检索结果-南通市图书馆

ConvNeXt-UperNet-Based Deep Learning Model for Road Extraction from High-Resolution Remote Sensing Images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第8期80卷 1907-1925页

作者： Jing Wang Chen Zhang Tianwen Lin geographic Information and tourism College Chuzhou UniversityChuzhou239000China Anhui Province Key Laboratory of Physical geographic Environment Chuzhou UniversityChuzhou239000China

When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in incomplete road extraction and low *** propose the introduction of spatial and channel attention modules to the convolutional neural network ***,ConvNeXt is used as the backbone network,which cooperates with the perceptual analysis network UPerNet,retains the detection head of the semantic segmentation,and builds a new model ConvNeXt-UPerNet to suppress noise *** on the open-source DeepGlobe and CHN6-CUG datasets and introducing the DiceLoss on the basis of CrossEntropyLoss solves the problem of positive and negative sample *** results show that the new network model can achieve the following performance on the DeepGlobe dataset:79.40%for precision(Pre),97.93% for accuracy(Acc),69.28% for intersection over union(IoU),and 83.56% for mean intersection over union(MIoU).On the CHN6-CUG dataset,the model achieves the respective values of 78.17%for Pre,97.63%for Acc,65.4% for IoU,and 81.46% for *** with other network models,the fused ConvNeXt-UPerNet model can extract road information better when faced with the influence of noise contained in high-resolution remote sensing *** also achieves multiscale image feature information with unified perception,ultimately improving the generalization ability of deep learning technology in extracting complex roads from high-resolution remote sensing images.

关键词： Deep learning semantic segmentation remote sensing imagery road extraction

Enhancing transboundary natural tourism resources governance:unveiling the spatial pattern and its influencing factors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Mountain science 2024年第3期21卷 973-986页

作者： ZHANG Shengrui ZHANG Tongyan JU Hongrun WANG Yingjie Management College Ocean University of ChinaQingdao 266100China school of tourism and Geography science Qingdao UniversityQingdao 266071China Institute of geographic sciences and Natural Resources Research Chinese Academy of SciencesBeijing 100101China

tourism resources that span provincial boundaries in China play a pivotal role in regional development,yet effective governance poses persistent *** study addresses this issue by constructing a comprehensive database of transboundary natural tourism resources(TNTR)through amalgamation of diverse data *** the Getis-Ord Gi^(*),kernel density estimation,and geographical detectors,we scrutinize the spatial patterns of TNTR,focusing on both named and unnamed entities,while exploring the influencing *** findings reveal 7883 identified TNTR in China,with mountain tourism resources emerging as the predominant *** provinces,Hunan boasts the highest count,while Shanghai exhibits the *** China demonstrates a pronounced clustering trend in TNTR distribution,with the spatial arrangement of biological landscapes appearing more random compared to geological and water *** China,characterized by intricate terrain,exhibits fewer TNTR,concurrently unveiling a significant presence of unnamed natural tourism ***,administrative segmentation influences TNTR development,generating disparities in regional goals,developmental stages and intensities,and management *** response to these variations,we advocate for strengthening the naming of the unnamed transboundary tourism resources,constructing a geographic database of TNTR for government and establishing a collaborative management mechanism based on TNTR *** research contributes to elucidating the intricate landscape of TNTR,offering insights for tailored governance strategies in the realm of cross-provincial tourism resource management.

关键词： Transboundary natural tourism resources(TNTR) Spatial difference Spatial autocorrelation Governance optimization China

Efficient knowledge distillation for hybrid models:A vision transformer‐convolutional neural network to convolutional neural network approach for classifying remote sensing images

在线全文

学校读者我要写书评

暂无评论

IET Cyber-Systems and Robotics 2024年第3期6卷 1-22页

作者： Huaxiang Song Yuxuan Yuan Zhiwei Ouyang Yu Yang Hui Xiang school of Geography science and tourism Hunan University of Arts and ScienceChangdeHunanChina

In various fields,knowledge distillation(KD)techniques that combine vision transformers(ViTs)and convolutional neural networks(CNNs)as a hybrid teacher have shown remarkable results in ***,in the realm of remote sensing images(RSIs),existing KD research studies are not only scarce but also lack *** issue significantly impedes the deployment of the notable advantages of ViTs and *** tackle this,the authors introduce a novel hybrid‐model KD approach named HMKD‐Net,which comprises a CNN‐ViT ensemble teacher and a CNN *** to popular opinion,the authors posit that the sparsity in RSI data distribution limits the effectiveness and efficiency of hybrid‐model knowledge *** a solution,a simple yet innovative method to handle variances during the KD phase is suggested,leading to substantial enhancements in the effectiveness and efficiency of hybrid knowledge *** authors assessed the performance of HMKD‐Net on three RSI *** findings indicate that HMKD‐Net significantly outperforms other cuttingedge methods while maintaining a significantly smaller ***,HMKD‐Net exceeds other KD‐based methods with a maximum accuracy improvement of 22.8%across various *** ablation experiments indicated,HMKD‐Net has cut down on time expenses by about 80%in the KD *** research study validates that the hybrid‐model KD technique can be more effective and efficient if the data distribution sparsity in RSIs is well handled.

关键词： hybrid‐model knowledge distillation remote sensing image classification vision transformer

A rapid field crop data collection method for complexity cropping patterns using UAV and YOLOv3

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Earth science 2024年第1期18卷 242-255页

作者： Huifang ZHANG Binyao WANG Zhonggang TANG Jiahui XUE Ruihang CHEN Hongcheng KAN Shumiao LU Lina FENG Ye HE Shuhua YI Institute of Fragile Eco-environment Nantong UniversityNantong 226019China school of geographic science Nantong UniversityNantong 226019China Nantong Key Laboratory of Spatial Information Technology R&D and Application School of Geographic ScienceNantong UniversityNantong 226019China

Crop type mapping using remote sensing is critical for global agricultural monitoring and food ***,the complexity of crop planting patternsand spatial heterogeneity pose significant challenges to field data collection,thereby limiting the accuracy of remotely sensed crop *** study proposed a new approach for rapidly collecting field crop data by integrating unmanned aerial vehicle(UAV)images with the YOLOv3(You Only Look Once version 3)*** impacts of UAV flight altitude and the number of training samples on the accuracy of crop identification models were investigated using peanut,soybean,and maize as *** results showed that the average Fl-score for crop type detection accuracy reached 0.91 when utilizing UAV images captured at an altitude of 20 *** addition,a positive correlation was observed between identification accuracy and the number of training *** model developed in this study can rapidly and automatically identify crop types from UAV images,which significantly improves the survey efficiency and provides an innovative solution for acquiring field crop data in large areas.

关键词： deep learning flight altitude crop survey peanut soybean maize

Historical Changes and Multi-scenario Prediction of Land Use and Terrestrial Ecosystem Carbon Storage in China

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese geographical science 2024年第3期34卷 487-503页

作者： AN Yue TAN Xuelan REN Hui LI Yinqi ZHOU Zhou College of Resources Hunan Agricultural UniversityChangsha 410128China school of geographic science Hunan Normal UniversityChangsha 410081China

Terrestrial carbon storage(CS)plays a crucial role in achieving carbon balance and mitigating global climate *** study employs the Shared Socioeconomic Pathways and Representative Concentration Pathways(SSPs-RCPs)published by the Intergovernmental Panel on Climate Change(IPCC)and incorporates the Policy Control Scenario(PCS)regulated by China’s land management *** Future Land Use Simulation(FLUS)model is employed to generate a 1 km resolution land use/cover change(LUCC)dataset for China in 2030 and *** on the carbon density dataset of China’s terrestrial ecosystems,the study analyses CS changes and their relationship with land use changes spanning from 1990 to *** findings indicate that the quantitative changes in land use in China from 1990 to 2020 are characterised by a reduction in the area proportion of cropland and grassland,along with an increase in the impervious surface and forest *** changing trend is projected to continue under the PCS from 2020 to *** the SSPs-RCPs scenario,the proportion of cropland and impervious surface predominantly increases,while the proportions of forest and grassland continuously *** loss in China’s carbon storage from 1990 to 2020 amounted to 0.53×10^(12)kg,primarily due to the reduced area of cropland and *** the SSPs-RCPs scenario,more significant carbon loss occurs,reaching a peak of8.07×10^(12)kg in the SSP4-RCP3.4 *** loss is mainly concentrated in the southeastern coastal area and the Beijing-TianjinHebei(BTH)region of China,with urbanisation and deforestation identified as the primary *** the future,it is advisable to enhance the protection of forests and grassland while stabilising cropland areas and improving the intensity of urban *** research findings offer valuable data support for China’s land management policy,land space optimisation,and the achievement of dual-carbon targets.

关键词： land use change Future Land Use Simulation(FLUS)model carbon storage carbon density dataset land use scenario China

Monitoring Surface Water Change in Northeast China in 1999–2020:Evidence from Satellite Observation and Refined Classification

在线全文

学校读者我要写书评

暂无评论

Chinese geographical science 2024年第1期34卷 106-117页

作者： LIU Kai ZHANG Dapeng CHEN Tan CUI Peipei FAN Chenyu SONG Chunqiao Key Laboratory of Watershed geographic sciences Nanjing Institute of Geography and LimnologyChinese Academy of SciencesNanjing210008China University of Chinese Academy of sciences Nanjing(UCASNJ)Nanjing211135China geographic Information and tourism College Chuzhou UniversityChuzhou239000China

As a typical region with high water demand for agricultural production,understanding the spatiotemporal surface water changes in Northeast China is critical for water resources management and sustainable ***,the long-term variation characteristics of surface water of different water body types in Northeast China remain rarely *** study investigated how surface water bodies of different types(e.g.,lake,reservoir,river,coastal aquaculture,marsh wetland,ephemeral water) changed during1999–2020 in Northeast China based on various remote sensing-based *** results showed that surface water in Northeast China grew dramatically in the past two decades,with an equivalent area increasing from 24 394 km^(2) in 1999 to 34 595 km^(2) in *** surge of ephemeral water is the primary driver of surface water expansion,which could ascribe to shifted precipitation *** wetlands,rivers,and reservoirs experienced a similar trend,with an approximate 20% increase at the interdecadal *** contrast,coastal aquacultures and natural lakes remain relatively *** study is expected to provide a more comprehensive investigation of the surface water variability in Northeast China and has important practical significance for the scientific management of different types of surface water.

关键词： surface water spatiotemporal variation water body classification remote sensing Northeast China

Interannual evolution of the chemical composition,sources and processes of PM_(2.5)in Chengdu,China:Insights from observations in four winters

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental sciences 2024年第4期138卷 32-45页

作者： Junke Zhang Jiaqi Li Yunfei Su Chunying Chen Luyao Chen Xiaojuan Huang Fangzheng Wang Yawen Huang Gehui Wang Faculty of Geosciences and Environmental Engineering Southwest Jiaotong UniversityChengdu 611756China Department of Environmental science&Engineering Shanghai Key Laboratory of Atmospheric Particle Pollution and Prevention(LAP3)Fudan UniversityShanghai 200438China Key Lab of geographic Information science of the Ministry of Education School of Geographic SciencesEast China Normal UniversityShanghai 200241China

The air quality in China has improved significantly in the last decade and,correspondingly,the characteristics of PM_(2.5)have also *** studied the interannual variation of PM_(2.5)in Chengdu,one of the most heavily polluted megacities in southwest China,during the most polluted season(winter).Our results show that the mass concentrations of PM_(2.5)decreased significantly year-by-year,from 195.8±91.0μg/m~3in winter 2016 to 96.1±39.3μg/m^(3)in winter *** mass concentrations of organic matter(OM),SO_()4^(2-),NH_(4)^(+)and NO_(3)^(-)decreased by 49.6%,57.1%,49.7% and 28.7%,*** differential reduction in the concentrations of chemical components increased the contributions from secondary organic carbon and NO_(3)^(-)and there was a larger contribution from mobile *** contribution of OM and NO_(3)^(-)not only increased with increasing levels of pollution,but also increased year-by-year at the same level of *** sources of PM_(2.5)were identified:combustion sources,vehicular emissions,dust and secondary *** aerosols made the highest contribution and increased year-by-year,from 40.6%in winter 2016 to 46.3% in winter *** contrast,the contribution from combustion sources decreased from 14.4% to 8.7%.Our results show the effectiveness of earlier pollution reduction policies and emphasizes that priority should be given to key pollutants(e.g.,OM and NO_(3)^(-))and sources(secondary aerosols and vehicular emissions)in future policies for the reduction of pollution in Chengdu during the winter months.

关键词： PM_(2.5) Chemical composition Sources Interannual evolution Winter Chengdu

Influence of varied drought types on soil conservation service within the framework of climate change:insights from the Jinghe River Basin,China

在线全文

学校读者我要写书评

暂无评论

Journal of Arid Land 2024年第2期16卷 220-245页

作者： BAI Jizhou LI Jing RAN Hui ZHOU Zixiang DANG Hui ZHANG Cheng YU Yuyang school of Geography and tourism Shaanxi Normal UniversityXi'an 710119China College of Geomatics Xi'an University of Science and TechnologyXi'an 710054China

Severe soil erosion and drought are the two main factors affecting the ecological security of the Loess Plateau,*** the influence of drought on soil conservation service is of great importance to regional environmental protection and sustainable ***,there is little research on the coupling relationship between *** this study,focusing on the Jinghe River Basin,China as a case study,we conducted a quantitative evaluation on meteorological,hydrological,and agricultural droughts(represented by the Standardized Precipitation Index(SPI),Standardized Runoff Index(SRI),and Standardized Soil Moisture Index(SSMI),respectively)using the Variable Infiltration Capacity(VIC)model,and quantified the soil conservation service using the Revised Universal Soil Loss Equation(RUSLE)in the historical period(2000-2019)and future period(2026-2060)under two Representative Concentration Pathways(RCPs)(RCP4.5 and RCP8.5).We further examined the influence of the three types of drought on soil conservation service at annual and seasonal *** NASA Earth Exchange Global Daily Downscaled Projections(NEX-GDDP)dataset was used to predict and model the hydrometeorological elements in the future period under the RCP4.5 and RCP8.5 *** results showed that in the historical period,annual-scale meteorological drought exhibited the highest intensity,while seasonal-scale drought was generally weakest in autumn and most severe in *** intensity of all three types of drought will increase over the next 40 years,with a greater increase under the RCP4.5 scenario than under the RCP8.5 ***,the intra-annual variation in the drought intensity of the three types of drought becomes smaller under the two future scenarios relative to the historical period(2000-2019).Soil conservation service exhibits a distribution pattern characterized by high levels in the southwest and southeast and lower levels in the north,and this pattern has remained

关键词： meteorological drought hydrological drought agricultural drought soil conservation service Variable Infiltration Capacity(VIC)model Revised Universal Soil Loss Equation(RUSLE) Jinghe River Basin

Influence of Human Activity Intensity on Habitat Quality in Hainan Tropical Rainforest National Park,China

在线全文

学校读者我要写书评

暂无评论

Chinese geographical science 2024年第3期34卷 519-532页

作者： HAN Nianlong YU Miao JIA Peihong ZHANG Yucheng HU Ke school of Geography and tourism Huizhou UniversityHuizhou 516007China school of Public Administration Hainan Uni-versityHaikou 570228China Department of Land Surveying and Geo-Informatics The Hong Kong Polytechnic UniversityHong KongChina school of geographic sciences and Remote Sensing Guangzhou UniversityGuangzhou 510006China school of Public Administration Nanjing Agricultural UniversityNanjing 210095China

Due to long-term human activity interference,the Hainan Tropical Rainforest National Park(HTRNP)of China has experienced ecological problems such as habitat fragmentation and biodiversity loss,and with the expanding scope and intensity of human activity impact,the regional ecological security is facing serious challenges.A scientific assessment of the interrelationship between human activity intensity and habitat quality in the HTRNP is a prerequisite for achieving effective management of ecological disturbances caused by human activities and can also provide scientific strategies for the sustainable development of the *** on the land use change data in 2000,2010,and 2020,the spatial and temporal variations and the relationship between habitat quality(HQ)and human activity intensity(HAI)in the HTRNP were explored using the integrated valuation of ecosystem services and trade-offs(InVEST)*** dynamics and land use simulation models were also combined to conduct multi-scenario simulations of their *** results showed that during 2000–2020,the habitat quality of the HTRNP improved,the intensity of human activities decreased each year,and there was a negative correlation between the ***,the system dynamic model could be well coupled with the land use simulation model by combining socio-economic and natural *** simulation scenarios of the coupling model showed that the harmonious development(HD)scenario is effective in curbing the increasing trend of human activity intensity and decreasing trend of habitat quality,with a weaker trade-off between the two compared with the baseline development(BD)and investment priority oriented(IPO)*** maintain the authenticity and integrity of the HTRNP,effective measures such as ecological corridor construction,ecological restoration,and the implementation of ecological compensation policies need to be strengthened.

关键词： human activity intensity(HAI) habitat quality(HQ) bivariate spatial autocorrelation system dynamics model integrated valuation of ecosystem services and trade-offs(InVEST)model Hainan Tropical Rainforest National Park(HTRNP)of China