检索结果-内蒙古大学图书馆

Projecting multiclass global land-use and land-cover change using deep learning and spherical geographic automata model

引用

Big Earth Data 2025年第1期9卷 1-28页

作者： Bright Addae Suzana Dragićević Kirsten Zickfeld Peter Hall Spatial Analysis and Modeling Laboratory Department of GeographySimon Fraser UniversityBurnabyBCCanada Climate Research Laboratory Department of GeographySimon Fraser UniversityBurnabyBCCanada Urban Studies Program Simon Fraser UniversityVancouverBCCanada

Modelling land-use/landcover(LULC)change is vital for addressing global environmental and sustainability issues and evaluating various land system ***,existing geosimulation methodologies for global LULC change fail to account for spatial distortions caused by the Earth’s curvature and do not consider multiple LULC change ***,this research study proposes an enhanced spherical geosimulation modelling approach that integrates deep learning(DL)to simulate change of multiple classes of LULC process under the shared socioeconomic pathways(SSP)at the global *** on the simulation results,the frontiers of urbanization,cropland expansion,and deforestation are indicated to be in developing countries particularly in Asia and *** simulation outputs also reveal 42.5%-63.2%of new urban development would occur on *** proposed modelling approach can serve as a valuable tool for spatial decision-making and environmental policy formulation at the global level.

关键词： Global land-use/land-cover change modelling deep learning spherical geographic automata geographic information systems shared socioeconomic pathways

来源：评论

学校读者我要写书评

暂无评论

Correction to: Changing epidemiology of hemorrhagic fever with renal syndrome in Jiangsu Province, China, 1963–2017

引用

Journal of Public Health 2022年第2期31卷 329-330页

作者： Wang, Wenge Wang, Xiaochen Chen, Yue Yu, Lili Xiao, Shuang Zhang, Jun Li, Yiheng Hong, Shangzhi Fang, Liqun Hu, Jian Hu, Yi Qin, Yuanfang Yue, Ming Zhang, Yun Zhang, Bin Hu, Jianli Zhang, Zhijie Department of Epidemiology and Biostatistics School of Public Health Fudan University Shanghai China Key Laboratory of Public Health Safety Ministry of Education Shanghai China Laboratory for Spatial Analysis and Modeling School of Public Health Fudan University Shanghai China Department of Acute Infectious Disease Control and Prevention Jiangsu Provincial Center for Disease Control and Prevention Nanjing China Department of Epidemiology and Community Medicine Faculty of Medicine University of Ottawa Ottawa Canada Peace Center for Biostatistics Jiann-Ping Hsu College of Public Health Georgia Southern University Statesboro USA State Key Laboratory of Pathogen and Biosecurity Beijing Institute of Microbiology and Epidemiology Beijing China Department of Infectious Diseases The First Affiliated Hospital of Nanjing Medical University Nanjing China Institute of Epidemiology and Microbiology Eastern Theater Command Centers for Disease Control and Prevention Nanjing China

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Single Tree Information Extraction of Oil Palm in Malaysia Based on Sub-Meter Visible Light Satellite Images

SSRN

引用

SSRN 2024年

作者： Zhang, Sen Li, Nan Cui, Yaoping Dong, Jinwei Yu, Le Ran, Lishan Chen, Ziyue Niu, Jiqiang Yan, Wei Kanniah, Kasturi Devi Xiao, Xiangming Zhang, Yongguang Key Laboratory of Geospatial Technology for the Middle and Lower Yellow River Regions Henan University Ministry of Education Kaifeng475004 China College of Geography and Environmental Science Henan University Kaifeng475004 China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application International Institute for Earth System Sciences Nanjing University Nanjing210023 China Key Laboratory of Land Surface Pattern and Simulation Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing100101 China Department of Earth System Science Ministry of Education Key Laboratory for Earth System Modeling Institute for Global Change Studies Tsinghua University Beijing100084 China Department of Geography The University of Hong Kong Pokfulam999077 Hong Kong State Key Laboratory of Earth Surface Processes and Resource Ecology College of Global Change and Earth System Science Beijing Normal University Beijing100875 China College of Geographic Sciences Xinyang Normal University Xinyang464000 China Department of Geoinformation Faculty of Built Environment & Surveying Universiti Teknologi Malaysia Johor Bahru81310 Malaysia Department of Microbiology and Plant Biology Center for Spatial Analysis University of Oklahoma NormanOK73019 United States College of Environment and Planning Faculty of Geoinformation and Real Estate

The distribution of specific tree species and single tree information can shift down the research scale of geography and ecology, bridging research from regional to local scales. However, efficiently and finely extracting the spatial distribution and single tree information for a tree species regionally has always been a challenge due to the constraints of data and algorithms. With sub-meter visible light satellite images (RGB bands) in 2021 to 2022, we constructed a novel method for extracting the spatial distribution and single tree information of oil palm across Malaysia, namely the Single Tree Extraction Method - Oil Palm (STEM-OP). We developed a graphic morphological algorithm based on gradient difference window detection to extract the spatial distribution of oil palms. Then, we proposed an algorithm of double ring sliding detection algorithm to identify the canopy texture features of single oil palm. Finally, an adaptive iterative erosion algorithm was employed to separate overlapping and adjacent canopies into single trees. The overall accuracy of both the spatial distribution and number of single oil palm extracted by STEM-OP exceeded 90%. Our study revealed that the total area of oil palm in Malaysia was 5.25 million hectares, with a total of 572.6 million trees and an average planting density of 109 palms per hectare. The STEM-OP addresses the computational inefficiencies of methods with training samples and limitations of satellite image bands. For the first time, our study extracts the refined spatial distribution of oil palm and obtains the planting density and single tree position on a national scale. All of these are of great value to the formulation of oil palm development policies and ecological protection measures. © 2024, The Authors. All rights reserved.

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

Restoring soil health to reduce irrigation demand and buffer the impacts of drought

引用

Frontiers of Agricultural Science and Engineering 2020年第3期7卷 339-346页

作者： Rebecca SCHNEIDER Stephen MORREALE Zhigang LI Erin MENZIES PLUER Kirsten KURTZ Xilu NI Cuiping WANG Changxiao LI Harold VAN ES Department of Natural Resources Cornell UniversityIthacaNY14853USA School of Agriculture Ningxia UniversityYinchuan 750021China Modeling and Spatial Analysis Lab Department of Geography and Environmental ManagementUniversity of WaterlooWaterlooN2L 3G1Canada Cornell Soil Health Laboratory Cornell UniversityIthacaNY14853USA Breeding Base for State Key Laboratory of Land Degradation and Ecological Restoration of North-western China Ningxia UniversityYinchuan 750021China State Key Laboratory of the Seedling Bioengineering Ningxia Forestry InstituteYinchuan 750004China Collge of Life Sciences Southwest UniversityChongqing 400715China Department Soil and Crop Sciences Cornell UniversityIthacaNY14853USA

Irrigation consumes three quarters of globalwater withdrawals each year. Strategies are needed toreduce irrigationwater use, including increasingtheefficiency of transfer methods and field *** restoration of soil health, specificallythrough organic matter amendments, can substantiallyreduce irrigation demand and increase crop yield. Aprogram to restore severely degraded and desertified soilsby incorporating coarse woodchips into the soil success-fully increased rainfall capture and elevated soil moisturefor several weeks between rainfall events at both Ningxia,north-west China and North Dakota, USA. With additionof fertilizer, woodchip incorporation further increasedgrowth of wheat and alfalfa. Comprehensive soil healthassessment of remnant grasslands was used to developtarget reference soil profiles by which to guide restorationefforts. Given that most agricultural soils are degraded tosome degree, soil health restoration can provide a powerfulstrategy toward achieving global food and water security.

关键词： drought irrigation restoration soil health woodchips

来源：评论

学校读者我要写书评

暂无评论

Deconstructing geospatial agent-based model: Sensitivity analysis of forest insect infestation model 9th

Deconstructing geospatial agent-based model: Sensitivity ana...

引用

Workshop on Agent-Based Models and Complexity Science held as a part of the 9th International Conference on Geographic Information Science, GIScience 2016

作者： Anderson, Taylor Dragićević, Suzana Spatial Analysis and Modeling Research Laboratory Department of Geography Simon Fraser University 8888 University Drive BurnabyBCV5A 1S6 Canada

ISBN: (纸本)9789811044236

Agent-based models (ABM) can be used to represent the spatio-temporal dynamics of real world geospatial phenomena, however because of their complexity, they can be difficult to implement and validate. This study uses the invariant-variant validation approach to further model testing of a developed ABM of forest insect infestation representing spatio-temporal dynamics of the emerald ash borer (EAB). The invariant-variant method deconstructs model results to facilitate an improved understanding of the model’s sensitivity to changes in input parameters and focuses on EAB agents’ access to information. Obtained results indicate that the developed EAB agent-based model represents and maintains both process accuracy and spatial similarity. © 2018, Springer International Publishing AG.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

The identification of forest patches based on nationally defined forest biophysical parameters estimated from LiDAR and Landsat 8 data 39

The identification of forest patches based on nationally def...

引用

39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018

作者： Ikbal Nursal, Wim Budi Prasetyo, Lilik Setiawan, Yudi Environmental Analysis and Spatial Modeling Laboratory Department of Forest Resources Conservation and Ecotourism Faculty of Forestry Bogor Agricultural University Kampus IPB Darmaga Jl. Ulin Lingkar Akademik Bogor Jawa Barat16680 Indonesia

Indonesia has defined the forest by using its biophysical parameters such as canopy cover and height of trees in the size of half of hectare. In reality forest identification or classification in national scale has been done mainly through manual interpretation and classification of optical satellite imageries. To support our proposal to improve national forest monitoring system by digital classification approach, we studied the integration of LiDAR and Landsat 8 image. We chose agroforestry area in Cidanau watershed, West Java as a research site and a case study by considering its accessibility and resemblance to natural forest. From LiDAR data that acquired in September 2017, we extracted First Return Canopy Index (FRCI) as the estimators of forest canopy cover. This index are used together with spectral value of each bands and indices derived from Landsat image to develop statistical models. From the modeling process, there were two models considered valid for predicting forest canopy cover, which is a model that used predictors of band 2, band 5, and band 6 and a model that used Mid-infrared Vegetation Index (MVI). These two models then validated using a set of validation samples. Based on the Root Mean Squared Error (RMSE), a model which used Landsat bands as predictors (RMSE = 0.16) is superior to a model with MVI (RMSE = 0.19). The prediction of the best model was then compared with the land classification that made by the national authority for forest mapping particularly on the forest class. From the result of this study, we are confident that the digital classification approach by taking the advantage of the integration of LiDAR and Landsat 8 imageries is promising method to replace a current method used by the national authority to provide national scale forest map. © 2018 Proceedings - 39th Asian Conference on Remote Sensing: Remote Sensing Enabling Prosperity, ACRS 2018

关键词： Landsat

来源：评论

学校读者我要写书评

暂无评论

Assessing environmental factors associated with regional schistosomiasis prevalence in Anhui Province,Peoples’Republic of China using a geographical detector method

引用

Infectious Diseases of Poverty 2017年第1期6卷 761-768页

作者： Yi Hu Congcong Xia Shizhu Li Michael PWard Can Luo Fenghua Gao Qizhi Wang Shiqing Zhang Zhijie Zhang Department of Epidemiology School of Public HealthFudan UniversityShanghai 200032China Key Laboratory of Public Health Safety Ministry of EducationShanghaiChina Laboratory for Spatial Analysis and Modeling School of Public HealthFudan UniversityShanghaiChina Collaborative Innovation Center of Social Risks Governance in Health School of Public HealthFudan UniversityShanghaiChina National Institute of Parasitic Diseases Chinese Center for Disease Control and PreventionKey Laboratory of Parasite and Vector BiologyMinistry of HealthWHO Collaborating Center for Tropical diseasesShanghaiPeople’s Republic of China Faculty of Veterinary Science The University of Sydney NSWSydneyAustralia Department of Environmental Art and Architecture Changsha Environmental Protection Vocational Technical CollegeChangshaHunanPeople’s Republic of China Anhui Institute of Parasitic Diseases WuhuPeople’s Republic of China No.130 Dong’an Road Xuhui DistrictShanghai 200032China

Background:Schistosomiasis is a water-borne disease caused by trematode worms belonging to genus Schistosoma,which is prevalent most of the developing *** of the disease is usually associated with multiple biological characteristics and social factors but also factors can play a *** studies have assessed the exact and interactive influence of each factor promoting schistosomiasis ***:We used a series of different detectors(i.e.,specific detector,risk detector,ecological detector and interaction detector)to evaluate separate and interactive effects of the environmental factors on schistosomiasis ***,(i)specific detector quantifies the impact of a risk factor on an observed spatial disease pattern,which were ranked statistically by a value of Power of Determinate(PD)calculation;(ii)risk detector detects high risk areas of a disease on the condition that the study area is stratified by a potential risk factor;(iii)ecological detector explores whether a risk factor is more significant than another in controlling the spatial pattern of a disease;(iv)interaction detector probes whether two risk factors when taken together weaken or enhance one another,or whether they are independent in developing a *** data of schistosomiasis based on conventional surveys were obtained at the county level from the health authorities in Anhui Province,China and used in combination with information from Chinese weather stations and internationally available environmental ***:The specific detector identified various factors of potential importance as follows:Proximity to Yangtze River(0.322)>Land cover(0.285)>sunshine hours(0.256)>population density(0.109)>altitude(0.090)>the normalized different vegetation index(NDVI)(0.077)>land surface temperature at daytime(LST_(day))(0.007).The risk detector indicated that areas of schistosomiasis high risk were located within a buffer distance of 50 km from Yangtze ***

关键词： Schistosoma japonicum Geographical detector spatial variation analysis Environmental factors Geographic information systems China

来源：评论

学校读者我要写书评

暂无评论

Exploring the decision tree method for modelling urban land use change

引用

Geomatica 2015年第3期69卷 313-325页

作者： Samardžić-Petrović, Mileva Dragićević, Suzana Bajat, Branislav Kovačević, Miloš Spatial Analysis and Modeling Laboratory Department of Geography Simon Fraser University BurnabyBC Canada Department of Geodesy and Geoinformatics University of Belgrade Belgrade Serbia Department of Construction Project Management University of Belgrade Belgrade Serbia

Land use changes play an important role in interactions between human and physical systems, and have sig nif i cant impacts on the environment at local, regional and global scales. Land use change is a complex process and so developing dynamic models to represent the process is a challenging task. Decision Trees (DT) is a Machine Learning (ML) method with the capability to extract trends and generate a representative model using historical geospatial data. While DT is used in remote sensing as an image classification method, it is not sufficiently examined in land use science. The main objective of this research study is to examine the capability of DT method to model urban land use change. Various numbers of attributes for three municipalities in the City of Belgrade, Republic of Serbia were used. Land use is represented with nine land use classes for three different time instances for the years 2003, 2007 and 2011. The kappa statistics and weighted Area Under Receiver Operating Characteristic Curve (AUC) were used to compare the model outputs with real land use datasets for year 2011. The maximum obtained values for kappa and weighted AUC indicate that DT is a useful method for modelling urban land use change. Furthermore, the derived classification tree generates information about the relationship between the considered causal factors and land use changes and allows for better understanding of the change process. © 2015, Canadian Institute of Geomatics. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Characterizing Shorea robusta communities in the part of Indian Terai landscape

引用

Journal of Forestry Research 2014年第1期25卷 121-128页

作者： V.S.Chitale M.D.Behera S.Matin P.S.Roy V.K.Sinha Spatial Analysis and Modeling Laboratory Centre for Oceans RiversAtmosphere and Land Sciences (CORAL)Indian Institute of Technology (IIT) Kharagpur Center for Earth and Space Sciences University of Hyderabad Uttar Pradesh State Forest Dept.

Shorea robusta Gaertn. f.（Sal）is one of the important tim-ber-yielding plants in India, which dominates the vegetation of Terai landscape of Uttar Pradesh state in India forming various communities based on its associations. The present study deals with delineation, map-ping and characterization of various communities of Sal （Shorea robusta） forests in Terai landscape of Uttar Pradesh, India ranging across over 16 districts. Field survey and visual interpretation based forest vegetation type classification and mapping was carried out as part of the project entitled ‘Biodiversity characterization at landscape level using remote sensing and GIS’. Indian Remote Sensing-P6 （Resourcesat-1） Linear Imaging Self Scanner-III satellite data was used during the study. The total area covered by different Sal forests was found to be approximately 2256.77 km2. Sal communities were identified and characterized based on their spectral properties, physiognomy and phytosociological charac-teristics. Following nine Sal communities were identified, delineated and mapped with reasonable accuracyviz.,Chandar,Damar, dry plains, moist plains, western alluvium, western alluvium plains, mixed moist deciduous, mixed dry deciduous andSiwalik. It is evident from the area estimates that mixed moist deciduous Sal is the most dominant commu-nity in the region covering around （1613.90 km2）, other major communi-ties were found as western alluvium plains Sal （362.44 km2）, mixed dry deciduous Sal （362.44 km2） and dry plains Sal （107.71 km2）. The Terai landscape of Uttar Pradesh faces tremendous anthropogenic pressure leading to deterioration of the forests. Community level information could be used monitoring the status as well as for micro level conserva-tion and planning of the Sal forests in Terai Landscape of Uttar Pradesh.

关键词： Vegetation mapping LISS III Forest management Microlevel Conservation

来源：评论

学校读者我要写书评

暂无评论

Author Correction: The FLUXNET2015 dataset and the ONEFlux processing pipeline for eddy covariance data

引用

Scientific data 2021年第1期8卷 72页

作者： Gilberto Pastorello Carlo Trotta Eleonora Canfora Housen Chu Danielle Christianson You-Wei Cheah Cristina Poindexter Jiquan Chen Abdelrahman Elbashandy Marty Humphrey Peter Isaac Diego Polidori Markus Reichstein Alessio Ribeca Catharine van Ingen Nicolas Vuichard Leiming Zhang Brian Amiro Christof Ammann M Altaf Arain Jonas Ardö Timothy Arkebauer Stefan K Arndt Nicola Arriga Marc Aubinet Mika Aurela Dennis Baldocchi Alan Barr Eric Beamesderfer Luca Belelli Marchesini Onil Bergeron Jason Beringer Christian Bernhofer Daniel Berveiller Dave Billesbach Thomas Andrew Black Peter D Blanken Gil Bohrer Julia Boike Paul V Bolstad Damien Bonal Jean-Marc Bonnefond David R Bowling Rosvel Bracho Jason Brodeur Christian Brümmer Nina Buchmann Benoit Burban Sean P Burns Pauline Buysse Peter Cale Mauro Cavagna Pierre Cellier Shiping Chen Isaac Chini Torben R Christensen James Cleverly Alessio Collalti Claudia Consalvo Bruce D Cook David Cook Carole Coursolle Edoardo Cremonese Peter S Curtis Ettore D'Andrea Humberto da Rocha Xiaoqin Dai Kenneth J Davis Bruno De Cinti Agnes de Grandcourt Anne De Ligne Raimundo C De Oliveira Nicolas Delpierre Ankur R Desai Carlos Marcelo Di Bella Paul di Tommasi Han Dolman Francisco Domingo Gang Dong Sabina Dore Pierpaolo Duce Eric Dufrêne Allison Dunn Jiří Dušek Derek Eamus Uwe Eichelmann Hatim Abdalla M ElKhidir Werner Eugster Cacilia M Ewenz Brent Ewers Daniela Famulari Silvano Fares Iris Feigenwinter Andrew Feitz Rasmus Fensholt Gianluca Filippa Marc Fischer John Frank Marta Galvagno Mana Gharun Damiano Gianelle Bert Gielen Beniamino Gioli Anatoly Gitelson Ignacio Goded Mathias Goeckede Allen H Goldstein Christopher M Gough Michael L Goulden Alexander Graf Anne Griebel Carsten Gruening Thomas Grünwald Albin Hammerle Shijie Han Xingguo Han Birger Ulf Hansen Chad Hanson Juha Hatakka Yongtao He Markus Hehn Bernard Heinesch Nina Hinko-Najera Lukas Hörtnagl Lindsay Hutley Andreas Ibrom Hiroki Ikawa Marcin Jackowicz-Korczynski Dalibor Janouš Wilma Jans Rachhpal Jassal Shicheng Jiang Tomomichi Kato Myr Computational Research Division Lawrence Berkeley National Laboratory Berkeley CA 94720 USA. gzpastorello@lbl.gov. DIBAF University of Tuscia Viterbo 01100 Italy. Euro-Mediterranean Centre on Climate Change Foundation (CMCC) Lecce 73100 Italy. Climate & Ecosystem Sciences Division Lawrence Berkeley National Laboratory Berkeley CA 94720 USA. Computational Research Division Lawrence Berkeley National Laboratory Berkeley CA 94720 USA. Department of Civil Engineering California State University Sacramento CA 95819 USA. Department of Geography Environment and Spatial Sciences Michigan State University East Lansing MI 48823 USA. Department of Computer Science University of Virginia Charlottesville VA 22904 USA. TERN Ecosystem Processes Menzies Creek VIC3159 Australia. Max Planck Institute for Biogeochemistry Jena 07701 Germany. Laboratoire des Sciences du Climat et de l'Environnement (LSCE) CEA CNRS UVSQ UPSACLAY Gif sur Yvette 91190 France. Key Laboratory of Ecosystem Network Observation and Modeling Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing 100101 China. Department of Soil Science University of Manitoba Winnipeg MB R3T2N2 Canada. Department of Agroecology and Environment Agroscope Research Institute Zürich 8046 Switzerland. School of Geography and Earth Sciences McMaster University L8S4K1 Hamilton ON Canada. Department of Physical Geography and Ecosystem Science Lund University Lund 22362 Sweden. Department of Agronomy and Horticulture University of Nebraska-Lincoln Lincoln NE 68583 USA. School of Ecosystem and Forest Sciences The University of Melbourne Richmond VIC3121 Australia. Department of Biology Research Group PLECO University of Antwerp Antwerp 2610 Belgium. Joint Research Centre European Commission Ispra 21027 Italy. TERRA Teaching and Research Center University of Liege Gembloux B-5030 Belgium. Finnish Meteorological Institute Helsinki 00560 Finland. ES

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：