检索结果-内蒙古大学图书馆

RepDDNet:a fast and accurate deforestation detection model with high-resolution remote sensing image

International Journal of Digital Earth 2023年第1期16卷 2013-2033页

作者： Zhipan Wang Zhongwu Wang Dongmei Yan Zewen Mo Hua Zhang Qingling Zhang Shenzhen Key Laboratory of Intelligent Microsatellite Constellation Sun Yat-sen UniversityShenzhenPeople’s Republic of China Land Satellite Remote Sensing Application Center Ministry of Natural ResourcesBeijingPeople’s Republic of China Aerospace Information Research Institute Chinese Academy of SciencesBeijingPeople’s Republic of China Changsha University of Science&Technology ChangshaPeople’s Republic of China

Forest is the largest carbon reservoir and carbon absorber on ***,mapping forest cover change accurately is of great significance to achieving the global carbon neutrality *** forest change information could be acquired by deep learning methods using high-resolution remote sensing ***,deforestation detection based on deep learning on a large-scale region with high-resolution images required huge computational ***,there was an urgent need for a fast and accurate deforestation detection *** this study,we proposed an interesting but effective re-parameterization deforestation detection model,named *** other existing models designed for deforestation detection,the main feature of RepDDNet was its decoupling feature,which means that it allowed the multi-branch structure in the training stages to be converted into a plain structure in the inference stage,thus the computation efficiency can be significantly improved in the inference stage while maintaining the accuracy unchanged.A large-scale experiment was carried out in Ankang city with 2-meter high-resolution remote sensing images(the total area of it was over 20,000 square kilometers),and the result indicated that the model computation efficiency could be improved by nearly 30%compared with the model without ***,compared with other lightweight models,RepDDNet also displayed a trade-off between accuracy and computation efficiency.

关键词： Carbon neutral deforestation detection high-resolution remote sensing image deep learning reparameterization

来源：评论

学校读者我要写书评

暂无评论

Integrated monitoring of lakes’ turbidity in Wuhan, China during the COVID-19 epidemic using multi-sensor satellite observations

引用

International Journal of Digital Earth 2021年第4期14卷 443-463页

作者： Xianghan Sun Jianqiang Liu Jianru Wang Liqiao Tian Qu Zhou Jian Li State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan UniversityWuhanPeople’s Republic of China National Satellite Ocean Application Service BeijingPeople’s Republic of China School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science and TechnologyNanjingPeople’s Republic of China

During the COVID-19 epidemic in Wuhan,China,a series of measures were implemented by the government to prevent the spread of disease,including the lockdown policy and construction of emergency *** estimate the impact of these measures on aquatic environments,turbidity of lakes in Wuhan was dynamically monitored by integrating multi-sensor satellite *** against field measurements,empirical turbidity models were developed with high accuracy(R^(2)=0.77,RMSE=3.13 NTU).Time series of lake turbidity during COVID-19 were then retrieved,and possible factors for the turbidity change were discussed,including meteorological conditions and human *** demonstrated that(1)the mean turbidity showed a 24.9%decline from 33.4 NTU to 25.1 NTU after the lockdown in Wuhan,which dropped 16.0%compared to that in the previous *** decline might be related to the sharp reduction in human activities after the lockdown;(2)no obvious turbidity disturbance was observed in the lakes around emergency hospitals during their construction,and the lakes remained stable after the operation of *** method of integrating multi-sensor satellite observations used in this study shows great performance in term of temporal resolution for dynamic monitoring of inland water.

关键词： COVID-19 lake turbidity multi-sensor observations dynamic monitoring remote sensing

来源：评论

学校读者我要写书评

暂无评论

Unravelling the Enigma of Npp Variation in Chinese Vegetation Ecosystems: The Interplay of Climate Change and Land Use Change

SSRN

引用

SSRN 2023年

作者： Xu, Yong Lu, Yun-Gui Zou, Bin Xu, Ming Feng, Yu-Xi College of Geomatics and Geoinformation Guilin University of Technology Guilin541006 China Department of Surveying and Remote Sensing Science Jiangmen Laboratory of Carbon Science and Technology Hong Kong University of Science and Technology Jiangmen529199 China

Global carbon emissions have significantly exacerbated the greenhouse effect, exerting a profound impact on ecosystems worldwide. Gaining an understanding of the fluctuations in vegetation net primary productivity (NPP) is pivotal in the assessment of environmental quality, estimation of carbon source/sink potential, and facilitation of ecological restoration. Employing MODIS and meteorological data, we conducted a comprehensive analysis of NPP evolution in Chinese vegetation ecosystems, employing Theil–Sen median trend analysis and the Mann–Kendall test. Furthermore, utilizing scenario-based analysis, we quantitatively determined the respective contributions of climate change and land use change to NPP variations across various scales. The overall NPP exhibited a discernible upwards trend from 2000 to 2021, with a growth rate of 29.17 g·(m2·5a)-1. Forestland ecosystems displayed the highest rate of increase (46.98 g·(m2·5a)-1), followed by cropland ecosystems (20.01 g·(m2·5a)-1) and grassland ecosystems (17.02 g·(m2·yr)-1). Geographically, NPP exhibited a spatial pattern characterized by elevated values in the southeast and diminished values in the northwest. At the national level, climate change accounted for 83.14% of the NPP changes, while land use change contributed 14.14%. Notably, climate change emerged as the primary driving force behind NPP variations across all vegetation ecosystems, with land use change exerting the most pronounced influence on cropland ecosystems. At the grid scale (2 km×2 km), land use change accounted for 60.01% of the NPP variations, while climate change dominated in the forestland ecosystem (43.57%). Additionally, land use change played a substantial role in cropland ecosystems, contributing to 60.01% of the NPP variations. Conversely, climate change constituted 43.57% of the NPP changes in forestland ecosystems within China. © 2023, The Authors. All rights reserved.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

A Swin Transformer-Based Fusion Approach for Hyperspectral Image Super-Resolution

A Swin Transformer-Based Fusion Approach for Hyperspectral I...

引用

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： Yuchao Yang Yulei Wang Enyu Zhao Meiping Song Qiang Zhang Center for Hyperspectral Imaging in Remote Sensing (CHIRS) Information Science and Technology College Dalian Maritime University Dalian China

Hyperspectral image (HSI) has attracted much attention because of its rich spectral information. However, due to the limitation of imaging hardware conditions, it is often difficult to directly obtain a high spatial resolution hyperspectral image (HR-HSI). To improve the resolution, it is an economical and effective method to fuse the hyperspectral image with the high spatial resolution multispectral image (HR-MSI) collected from the same scene. In recent years, with the development of deep learning, the convolutional neural network (CNN) based models have been applied to solve the super-resolution reconstruction of hyperspectral images. However, limited by the convolution kernel size, the receptive field of CNN is relatively small with more attention to the local information of the image. In order to solve this problem, this paper proposes a Swin Transformer based super-resolution reconstruction (STSR) network for hyperspectral images. Specifically, Swin Transformer structure is innovatively used in STSR as the skeleton of the network, where the Swin Transformer residuals are used to extract the global spatial feature information in the image. In addition, in order to retain the spectral details in the process of super-resolution reconstruction, a spectral attention module is introduced to preserve the original spectral information. The experimental results show that the high-resolution hyperspectral images fused by the proposed STSR method are superior to the comparison method in terms of vision and quality, which proves the superiority of this method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Hierarchical Temporal Data Fusion Improves Yield Estimation under Extreme Climate Stress

Deep Hierarchical Temporal Data Fusion Improves Yield Estima...

引用

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： Xingguo Xiong Renhai Zhong Qiyu Tian Tao Lin College of Biosystems Engineering and Food Science Zhejiang University Hangzhou China Institute of Applied Remote Sensing and Information Technology Zhejiang University Hangzhou China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Accurate and reliable crop yield estimation under climate stress conditions is essential to ensure global food security. The crop yield variation can be characterized by the daily available climate factors and captured by the multi-temporal remote sensing observations. However, the fusion of multi-temporal remote sensing and meteorological data with different temporal resolutions remains insufficient for crop yield estimation. In this paper, we introduce a two-stream model to perform a feature-level fusion of the vegetation indices and climate variables across multiple time scales. Each stream builds upon a pyramid structure that progressively aggregates the input time series into multi-time-scale feature embeddings. The proposed model is tested in the nine Midwestern states within the US Corn Belt at county level over the years 2006-2012. Quantitative results show that the two-stream model outperforms the one-stream model and typical machine learning under climate stress. The higher estimation performance indicates that feature-level fusion is superior to utilizing the multi-source data rather than simply stacking the input data. Spatial visualization demonstrates that our approach effectively learns to capture the spatial pattern of yield loss, particularly in extreme heat and drought condition. Expanding the number of streams within the proposed architecture enables fusing more data sources, holding promise for crop yield modeling at larger scales.

关键词： Soft sensors Time series analysis Stacking Vegetation mapping Spatial databases Yield estimation Reliability

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Target Detection Based on One-Dimensional Generative Adversarial Network

Hyperspectral Target Detection Based on One-Dimensional Gene...

引用

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： Yulei Wang Hongzhou Wang Yuchao Yang Enyu Zhao Meiping Song Chunyan Yu Center for Hyperspectral Imaging in Remote Sensing (CHIRS) Information Science and Technology College Dalian Maritime University Dalian China

Hyperspectral images provide spectral curves that reflect the "fingerprint" properties of substances, making them suitable for many applications. Thanks to the rapid development of computing resources, deep learning algorithms can significantly improve the cognitive ability of the network by extracting hidden features, and have been successfully applied to hyperspectral image processing, such as classification and detection. In this paper, a new hyperspectral target detection model based on one-dimensional generative adversarial networks (1D-GAN) is proposed. The proposed 1D-GAN network is designed to extract HSI features, and the probability is calculated accordingly whether the pixel to be detected is a target or background. In order to capture the spatial features, the guided filter is then used to obtain the final detection map. Performance comparison with several state-of-the-art methods demonstrate the effectiveness and efficiency of the proposed 1D-GAN algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Construction of Environmental Factor Model Based on Agent

Construction of Environmental Factor Model Based on Agent

引用

作者： Lingyun Li Bo Wang School of Geography Nanjing Normal University School of Remote Sensing & Geomatics Engineering Nanjing University of Information Science and Technology

This paper explores the ability and expression form of the combination of intelligent agents and environmental element modeling from a GIS perspective. Firstly, the complexity of environmental element data is analyzed, and the current spatial-temporal model of environmental data organization in the geographic information field is reviewed, and the full-process operation of the interaction between intelligent agents and the environment is proposed. Secondly, to address the disadvantage of the insufficient storage, analysis, and expression capabilities of intelligent agents for environmental element data, an environmental modeling framework based on spatial grid division applicable to the entire space range is established. By further extending the object-oriented thinking and fully leveraging the expression mechanism of the grid body for internal environmental element attributes and element changes, it is conducive to the efficient use of intelligent agent perception information and computational analysis, scenario deduction and decision support. Finally, through task-driven case studies in the military domain, the effectiveness of the intelligent agent-based environmental element organization and expression model is demonstrated, providing a reference for the wider application of intelligent agent technology in the geographic information field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dust Source Emission Forecasting using GraphSAGE and Delaunay Graph

Dust Source Emission Forecasting using GraphSAGE and Delauna...

引用

International Conference of Signal Processing and Intelligent Systems (ICSPIS)

作者： Maryam Sanisales Ali Vefghi Zahed Rahmati Ali Darvishi Boloorani Department of Mathematics and Computer Science Amirkabir University of Technology Tehran Iran Department of Remote Sensing and GIS Faculty of Geography University of Tehran Tehran Iran

ISBN: (数字)9798331532543

ISBN: (纸本)9798331532550

Our work proposes a method for forecasting dust source emission (DSE) using a graph neural network (GNN). Dust storms pose a significant environmental and health hazard, and accurately forecasting their origin is crucial for mitigation strategies. Traditional methods like direct field measurements are limited in coverage or resolution. This work introduces a framework that constructs a novel connected graph, Delaunay graph from historical dust hotspot events, incorporating spatial and temporal relationships between environmental parameters obtained from remote sensing data. A state-of-the-art GNN model, inductive GraphSAGE, is applied to this graph to predict future active dust source locations. The proposed method outperforms a baseline random forest model, demonstrating its ability to capture temporal relationships throughout months. The AUC of GraphSAGE for dust source emission forecasting was approximately 73% which is 17% better than a simple random forest.

关键词： Storms Prevention and mitigation Signal processing Predictive models Position measurement Graph neural networks Forecasting Spatial resolution Intelligent systems remote sensing

来源：评论

学校读者我要写书评

暂无评论

Algorithm for the Multi-target Joint Detection and Ambiguity Resolving Based on Dynamic programming

Algorithm for the Multi-target Joint Detection and Ambiguity...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Mao, Yitong Song, Chong Wang, Bingnan Zhao, Chenhao Chinese Academy of Sciences National Key Laboratory of Microwave Imaging Technology Aerospace Information Research Institute China University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering China Chinese Academy of Sciences State Key Laboratory of Remote Sensing Science Aerospace Information Research Institute China

ISBN: (纸本)9798350375909

The mode of wide range surveillance and over-sight detection of satellite platform brings serious range ambiguity. The traditional method is to transmit multiple Pulse Repetition Frequencies (PRFs) and correlate them to solve the ambiguity. To ensure the detection of targets by using low threshold, which will lead to a large number of false alarms. In order to solve this problem, a new algorithm for the multi-target joint detection and range ambiguity resolving based on dynamic programming algorithm (DP) is presented. The algorithm divides the false alarm suppression and deblurring into several sub-problems. By splitting into sub-sequences for association operations, and then the sub-results are associated to obtain the unambiguous target state prediction that suppresses false alarms. It effectively alleviates the problem of sudden increase in computational complexity caused by the multi-target, and has better real-time performance. © 2024 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Worldwide impacts of atmospheric vapor pressure deficit on the interannual variability of terrestrial carbon sinks

引用

National science Review 2022年第4期9卷 33-40页

作者： Bin He Chen Chen Shangrong Lin Wenping Yuan Hans W.Chen Deliang Chen Yafeng Zhang Lanlan Guo Xiang Zhao Xuebang Liu Shilong Piao Ziqian Zhong Rui Wang Rui Tang State Key Laboratory of Earth Surface Processes and Resource Ecology College of Global Change and Earth System ScienceBeijing Normal University Department of Application Research Twenty First Century Aerospace Technology Co.Ltd. School of Atmospheric Sciences Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)Sun Yat-sen University Department of Physical Geography and Ecosystem Science Lund University Regional Climate Group Department of Earth SciencesUniversity of Gothenburg Academy of Disaster Reduction and Emergency Management School of GeographyBeijing Normal University State Key Laboratory of Remote Sensing Science Faculty of Geographical ScienceBeijing Normal University Sino-French Institute for Earth System Science College of Urban and Environmental SciencesPeking University

Interannual variability of the terrestrial ecosystem carbon sink is substantially regulated by various environmental variables and highly dominates the interannual variation of atmospheric carbon dioxide（CO2） ***,it is necessary to determine dominating factors affecting the interannual variability of the carbon sink to improve our capability of predicting future terrestrial carbon *** global datasets derived from machine-learning methods and process-based ecosystem models,this study reveals that the inter annual variability of the atmospheric vapor pressure deficit（VPD） was significantly negatively correlated with net ecosystem production（NEP） and substantially impacted the inter annual variability of the atmospheric CO2growth rate（CGR）.Further analyses found widespread constraints of VPD interannual variability on terrestrial gross primary production（GPP）,causing VPD to impact NEP and *** correlation analysis confirms the persistent and widespread impacts of VPD on terrestrial carbon sinks compared to other environmental *** Earth system models underestimate the interannual variability in VPD and its impacts on GPP and *** results highlight the importance of VPD for terrestrial carbon sinks in assessing ecosystems' responses to future climate conditions.

关键词： vapor pressure deficit net ecosystem production gross vegetation production carbon dioxide concentration

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：