supervision mechanism is also devised to ensure the model learns cloud features at multiple scales, further boosting the accuracy and robustness of cloud mask generation. Experimental results demonstrate that the enhanced model achieves superior performance compared to other benchmarked methods in complex scenarios. It significantly improves cloud detection accuracy, highlighting its strong potential for practical applications in cloud detection tasks.展开更多
Source identification and deformation analysis of disaster bodies are the main contents of high-steep slope risk assessment,the establishment of high-precision model and the quantification of the fine geometric featur...Source identification and deformation analysis of disaster bodies are the main contents of high-steep slope risk assessment,the establishment of high-precision model and the quantification of the fine geometric features of the slope are the prerequisites for the above work.In this study,based on the UAV remote sensing technology in acquiring refined model and quantitative parameters,a semi-automatic dangerous rock identification method based on multi-source data is proposed.In terms of the periodicity UAV-based deformation monitoring,the monitoring accuracy is defined according to the relative accuracy of multi-temporal point cloud.Taking a high-steep slope as research object,the UAV equipped with special sensors was used to obtain multi-source and multitemporal data,including high-precision DOM and multi-temporal 3D point clouds.The geometric features of the outcrop were extracted and superimposed with DOM images to carry out semi-automatic identification of dangerous rock mass,realizes the closed-loop of identification and accuracy verification;changing detection of multi-temporal 3D point clouds was conducted to capture deformation of slope with centimeter accuracy.The results show that the multi-source data-based semiautomatic dangerous rock identification method can complement each other to improve the efficiency and accuracy of identification,and the UAV-based multi-temporal monitoring can reveal the near real-time deformation state of slopes.展开更多
Enhancing the carbon sink of terrestrial ecosystems is an essential nature-based solution to mitigate global warming and achieve the target of carbon neutrality.Over recent decades,China has launched a series of long-...Enhancing the carbon sink of terrestrial ecosystems is an essential nature-based solution to mitigate global warming and achieve the target of carbon neutrality.Over recent decades,China has launched a series of long-running and large-scale ambitious forestation projects.However,there is still a lack of year-to-year evaluation on the effects of afforestation on carbon sequestration.Satellite remote sensing provides continuous observations of vegetation dynamics and land use and land cover change,is becoming a practical tool to evaluate the changes of vegetation productivity driven by afforestation.Here,a spatially-explicit analysis was conducted by combining Moderate Resolution Imaging Spectroradiometer(MODIS)land cover and three up-to-date remote sensing gross primary productivity(GPP)datasets of China.The results showed that the generated afforestation maps have similar spatial distribution with the national forest inventory data at the provincial level.The accumulative areas of afforestation were 3.02×10^(5)km^(2)in China from 2002 to 2018,it was mainly distributed in Southwest(SW),South(Sou),Southeast(SE)and Northeast(NE)of China.Among them,SW possesses the largest afforestation sub-region,with an area of 9.38×10^(4)km^(2),accounting for 31.06%of the total.There were divergent trends of affores-tation area among different sub-regions.The southern sub-regions showed increasing trends,while the northern sub-regions showed decreasing trends.In keeping with these,the center of annual afforestation moved to the south after 2009.The southern sub-regions were the majority of the cumula-tive GPP,accounting for nearly 70%of the total.The GPP of new afforestation showed an increasing trend from 2002 to 2018,and the increasing rate was higher than existing forests.After afforestation,the GPP change of afforestation was higher than adjacent non-forest over the same period.Our work provides new evidence that afforestation of China has enhanced the carbon assimilation and will deepen our understanding of dynamics of carbon sequestration driven by afforestation.展开更多
Semantic segmentation of remote sensing images is a critical research area in the field of remote sensing.Despite the success of Convolutional Neural Networks(CNNs),they often fail to capture inter-layer feature relat...Semantic segmentation of remote sensing images is a critical research area in the field of remote sensing.Despite the success of Convolutional Neural Networks(CNNs),they often fail to capture inter-layer feature relationships and fully leverage contextual information,leading to the loss of important details.Additionally,due to significant intraclass variation and small inter-class differences in remote sensing images,CNNs may experience class confusion.To address these issues,we propose a novel Category-Guided Feature Collaborative Learning Network(CG-FCLNet),which enables fine-grained feature extraction and adaptive fusion.Specifically,we design a Feature Collaborative Learning Module(FCLM)to facilitate the tight interaction of multi-scale features.We also introduce a Scale-Aware Fusion Module(SAFM),which iteratively fuses features from different layers using a spatial attention mechanism,enabling deeper feature fusion.Furthermore,we design a Category-Guided Module(CGM)to extract category-aware information that guides feature fusion,ensuring that the fused featuresmore accurately reflect the semantic information of each category,thereby improving detailed segmentation.The experimental results show that CG-FCLNet achieves a Mean Intersection over Union(mIoU)of 83.46%,an mF1 of 90.87%,and an Overall Accuracy(OA)of 91.34% on the Vaihingen dataset.On the Potsdam dataset,it achieves a mIoU of 86.54%,an mF1 of 92.65%,and an OA of 91.29%.These results highlight the superior performance of CG-FCLNet compared to existing state-of-the-art methods.展开更多
In recent years,convolutional neural networks(CNN)and Transformer architectures have made significant progress in the field of remote sensing(RS)change detection(CD).Most of the existing methods directly stack multipl...In recent years,convolutional neural networks(CNN)and Transformer architectures have made significant progress in the field of remote sensing(RS)change detection(CD).Most of the existing methods directly stack multiple layers of Transformer blocks,which achieves considerable improvement in capturing variations,but at a rather high computational cost.We propose a channel-Efficient Change Detection Network(CE-CDNet)to address the problems of high computational cost and imbalanced detection accuracy in remote sensing building change detection.The adaptive multi-scale feature fusion module(CAMSF)and lightweight Transformer decoder(LTD)are introduced to improve the change detection effect.The CAMSF module can adaptively fuse multi-scale features to improve the model’s ability to detect building changes in complex scenes.In addition,the LTD module reduces computational costs and maintains high detection accuracy through an optimized self-attention mechanism and dimensionality reduction operation.Experimental test results on three commonly used remote sensing building change detection data sets show that CE-CDNet can reduce a certain amount of computational overhead while maintaining detection accuracy comparable to existing mainstream models,showing good performance advantages.展开更多
While algorithms have been created for land usage in urban settings,there have been few investigations into the extraction of urban footprint(UF).To address this research gap,the study employs several widely used imag...While algorithms have been created for land usage in urban settings,there have been few investigations into the extraction of urban footprint(UF).To address this research gap,the study employs several widely used image classification method classified into three categories to evaluate their segmentation capabilities for extracting UF across eight cities.The results indicate that pixel-based methods only excel in clear urban environments,and their overall accuracy is not consistently high.RF and SVM perform well but lack stability in object-based UF extraction,influenced by feature selection and classifier performance.Deep learning enhances feature extraction but requires powerful computing and faces challenges with complex urban layouts.SAM excels in medium-sized urban areas but falters in intricate layouts.Integrating traditional and deep learning methods optimizes UF extraction,balancing accuracy and processing efficiency.Future research should focus on adapting algorithms for diverse urban landscapes to enhance UF extraction accuracy and applicability.展开更多
This research systematically investigates urban three-dimensional greening layout optimization and smart ecocity construction using deep learning and remote sensing technology.An improved U-Net++ architecture combined...This research systematically investigates urban three-dimensional greening layout optimization and smart ecocity construction using deep learning and remote sensing technology.An improved U-Net++ architecture combined with multi-source remote sensing data achieved high-precision recognition of urban three-dimensional greening with 92.8% overall accuracy.Analysis of spatiotemporal evolution patterns in Shanghai,Hangzhou,and Nanjing revealed that threedimensional greening shows a development trend from demonstration to popularization,with 16.5% annual growth rate.The study quantitatively assessed ecological benefits of various three-dimensional greening types.Results indicate that modular vertical greening and intensive roof gardens yield highest ecological benefits,while climbing-type vertical greening and extensive roof gardens offer optimal benefit-cost ratios.Integration of multiple forms generates 15-22% synergistic enhancement.Compared with traditional planning,the multi-objective optimization-based layout achieved 27.5% increase in carbon sequestration,32.6% improvement in temperature regulation,35.8% enhancement in stormwater management,and 42.3% rise in biodiversity index.Three pilot projects validated that actual ecological benefits reached 90.3-102.3% of predicted values.Multi-scenario simulations indicate optimized layouts can reduce urban heat island intensity by 15.2-18.7%,increase carbon neutrality contribution to 8.6-10.2%,and decrease stormwater runoff peaks by 25.3-32.6%.The findings provide technical methods for urban three-dimensional greening optimization and smart eco-city construction,promoting sustainable urban development.展开更多
In response to challenges posed by complex backgrounds,diverse target angles,and numerous small targets in remote sensing images,alongside the issue of high resource consumption hindering model deployment,we propose a...In response to challenges posed by complex backgrounds,diverse target angles,and numerous small targets in remote sensing images,alongside the issue of high resource consumption hindering model deployment,we propose an enhanced,lightweight you only look once version 8 small(YOLOv8s)detection algorithm.Regarding network improvements,we first replace tradi-tional horizontal boxes with rotated boxes for target detection,effectively addressing difficulties in feature extraction caused by varying target angles.Second,we design a module integrating convolu-tional neural networks(CNN)and Transformer components to replace specific C2f modules in the backbone network,thereby expanding the model’s receptive field and enhancing feature extraction in complex backgrounds.Finally,we introduce a feature calibration structure to mitigate potential feature mismatches during feature fusion.For model compression,we employ a lightweight channel pruning technique based on localized mean average precision(LMAP)to eliminate redundancies in the enhanced model.Although this approach results in some loss of detection accuracy,it effec-tively reduces the number of parameters,computational load,and model size.Additionally,we employ channel-level knowledge distillation to recover accuracy in the pruned model,further enhancing detection performance.Experimental results indicate that the enhanced algorithm achieves a 6.1%increase in mAP50 compared to YOLOv8s,while simultaneously reducing parame-ters,computational load,and model size by 57.7%,28.8%,and 52.3%,respectively.展开更多
The secured access is studied in this paper for the network of the image remote sensing.Each sensor in this network encounters the information security when uploading information of the images wirelessly from the sens...The secured access is studied in this paper for the network of the image remote sensing.Each sensor in this network encounters the information security when uploading information of the images wirelessly from the sensor to the central collection point.In order to enhance the sensing quality for the remote uploading,the passive reflection surface technique is employed.If one eavesdropper that exists nearby this sensor is keeping on accessing the same networks,he may receive the same image from this sensor.Our goal in this paper is to improve the SNR of legitimate collection unit while cut down the SNR of the eavesdropper as much as possible by adaptively adjust the uploading power from this sensor to enhance the security of the remote sensing images.In order to achieve this goal,the secured energy efficiency performance is theoretically analyzed with respect to the number of the passive reflection elements by calculating the instantaneous performance over the channel fading coefficients.Based on this theoretical result,the secured access is formulated as a mathematical optimization problem by adjusting the sensor uploading power as the unknown variables with the objective of the energy efficiency maximization while satisfying any required maximum data rate of the eavesdropper sensor.Finally,the analytical expression is theoretically derived for the optimum uploading power.Numerical simulations verify the design approach.展开更多
Oyster farming provides substantial ecological and economic benefits but is often constrained by the challenges of selecting suitable sites in dynamic coastal environments.This study presents a tailored oyster suitabi...Oyster farming provides substantial ecological and economic benefits but is often constrained by the challenges of selecting suitable sites in dynamic coastal environments.This study presents a tailored oyster suitability index(OSI)for the Zhujiang(Pearl)River Estuary(PRE),developed using Landsat satellite imagery and in situ observations collected from 2013 to 2023.Key environmental parameters,including sea surface temperature(SST),salinity,turbidity,and chlorophyll-a(Chl-a)concentration,were integrated for OSI retrieval.Optimal algorithms for each parameter were identified through evaluation using field measurements,yielding high accuracy,as evidenced by strong determination coefficients(R^(2))and low root mean square error(RMSE):R^(2)=0.98,RMSE=0.74℃for SST;R^(2)=0.94,RMSE=0.50 for salinity;R^(2)=0.95,RMSE=1.21 mg/m^(3)for Chl-a;R^(2)=0.91,RMSE=1.48 NTU for turbidity.The OSI revealed pronounced seasonal and spatial variability,with the highest suitability observed during winter and the lowest during summer.Validation results demonstrated strong alignment between OSI predictions and existing oyster farming zones.These findings underscore the value of remote sensing for scalable,near-real-time aquaculture site assessments.The OSI framework provides a robust decision-support tool for optimizing oyster cultivation,promoting sustainable aquaculture development in dynamic estuarine systems such as the PRE and beyond.展开更多
基金supported by the National Natural Science Foundation of China(No.62241109)the Tianjin Science and Technology Commissioner Project(No.20YDTPJC01110)。
文摘An improved model based on you only look once version 8(YOLOv8)is proposed to solve the problem of low detection accuracy due to the diversity of object sizes in optical remote sensing images.Firstly,the feature pyramid network(FPN)structure of the original YOLOv8 mode is replaced by the generalized-FPN(GFPN)structure in GiraffeDet to realize the"cross-layer"and"cross-scale"adaptive feature fusion,to enrich the semantic information and spatial information on the feature map to improve the target detection ability of the model.Secondly,a pyramid-pool module of multi atrous spatial pyramid pooling(MASPP)is designed by using the idea of atrous convolution and feature pyramid structure to extract multi-scale features,so as to improve the processing ability of the model for multi-scale objects.The experimental results show that the detection accuracy of the improved YOLOv8 model on DIOR dataset is 92%and mean average precision(mAP)is 87.9%,respectively 3.5%and 1.7%higher than those of the original model.It is proved the detection and classification ability of the proposed model on multi-dimensional optical remote sensing target has been improved.
基金supported by National Key R&D Program of China(2022YFD2000100)National Natural Science Foundation of China(42401400)Zhejiang Provincial Key Research and Development Program(2023C02018).
文摘Yellow rust(Puccinia striiformis f.sp.Tritici,YR)and fusarium head blight(Fusarium graminearum,FHB)are the two main diseases affecting wheat in the main grain-producing areas of East China,which is common for the two diseases to appear simultaneously in some main production areas.It is necessary to discriminate wheat YR and FHB at the regional scale to accurately locate the disease in space,conduct detailed disease severity monitoring,and scientific control.Four images on different dates were acquired from Sentinel-2,Landsat-8,and Gaofen-1 during the critical period of winter wheat,and 22 remote sensing features that characterize the wheat growth status were then calculated.Meanwhile,6 meteorological parameters that reflect the wheat phenological information were also obtained by combining the site meteorological data and spatial interpolation technology.Then,the principal components(PCs)of comprehensive remote sensing and meteorological features were extracted with principal component analysis(PCA).The PCs-based discrimination models were established to map YR and FHB damage using the random forest(RF)and backpropagation neural network(BPNN).The models’performance was verified based on the disease field truth data(57 plots during the filling period)and 5-fold cross-validation.The results revealed that the PCs obtained after PCA dimensionality reduction outperformed the initial features(IFs)from remote sensing and meteorology in discriminating between the two diseases.Compared to the IFs,the average area under the curve for both micro-average and macro-average ROC curves increased by 0.07 in the PCs-based RF models and increased by 0.16 and 0.13,respectively,in the PCs-based BPNN models.Notably,the PCs-based BPNN discrimination model emerged as the most effective,achieving an overall accuracy of 83.9%.Our proposed discrimination model for wheat YR and FHB,coupled with multi-source remote sensing images and meteorological data,overcomes the limitations of a single-sensor and single-phase remote sensing information in multiple stress discrimination in cloudy and rainy areas.It performs well in revealing the damage spatial distribution of the two diseases at a regional scale,providing a basis for detailed disease severity monitoring,and scientific prevention and control.
文摘Blue carbon ecosystems,including mangroves,seagrasses,and salt marshes,play a crucial role in mitigating climate change by capturing and storing atmospheric CO_(2)at rates exceeding those of terrestrial forests.This study explores the potential of HCWs(Human-Controlled Wetlands)in the Italian Venice Lagoon as an underappreciated component of the global blue carbon pool.Using GEE(Google Earth Engine),we conducted a large-scale assessment of carbon sequestration in these wetlands,demonstrating its advantages over traditional in situ methods in addressing spatial variability.Our findings highlight the significance of below-water mud sediments as primary carbon reservoirs,with a TC(Total Carbon)content of 3.81%±0.94%and a stable storage function akin to peat,reinforced by high CEC(Cation Exchange Capacity).GEE analysis identified a redoximorphic zone at a depth of 20-30 cm,where microbial respiration shifts to anaerobic pathways,preventing carbon release and maintaining long-term sequestration.The study also evaluates key factors affecting remote sensing accuracy,including tidal variations,water depth,and sky cover.The strong correlation between field-measured and satellite-derived carbon parameters(R^(2)>0.85)confirms the reliability of our approach.Furthermore,we developed a GEE-based script for monitoring sediment bioturbation,leveraging Sentinel-1 SAR(Synthetic Aperture Radar)and Sentinel-2 optical data to quantify biological disturbances affecting carbon fluxes.Our results underscore the value of HCWs for carbon sequestration,reinforcing the need for targeted conservation strategies.The scalability and efficiency of remote sensing methodologies,particularly GEE,make them essential for the long-term monitoring of blue carbon ecosystems and the development of effective climate mitigation policies.
基金the National Science Foundation of China (Grant No. NSFC: 92162213)the Geology Department Faculty of Science of Al-Azhar University (Assiut Branch)+2 种基金the China Scholarship CouncilChang'an UniversityIstanbul Technical University's Scientific Research Project (BAP Project ID: 45396, code: FHD-2024-45396)
文摘In the Fatira(Abu Zawal)mine area,located in the northern Eastern Desert of Egypt,fieldwork and mineralogical analysis,integrated with machine learning techniques applied to Landsat-8 OLI,ASTER,and Sentinel-2 multi-spectral imagery(MSI)data delineate gold-sulfide mineralization in altered rocks.Gold(Au)anomalies in hydrothermal breccias and quartz veins are associated with NE-oriented felsite dykes and silicified granitic rocks.Two main alteration types are identified:a pyrite-sericite-quartz and a sulfide-chlorite-carbonate assemblage,locally with dispersed free-milling Au specks.Dimensionality reduction techniques,including principal component analysis(PCA)and independent component analysis(ICA),enabled mapping of alteration types.Sentinel-2 PC125 composite images offered efficient lithological differentiation,while supervised classifications,i.e.,the support vector machine(SVM)of Landsat-8 yielded an accuracy of 88.55%and a Kappa value of 0.86.ASTER mineral indices contributed to map hydrothermal alteration mineral phases,including sericite,muscovite,kaolinite,and iron oxides.Results indicate that post-magmatic epigenetic hydrothermal activity significantly contributed to the Au-sulfide mineralization in the Fatira area,distinguishing it from the more prevalent orogenic gold deposits in the region.
基金supported by National Natural Science Foundation of China(No.52374155)Anhui Provincial Natural Science Foundation(No.2308085 MF218).
文摘The convolutional neural network(CNN)method based on DeepLabv3+has some problems in the semantic segmentation task of high-resolution remote sensing images,such as fixed receiving field size of feature extraction,lack of semantic information,high decoder magnification,and insufficient detail retention ability.A hierarchical feature fusion network(HFFNet)was proposed.Firstly,a combination of transformer and CNN architectures was employed for feature extraction from images of varying resolutions.The extracted features were processed independently.Subsequently,the features from the transformer and CNN were fused under the guidance of features from different sources.This fusion process assisted in restoring information more comprehensively during the decoding stage.Furthermore,a spatial channel attention module was designed in the final stage of decoding to refine features and reduce the semantic gap between shallow CNN features and deep decoder features.The experimental results showed that HFFNet had superior performance on UAVid,LoveDA,Potsdam,and Vaihingen datasets,and its cross-linking index was better than DeepLabv3+and other competing methods,showing strong generalization ability.
基金supported by the National Natural Science Foundation of China(Nos.42371094,41907253)partially supported by the Interdisciplinary Cultivation Program of Xidian University(No.21103240005)the Postdoctoral Fellowship Program of CPSF(No.GZB20240589)。
文摘INTRODUCTION.On May 1st,2024,around 2:10 a.m.,a catastrophic collapse occurred along the Meilong Expressway near Meizhou City,Guangdong Province,China,at coordinates 24°29′24″N and 116°40′25″E.This collapse resulted in a pavement failure of approximately 17.9 m in length and covering an area of about 184.3 m^(2)(Chinanews,2024).
文摘The use of AI technologies in remote sensing(RS)tasks has been the focus of many individuals in both the professional and academic domains.Having more accessible interfaces and tools that allow people of little or no experience to intuitively interact with RS data of multiple formats is a potential provided by this integration.However,the use of AI and AI agents to help automate RS-related tasks is still in its infancy stage,with some frameworks and interfaces built on top of well-known vision language models(VLM)such as GPT-4,segment anything model(SAM),and grounding DINO.These tools do promise and draw guidelines on the potentials and limitations of existing solutions concerning the use of said models.In this work,the state of the art AI foundation models(FM)are reviewed and used in a multi-modal manner to ingest RS imagery input and perform zero-shot object detection using natural language.The natural language input is then used to define the classes or labels the model should look for,then,both inputs are fed to the pipeline.The pipeline presented in this work makes up for the shortcomings of the general knowledge FMs by stacking pre-processing and post-processing applications on top of the FMs;these applications include tiling to produce uniform patches of the original image for faster detection,outlier rejection of redundant bounding boxes using statistical and machine learning methods.The pipeline was tested with UAV,aerial and satellite images taken over multiple areas.The accuracy for the semantic segmentation showed improvement from the original 64%to approximately 80%-99%by utilizing the pipeline and techniques proposed in this work.GitHub Repository:MohanadDiab/LangRS.
文摘One of the crucial elements that is directly tied to the quality of living organisms is the quality of the water.How-ever,water quality has been adversely affected by plastic pollution,a global environmental disaster that has an effect on aquatic life,wildlife,and human health.To prevent these effects,better monitoring,detection,characterisation,quanti-fication,and tracking of aquatic plastic pollution at regional and global scales is urgently needed.Remote sensing tech-nology is regarded as a useful technique,as it offers a promising new and less labour-intensive tool for the detection,quantification,and characterisation of aquatic plastic pollution.The study seeks to supplement to the body of scientific literature by compiling original data on the monitoring of plastic pollution in aquatic environments using remote sensing technology,which can function as a cost saving method for water pollution and risk management in developing nations.This article provides a profound analysis of plastic pollution,including its categories,sources,distribution,chemical properties,and potential risks.It also provides an in-depth review of remote sensing technologies,satellite-derived in-dices,and research trends related to their applicability.Additionally,the study clarifies the difficulties in using remote sensing technologies for aquatic plastic monitoring and practical ways to reduce aquatic plastic pollution.The study will improve the understanding of aquatic plastic pollution,health hazards,and the suitability of remote sensing technology for aquatic plastic contamination monitoring studies among researchers and interested parties.
基金National Natural Science foundation of China(No.42271432)Foundation of Shanxi Vocational University of Engineering Science and Technology(No.KJ 202426).
文摘Strong sensitivity of satellite microwave remote sensing to the change of surface dielectric properties,as well as the insensitivity to air pollution and solar illumination effects,makes it very suitable for monitoring freeze-thaw conditions.The freeze-thaw cycle changes in the Qinghai-Xizang Plateau have an important impact on the ecological environment and infrastructure.Based on the Scanning Multi-channel Microwave Radiometer(SMMR)and other sensors of microwave satellite,the freeze-thaw cycle data of permafrost in the Qinghai-Xizang Plateau in the past 40 years from 1981 to 2020 was obtained.The changes of soil freeze-thaw conditions in different seasons of 2020 and in the same season of 1990,2000,2010 and 2020 were compared,and the annual variation trend of soil freeze-thaw area in the four years was analyzed.Further,the linear regression analysis was carried out on the duration of soil freezing/thawing/transition and the interannual variation trend under different area conditions from 1981 to 2020.The results show that the freeze-thaw changes in different years are similar.In winter,it is mainly frozen for about 110 days.Spring and autumn are transitional periods,lasting for 170 days.In summer,it is mainly thawed for about 80 days.From 1981 to 2020,the freezing period and the average freezing area of the Qinghai-Xizang Plateau decreased at a rate of 0.22 days and 1986 km^(2) per year,respectively,while the thawing period and the average thawing area increased at a rate of 0.07 days and 3187 km^(2) per year,respectively.The research results provide important theoretical support for the ecological environment and permafrost protection of the Qinghai-Xizang Plateau.
文摘This study presents an AI-driven Spatial Decision Support System (SDSS) aimed at transforming groundwater suitability assessments for domestic and irrigation uses in Visakhapatnam District, Andhra Pradesh, India. By employing advanced remote sensing, GIS, and machine learning techniques, groundwater quality data from 50 monitoring wells, sourced from the Central Ground Water Board (CGWB), was meticulously analysed. Key parameters, including pH, electrical conductivity, total dissolved solids, and major ion concentrations, were evaluated against World Health Organization (WHO) standards to determine domestic suitability. For irrigation, advanced metrics such as Sodium Adsorption Ratio (SAR), Kelly’s Ratio, Residual Sodium Carbonate (RSC), and percentage sodium (% Na) were utilized to assess water quality. The integration of GIS for spatial mapping and AI models for predictive analytics allows for a comprehensive visualization of groundwater quality distribution across the district. Additionally, the irrigation water quality was evaluated using the USA Salinity Laboratory diagram, providing essential insights for effective agricultural water management. This innovative SDSS framework promises to significantly enhance groundwater resource management, fostering sustainable practices for both domestic use and agriculture in the region.
文摘Cloud detection is a critical preprocessing step in remote sensing image processing, as the presence of clouds significantly affects the accuracy of remote sensing data and limits its applicability across various domains. This study presents an enhanced cloud detection method based on the U-Net architecture, designed to address the challenges of multi-scale cloud features and long-range dependencies inherent in remote sensing imagery. A Multi-Scale Dilated Attention (MSDA) module is introduced to effectively integrate multi-scale information and model long-range dependencies across different scales, enhancing the model’s ability to detect clouds of varying sizes. Additionally, a Multi-Head Self-Attention (MHSA) mechanism is incorporated to improve the model’s capacity for capturing finer details, particularly in distinguishing thin clouds from surface features. A multi-path supervision mechanism is also devised to ensure the model learns cloud features at multiple scales, further boosting the accuracy and robustness of cloud mask generation. Experimental results demonstrate that the enhanced model achieves superior performance compared to other benchmarked methods in complex scenarios. It significantly improves cloud detection accuracy, highlighting its strong potential for practical applications in cloud detection tasks.
基金financially supported by the Youth Innovation Promotion Association CAS(No.2021325)the National Natural Science Foundation of China(Nos.52179117,U21A20159)the Research project of Panzhihua Iron and Steel Group Mining Co.,Ltd.(No.2021-P6-D2-05)。
文摘Source identification and deformation analysis of disaster bodies are the main contents of high-steep slope risk assessment,the establishment of high-precision model and the quantification of the fine geometric features of the slope are the prerequisites for the above work.In this study,based on the UAV remote sensing technology in acquiring refined model and quantitative parameters,a semi-automatic dangerous rock identification method based on multi-source data is proposed.In terms of the periodicity UAV-based deformation monitoring,the monitoring accuracy is defined according to the relative accuracy of multi-temporal point cloud.Taking a high-steep slope as research object,the UAV equipped with special sensors was used to obtain multi-source and multitemporal data,including high-precision DOM and multi-temporal 3D point clouds.The geometric features of the outcrop were extracted and superimposed with DOM images to carry out semi-automatic identification of dangerous rock mass,realizes the closed-loop of identification and accuracy verification;changing detection of multi-temporal 3D point clouds was conducted to capture deformation of slope with centimeter accuracy.The results show that the multi-source data-based semiautomatic dangerous rock identification method can complement each other to improve the efficiency and accuracy of identification,and the UAV-based multi-temporal monitoring can reveal the near real-time deformation state of slopes.
基金funded by the National Key Research and Development Program of China(Grant No.2020YFA0608103)the National Science Foundation of China(Grant Nos.42265012 and 31770765).
文摘Enhancing the carbon sink of terrestrial ecosystems is an essential nature-based solution to mitigate global warming and achieve the target of carbon neutrality.Over recent decades,China has launched a series of long-running and large-scale ambitious forestation projects.However,there is still a lack of year-to-year evaluation on the effects of afforestation on carbon sequestration.Satellite remote sensing provides continuous observations of vegetation dynamics and land use and land cover change,is becoming a practical tool to evaluate the changes of vegetation productivity driven by afforestation.Here,a spatially-explicit analysis was conducted by combining Moderate Resolution Imaging Spectroradiometer(MODIS)land cover and three up-to-date remote sensing gross primary productivity(GPP)datasets of China.The results showed that the generated afforestation maps have similar spatial distribution with the national forest inventory data at the provincial level.The accumulative areas of afforestation were 3.02×10^(5)km^(2)in China from 2002 to 2018,it was mainly distributed in Southwest(SW),South(Sou),Southeast(SE)and Northeast(NE)of China.Among them,SW possesses the largest afforestation sub-region,with an area of 9.38×10^(4)km^(2),accounting for 31.06%of the total.There were divergent trends of affores-tation area among different sub-regions.The southern sub-regions showed increasing trends,while the northern sub-regions showed decreasing trends.In keeping with these,the center of annual afforestation moved to the south after 2009.The southern sub-regions were the majority of the cumula-tive GPP,accounting for nearly 70%of the total.The GPP of new afforestation showed an increasing trend from 2002 to 2018,and the increasing rate was higher than existing forests.After afforestation,the GPP change of afforestation was higher than adjacent non-forest over the same period.Our work provides new evidence that afforestation of China has enhanced the carbon assimilation and will deepen our understanding of dynamics of carbon sequestration driven by afforestation.
基金funded by National Natural Science Foundation of China(61603245).
文摘Semantic segmentation of remote sensing images is a critical research area in the field of remote sensing.Despite the success of Convolutional Neural Networks(CNNs),they often fail to capture inter-layer feature relationships and fully leverage contextual information,leading to the loss of important details.Additionally,due to significant intraclass variation and small inter-class differences in remote sensing images,CNNs may experience class confusion.To address these issues,we propose a novel Category-Guided Feature Collaborative Learning Network(CG-FCLNet),which enables fine-grained feature extraction and adaptive fusion.Specifically,we design a Feature Collaborative Learning Module(FCLM)to facilitate the tight interaction of multi-scale features.We also introduce a Scale-Aware Fusion Module(SAFM),which iteratively fuses features from different layers using a spatial attention mechanism,enabling deeper feature fusion.Furthermore,we design a Category-Guided Module(CGM)to extract category-aware information that guides feature fusion,ensuring that the fused featuresmore accurately reflect the semantic information of each category,thereby improving detailed segmentation.The experimental results show that CG-FCLNet achieves a Mean Intersection over Union(mIoU)of 83.46%,an mF1 of 90.87%,and an Overall Accuracy(OA)of 91.34% on the Vaihingen dataset.On the Potsdam dataset,it achieves a mIoU of 86.54%,an mF1 of 92.65%,and an OA of 91.29%.These results highlight the superior performance of CG-FCLNet compared to existing state-of-the-art methods.
基金supported by Henan Province Key R&D Project(241111210400)Henan Provincial Science and Technology Research Project(242102211007 and 242102211020)+1 种基金Jiangsu Science and Technology Programme-General Programme(BK20221260)Science and Technology Innovation Project of Zhengzhou University of Light Industry(23XNKJTD0205).
文摘In recent years,convolutional neural networks(CNN)and Transformer architectures have made significant progress in the field of remote sensing(RS)change detection(CD).Most of the existing methods directly stack multiple layers of Transformer blocks,which achieves considerable improvement in capturing variations,but at a rather high computational cost.We propose a channel-Efficient Change Detection Network(CE-CDNet)to address the problems of high computational cost and imbalanced detection accuracy in remote sensing building change detection.The adaptive multi-scale feature fusion module(CAMSF)and lightweight Transformer decoder(LTD)are introduced to improve the change detection effect.The CAMSF module can adaptively fuse multi-scale features to improve the model’s ability to detect building changes in complex scenes.In addition,the LTD module reduces computational costs and maintains high detection accuracy through an optimized self-attention mechanism and dimensionality reduction operation.Experimental test results on three commonly used remote sensing building change detection data sets show that CE-CDNet can reduce a certain amount of computational overhead while maintaining detection accuracy comparable to existing mainstream models,showing good performance advantages.
文摘While algorithms have been created for land usage in urban settings,there have been few investigations into the extraction of urban footprint(UF).To address this research gap,the study employs several widely used image classification method classified into three categories to evaluate their segmentation capabilities for extracting UF across eight cities.The results indicate that pixel-based methods only excel in clear urban environments,and their overall accuracy is not consistently high.RF and SVM perform well but lack stability in object-based UF extraction,influenced by feature selection and classifier performance.Deep learning enhances feature extraction but requires powerful computing and faces challenges with complex urban layouts.SAM excels in medium-sized urban areas but falters in intricate layouts.Integrating traditional and deep learning methods optimizes UF extraction,balancing accuracy and processing efficiency.Future research should focus on adapting algorithms for diverse urban landscapes to enhance UF extraction accuracy and applicability.
文摘This research systematically investigates urban three-dimensional greening layout optimization and smart ecocity construction using deep learning and remote sensing technology.An improved U-Net++ architecture combined with multi-source remote sensing data achieved high-precision recognition of urban three-dimensional greening with 92.8% overall accuracy.Analysis of spatiotemporal evolution patterns in Shanghai,Hangzhou,and Nanjing revealed that threedimensional greening shows a development trend from demonstration to popularization,with 16.5% annual growth rate.The study quantitatively assessed ecological benefits of various three-dimensional greening types.Results indicate that modular vertical greening and intensive roof gardens yield highest ecological benefits,while climbing-type vertical greening and extensive roof gardens offer optimal benefit-cost ratios.Integration of multiple forms generates 15-22% synergistic enhancement.Compared with traditional planning,the multi-objective optimization-based layout achieved 27.5% increase in carbon sequestration,32.6% improvement in temperature regulation,35.8% enhancement in stormwater management,and 42.3% rise in biodiversity index.Three pilot projects validated that actual ecological benefits reached 90.3-102.3% of predicted values.Multi-scenario simulations indicate optimized layouts can reduce urban heat island intensity by 15.2-18.7%,increase carbon neutrality contribution to 8.6-10.2%,and decrease stormwater runoff peaks by 25.3-32.6%.The findings provide technical methods for urban three-dimensional greening optimization and smart eco-city construction,promoting sustainable urban development.
基金supported in part by the National Natural Foundation of China(Nos.52472334,U2368204)。
文摘In response to challenges posed by complex backgrounds,diverse target angles,and numerous small targets in remote sensing images,alongside the issue of high resource consumption hindering model deployment,we propose an enhanced,lightweight you only look once version 8 small(YOLOv8s)detection algorithm.Regarding network improvements,we first replace tradi-tional horizontal boxes with rotated boxes for target detection,effectively addressing difficulties in feature extraction caused by varying target angles.Second,we design a module integrating convolu-tional neural networks(CNN)and Transformer components to replace specific C2f modules in the backbone network,thereby expanding the model’s receptive field and enhancing feature extraction in complex backgrounds.Finally,we introduce a feature calibration structure to mitigate potential feature mismatches during feature fusion.For model compression,we employ a lightweight channel pruning technique based on localized mean average precision(LMAP)to eliminate redundancies in the enhanced model.Although this approach results in some loss of detection accuracy,it effec-tively reduces the number of parameters,computational load,and model size.Additionally,we employ channel-level knowledge distillation to recover accuracy in the pruned model,further enhancing detection performance.Experimental results indicate that the enhanced algorithm achieves a 6.1%increase in mAP50 compared to YOLOv8s,while simultaneously reducing parame-ters,computational load,and model size by 57.7%,28.8%,and 52.3%,respectively.
基金supported in part by Jiangsu Province High Level“333”Program (0401206044)National Natural Science Foundation of China (61801243,62072255)+4 种基金Program for Scientific Research Foundation for Talented Scholars of Jinling Institute of Technology (JIT-B-202031)University Incubator Foundation of Jinling Institute of Technology (JIT-FHXM-202110)Open Project of Fujian Provincial Key Lab.of Network Security and Cryptology (NSCL-KF2021-02)Open Foundation of National Railway Intelligence Transportation System Engineering Tech.Research Center (RITS2021KF02)China Postdoctoral Science Foundation (2019M651914)。
文摘The secured access is studied in this paper for the network of the image remote sensing.Each sensor in this network encounters the information security when uploading information of the images wirelessly from the sensor to the central collection point.In order to enhance the sensing quality for the remote uploading,the passive reflection surface technique is employed.If one eavesdropper that exists nearby this sensor is keeping on accessing the same networks,he may receive the same image from this sensor.Our goal in this paper is to improve the SNR of legitimate collection unit while cut down the SNR of the eavesdropper as much as possible by adaptively adjust the uploading power from this sensor to enhance the security of the remote sensing images.In order to achieve this goal,the secured energy efficiency performance is theoretically analyzed with respect to the number of the passive reflection elements by calculating the instantaneous performance over the channel fading coefficients.Based on this theoretical result,the secured access is formulated as a mathematical optimization problem by adjusting the sensor uploading power as the unknown variables with the objective of the energy efficiency maximization while satisfying any required maximum data rate of the eavesdropper sensor.Finally,the analytical expression is theoretically derived for the optimum uploading power.Numerical simulations verify the design approach.
基金The Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)under contract No.SML2021SP308the National Natural Science Foundation of China under contract Nos 42176173 and 42476268+1 种基金the Innovation Group Project of Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)under contract No.311020004Guangdong Geographical Science Data Center under contract No.2021B1212100003.
文摘Oyster farming provides substantial ecological and economic benefits but is often constrained by the challenges of selecting suitable sites in dynamic coastal environments.This study presents a tailored oyster suitability index(OSI)for the Zhujiang(Pearl)River Estuary(PRE),developed using Landsat satellite imagery and in situ observations collected from 2013 to 2023.Key environmental parameters,including sea surface temperature(SST),salinity,turbidity,and chlorophyll-a(Chl-a)concentration,were integrated for OSI retrieval.Optimal algorithms for each parameter were identified through evaluation using field measurements,yielding high accuracy,as evidenced by strong determination coefficients(R^(2))and low root mean square error(RMSE):R^(2)=0.98,RMSE=0.74℃for SST;R^(2)=0.94,RMSE=0.50 for salinity;R^(2)=0.95,RMSE=1.21 mg/m^(3)for Chl-a;R^(2)=0.91,RMSE=1.48 NTU for turbidity.The OSI revealed pronounced seasonal and spatial variability,with the highest suitability observed during winter and the lowest during summer.Validation results demonstrated strong alignment between OSI predictions and existing oyster farming zones.These findings underscore the value of remote sensing for scalable,near-real-time aquaculture site assessments.The OSI framework provides a robust decision-support tool for optimizing oyster cultivation,promoting sustainable aquaculture development in dynamic estuarine systems such as the PRE and beyond.
