Accurate boundaries of smallholder farm fields are important and indispensable geo-information that benefits farmers,managers,and policymakers in terms of better managing and utilizing their agricultural resources.Due...Accurate boundaries of smallholder farm fields are important and indispensable geo-information that benefits farmers,managers,and policymakers in terms of better managing and utilizing their agricultural resources.Due to their small size,irregular shape,and the use of mixed-cropping techniques,the farm fields of smallholder can be difficult to delineate automatically.In recent years,numerous studies on field contour extraction using a deep Convolutional Neural Network(CNN)have been proposed.However,there is a relative shortage of labeled data for filed boundaries,thus affecting the training effect of CNN.Traditional methods mostly use image flipping,and random rotation for data augmentation.In this paper,we propose to apply Generative Adversarial Network(GAN)for the data augmentation of farm fields label to increase the diversity of samples.Specifically,we propose an automated method featured by Fully Convolutional Neural networks(FCN)in combination with GAN to improve the delineation accuracy of smallholder farms from Very High Resolution(VHR)images.We first investigate four State-Of-The-Art(SOTA)FCN architectures,i.e.,U-Net,PSPNet,SegNet and OCRNet,to find the optimal architecture in the contour detection task of smallholder farm fields.Second,we apply the identified optimal FCN architecture in combination with Contour GAN and pixel2pixel GAN to improve the accuracy of contour detection.We test our method on the study area in the Sudano-Sahelian savanna region of northern Nigeria.The best combination achieved F1 scores of 0.686 on Test Set 1(TS1),0.684 on Test Set 2(TS2),and 0.691 on Test Set 3(TS3).Results indicate that our architecture adapts to a variety of advanced networks and proves its effectiveness in this task.The conceptual,theoretical,and experimental knowledge from this study is expected to seed many GAN-based farm delineation methods in the future.展开更多
The Digital Earth concept as originally proposed by former US Vice president Al Gore is now well established and widely adopted internationally.Similarly,many researchers world-wide are studying the causes,effects and...The Digital Earth concept as originally proposed by former US Vice president Al Gore is now well established and widely adopted internationally.Similarly,many researchers world-wide are studying the causes,effects and impacts of Global Change.The authors commence by describing a five-step approach to the development of Digital Earth technologies.This is followed by a detailed account of Digital Earth research and developments in China.The authors then present the research results of Global Change studies carried out in China,based on the Digital Earth approach.These research results are based on a classification of global change regions.This covers the following global change situations:Forest and grassland fires in Northern China,temperate region desertification and dust storms,underground coal fires,deforestation and carbon sequestration,protection and utilisation of wetlands,Avian Influenza and the spread of diseases,Tibet Plateau uplift and sub-tropical monsoon climate region,and sea-level rise.The research results show that the environment does not behave in a way easily understood by the traditional disciplinary approach.Although man is clearly a contributing factor to certain Global Change aspects,such as underground coal fires,desertification,land use changes etc.,many of the aspects of Global Change are naturally occurring phenomena which have been changing over centuries,and will continue to do so,no matter what actions we undertake to reverse these processes.Hence,in their conclusions,the authors propose that the communities involved in Digital Earth modelling and in Global Change research co-operate closer to overcome the limitations inherent in the current‘conventional’scientific approach,where scientists have very much stayed within their respective scientific boundaries.Such an integrated approach will enable us to build the next level of scientific infrastructure required to understand and predict naturally occurring environmental changes,as well as that of coupled humanenvironmental systems.展开更多
Almost all causative factors of diseases depend on location.The Digital Earth approach is suitable for studying diseases globally.Geospatial information systems integrated with statistical models can be used to model ...Almost all causative factors of diseases depend on location.The Digital Earth approach is suitable for studying diseases globally.Geospatial information systems integrated with statistical models can be used to model the relationship between a disease and its causative factors.Through modelling,the most important causative factors can be extracted and the epidemiology of the disease can be observed.In this paper,skin cancer(the most common type of cancer)has been modelled based on its causative factors,including climate factors,people’s occupations,nutrition habits,socio-economic factors,and usage of chemical fertiliser.To fit the model,a data framework was first designed,and then data were gathered and processed.Finally,the disease was modelled using Generalised Linear Models(GLM),a statistical model based on the location of the factors.The results of this study identify the most important causative factors together with their relative priority.Furthermore,a model was used to predict the change in skin cancer occurrences caused by a change in one of its causative factors.This work illustrates the ability of the model to predict disease occurrence.Thus,by using this Digital Earth approach,skincancer can be studied in all the key countries around the world.展开更多
The concept of Digital Earth(DE)was formalized by Al Gore in 1998.At that time the technologies needed for its implementation were in an embryonic stage and the concept was quite visionary.Since then digital technolog...The concept of Digital Earth(DE)was formalized by Al Gore in 1998.At that time the technologies needed for its implementation were in an embryonic stage and the concept was quite visionary.Since then digital technologies have progressed significantly and their speed and pervasiveness have generated and are still causing the digital transformation of our society.This creates new opportunities and challenges for the realization of DE.‘What is DE today?’,‘What could DE be in the future?’,and‘What is needed to make DE a reality?’.To answer these questions it is necessary to examine DE considering all the technological,scientific,social,and economic aspects,but also bearing in mind the principles that inspired its formulation.By understanding the lessons learned from the past,it becomes possible to identify the remaining scientific and technological challenges,and the actions needed to achieve the ultimate goal of a‘Digital Earth for all’.This article reviews the evolution of the DE vision and its multiple definitions,illustrates what has been achieved so far,explains the impact of digital transformation,illustrates the new vision,and concludes with possible future scenarios and recommended actions to facilitate full DE implementation.展开更多
The Belt and Road initiative has a significant focus on infrastructure,trade,and economic development across a vast region,and it also provides significant opportunities for sustainable development.The combined pressu...The Belt and Road initiative has a significant focus on infrastructure,trade,and economic development across a vast region,and it also provides significant opportunities for sustainable development.The combined pressure of climate variability,intensified use of resources,and the fragility of ecosystems make it very challenging,however,to achieve future sustainability.To develop the path in a sustainable way,it is important to have a comprehensive understanding of these issues across nations and evaluate them in a scientific and well-informed approach.In this context,the Digital Belt and Road(DBAR)program was initiated as an international venture to share expertise,knowledge,technologies,and data to demonstrate the role of Earth observation science and technology and big Earth data applications to support large-scale development.In this paper,we identify pressing challenges,present the research priorities and foci of the DBAR program,and propose solutions where big Earth data can make significant contributions.This paper calls for further joint actions and collaboration to build a digital silk road in support of sustainable development at national,regional and global levels.展开更多
Urbanization is one of the most important social and economic phenomena in the world today.This paper reviews the formation of megacities and summarizes the main problems,challenges and opportunities faced by the sust...Urbanization is one of the most important social and economic phenomena in the world today.This paper reviews the formation of megacities and summarizes the main problems,challenges and opportunities faced by the sustainable development of such large megacities.Issues discussed include the problems of land subsidence in megacities,environmental issues,traffic problems and energy supply aspects.The sustainable development of megacities in other parts of the world provided the references and experiences for the countermeasures of megacity planning and development in China.The vision of Digital Earth and Digital Cities can play a major role in the efficient management and sustainable growth of such megacities all around the world.展开更多
The past two decades have witnessed the burgeoning of enormous digital technologies and data collected via countless channels.They are combined in numerous ways in different fields,including epidemiology,mHealth and m...The past two decades have witnessed the burgeoning of enormous digital technologies and data collected via countless channels.They are combined in numerous ways in different fields,including epidemiology,mHealth and modeling of health systems,with the intention to improve human health(e.g.,clinical decision support,electronic medical record management)[1-6].However,this is a new interdisciplinary area where no single scientific discipline knows how to take full advantage of these data and technologies to solve health problems[1].展开更多
This is a very useful textbook for university teachers giving undergraduate courses in remote sensing,and for those giving courses on environmental issues.It is written by one of the best known European remote sensing...This is a very useful textbook for university teachers giving undergraduate courses in remote sensing,and for those giving courses on environmental issues.It is written by one of the best known European remote sensing professors.The book consists of nine well-structured chapters,which,together with the more than 30 pages of literature references makes it also an excellent reference for post-graduate students doing research on environmental applications of remote sensing.展开更多
by Q.Weng,CRC Press,Taylor&Francis Group,Boca Raton,USA,2011,556 pp.,(hardback),ISBN 978-1-4200-9175-5 This volume is part of the Taylor&Francis Series in Remote Sensing Applications.So far,some seven books ha...by Q.Weng,CRC Press,Taylor&Francis Group,Boca Raton,USA,2011,556 pp.,(hardback),ISBN 978-1-4200-9175-5 This volume is part of the Taylor&Francis Series in Remote Sensing Applications.So far,some seven books have been published in this series,on topics such as:Remote Sensing of Coastal Environments,Remote Sensing of Global Croplands for Food Security,Global Mapping of Human Settlement,Hyperspectral Remote Sensing,etc.展开更多
This paper introduces an improved convolutional neural network based on the conventional U-Net for simulating built-up land expansion.The proposed method hires a pixel-wise semantic segmentation approach considering t...This paper introduces an improved convolutional neural network based on the conventional U-Net for simulating built-up land expansion.The proposed method hires a pixel-wise semantic segmentation approach considering the spatial drivers affecting urbanization as data cubes.Independent variables including altitude,slope,and distance from barren,crop,greenery,roads,and urban areas for 1998,2008,and 2018 were considered as covariates for the simulation of built-up land expansion in Tehran and Karaj regions in Iran.The proposed method was compared with the random forest(RF)algorithm as the baseline model.Evaluation using the area under the total operating characteristic indicated the superiority of our modified U-Net(0.87)over the RF(0.82)algorithm.Furthermore,evaluation using the percent correct metric indicated that our proposed model is capable of learning neighborhood effects effectively leading to simulate built-up land expansion accurately,independent from applying a cellular automata(CA)model.Therefore,the modified U-Net independent from the CA which can consider the neighborhood effects is recommended for the simulation of built-up land expansion precisely.展开更多
This is a most interesting and useful book for readers of this Journal,as it is very relevant to the Digital Earth topic of monitoring changes at global,regional and local levels.The book has eight chapters,which desc...This is a most interesting and useful book for readers of this Journal,as it is very relevant to the Digital Earth topic of monitoring changes at global,regional and local levels.The book has eight chapters,which describe and discuss the occurrence of global drought events,their characteristics,causes and impacts,going from the Holocene(the last 12,000 years),through the twentieth century to the present day.It also gives expected trends to the end of the twenty-first century.The chapters describe the physical processes of drought development and the science behind drought reconstruction,observation and modelling.The book also places drought into the broader issue of Global Change.展开更多
Only one Earth:the long road via Rio to sustainable development,edited by F.Dodds and M.Strauss,London and New York,Routledge,Taylor&Francis Group,2012,312 pp.,(hbk),ISBN 978-0-415-54025-4 This well-written book t...Only one Earth:the long road via Rio to sustainable development,edited by F.Dodds and M.Strauss,London and New York,Routledge,Taylor&Francis Group,2012,312 pp.,(hbk),ISBN 978-0-415-54025-4 This well-written book traces the history and development of the long,and often painful,journey from the original Stockholm Summit of 1972,via the Rio Conference of 1992,to the‘RIO+20’held this year.展开更多
基金Foundation of Anhui Province Key Laboratory of Physical Geographic Environment(No.2022PGE012)
文摘Accurate boundaries of smallholder farm fields are important and indispensable geo-information that benefits farmers,managers,and policymakers in terms of better managing and utilizing their agricultural resources.Due to their small size,irregular shape,and the use of mixed-cropping techniques,the farm fields of smallholder can be difficult to delineate automatically.In recent years,numerous studies on field contour extraction using a deep Convolutional Neural Network(CNN)have been proposed.However,there is a relative shortage of labeled data for filed boundaries,thus affecting the training effect of CNN.Traditional methods mostly use image flipping,and random rotation for data augmentation.In this paper,we propose to apply Generative Adversarial Network(GAN)for the data augmentation of farm fields label to increase the diversity of samples.Specifically,we propose an automated method featured by Fully Convolutional Neural networks(FCN)in combination with GAN to improve the delineation accuracy of smallholder farms from Very High Resolution(VHR)images.We first investigate four State-Of-The-Art(SOTA)FCN architectures,i.e.,U-Net,PSPNet,SegNet and OCRNet,to find the optimal architecture in the contour detection task of smallholder farm fields.Second,we apply the identified optimal FCN architecture in combination with Contour GAN and pixel2pixel GAN to improve the accuracy of contour detection.We test our method on the study area in the Sudano-Sahelian savanna region of northern Nigeria.The best combination achieved F1 scores of 0.686 on Test Set 1(TS1),0.684 on Test Set 2(TS2),and 0.691 on Test Set 3(TS3).Results indicate that our architecture adapts to a variety of advanced networks and proves its effectiveness in this task.The conceptual,theoretical,and experimental knowledge from this study is expected to seed many GAN-based farm delineation methods in the future.
基金The authors also gratefully acknowledge the support of the Centre for Earth Observation and Digital Earth in Beijing,which kindly provided many of the satellite images used to illustrate the global change aspects
文摘The Digital Earth concept as originally proposed by former US Vice president Al Gore is now well established and widely adopted internationally.Similarly,many researchers world-wide are studying the causes,effects and impacts of Global Change.The authors commence by describing a five-step approach to the development of Digital Earth technologies.This is followed by a detailed account of Digital Earth research and developments in China.The authors then present the research results of Global Change studies carried out in China,based on the Digital Earth approach.These research results are based on a classification of global change regions.This covers the following global change situations:Forest and grassland fires in Northern China,temperate region desertification and dust storms,underground coal fires,deforestation and carbon sequestration,protection and utilisation of wetlands,Avian Influenza and the spread of diseases,Tibet Plateau uplift and sub-tropical monsoon climate region,and sea-level rise.The research results show that the environment does not behave in a way easily understood by the traditional disciplinary approach.Although man is clearly a contributing factor to certain Global Change aspects,such as underground coal fires,desertification,land use changes etc.,many of the aspects of Global Change are naturally occurring phenomena which have been changing over centuries,and will continue to do so,no matter what actions we undertake to reverse these processes.Hence,in their conclusions,the authors propose that the communities involved in Digital Earth modelling and in Global Change research co-operate closer to overcome the limitations inherent in the current‘conventional’scientific approach,where scientists have very much stayed within their respective scientific boundaries.Such an integrated approach will enable us to build the next level of scientific infrastructure required to understand and predict naturally occurring environmental changes,as well as that of coupled humanenvironmental systems.
文摘Almost all causative factors of diseases depend on location.The Digital Earth approach is suitable for studying diseases globally.Geospatial information systems integrated with statistical models can be used to model the relationship between a disease and its causative factors.Through modelling,the most important causative factors can be extracted and the epidemiology of the disease can be observed.In this paper,skin cancer(the most common type of cancer)has been modelled based on its causative factors,including climate factors,people’s occupations,nutrition habits,socio-economic factors,and usage of chemical fertiliser.To fit the model,a data framework was first designed,and then data were gathered and processed.Finally,the disease was modelled using Generalised Linear Models(GLM),a statistical model based on the location of the factors.The results of this study identify the most important causative factors together with their relative priority.Furthermore,a model was used to predict the change in skin cancer occurrences caused by a change in one of its causative factors.This work illustrates the ability of the model to predict disease occurrence.Thus,by using this Digital Earth approach,skincancer can be studied in all the key countries around the world.
文摘The concept of Digital Earth(DE)was formalized by Al Gore in 1998.At that time the technologies needed for its implementation were in an embryonic stage and the concept was quite visionary.Since then digital technologies have progressed significantly and their speed and pervasiveness have generated and are still causing the digital transformation of our society.This creates new opportunities and challenges for the realization of DE.‘What is DE today?’,‘What could DE be in the future?’,and‘What is needed to make DE a reality?’.To answer these questions it is necessary to examine DE considering all the technological,scientific,social,and economic aspects,but also bearing in mind the principles that inspired its formulation.By understanding the lessons learned from the past,it becomes possible to identify the remaining scientific and technological challenges,and the actions needed to achieve the ultimate goal of a‘Digital Earth for all’.This article reviews the evolution of the DE vision and its multiple definitions,illustrates what has been achieved so far,explains the impact of digital transformation,illustrates the new vision,and concludes with possible future scenarios and recommended actions to facilitate full DE implementation.
基金the Strategic Priority Research Program of Chinese Academy of Sciences,Project title:CASEarth[XDA19000000]Digital Belt and Road[XDA19030000].
文摘The Belt and Road initiative has a significant focus on infrastructure,trade,and economic development across a vast region,and it also provides significant opportunities for sustainable development.The combined pressure of climate variability,intensified use of resources,and the fragility of ecosystems make it very challenging,however,to achieve future sustainability.To develop the path in a sustainable way,it is important to have a comprehensive understanding of these issues across nations and evaluate them in a scientific and well-informed approach.In this context,the Digital Belt and Road(DBAR)program was initiated as an international venture to share expertise,knowledge,technologies,and data to demonstrate the role of Earth observation science and technology and big Earth data applications to support large-scale development.In this paper,we identify pressing challenges,present the research priorities and foci of the DBAR program,and propose solutions where big Earth data can make significant contributions.This paper calls for further joint actions and collaboration to build a digital silk road in support of sustainable development at national,regional and global levels.
基金the National Key R&D plan on Strategic International Scientific and Technological Innovation Cooperation special project(2016YFE0202300)the Wuhan Chen Guang project(2016070204010114)+2 种基金the Guangzhou Science and Technology project(201604020070)the Special Task of Technical Innovation in Hubei Province project(2016AAA018)the Natural Science Foundation of China(61671332,41771452 and 41771454).
文摘Urbanization is one of the most important social and economic phenomena in the world today.This paper reviews the formation of megacities and summarizes the main problems,challenges and opportunities faced by the sustainable development of such large megacities.Issues discussed include the problems of land subsidence in megacities,environmental issues,traffic problems and energy supply aspects.The sustainable development of megacities in other parts of the world provided the references and experiences for the countermeasures of megacity planning and development in China.The vision of Digital Earth and Digital Cities can play a major role in the efficient management and sustainable growth of such megacities all around the world.
基金funded in part by research grants from the USbased China Medical Board (16-262)the United Nations International Children’s Emergency Fund (2018-Nutrition-2.1.2.3)+2 种基金the National Natural Science Foundation of China (11771240, 91746205, 71673199)funding from Xi’an Jiaotong UniversityUniversity of Twente
文摘The past two decades have witnessed the burgeoning of enormous digital technologies and data collected via countless channels.They are combined in numerous ways in different fields,including epidemiology,mHealth and modeling of health systems,with the intention to improve human health(e.g.,clinical decision support,electronic medical record management)[1-6].However,this is a new interdisciplinary area where no single scientific discipline knows how to take full advantage of these data and technologies to solve health problems[1].
文摘This is a very useful textbook for university teachers giving undergraduate courses in remote sensing,and for those giving courses on environmental issues.It is written by one of the best known European remote sensing professors.The book consists of nine well-structured chapters,which,together with the more than 30 pages of literature references makes it also an excellent reference for post-graduate students doing research on environmental applications of remote sensing.
文摘by Q.Weng,CRC Press,Taylor&Francis Group,Boca Raton,USA,2011,556 pp.,(hardback),ISBN 978-1-4200-9175-5 This volume is part of the Taylor&Francis Series in Remote Sensing Applications.So far,some seven books have been published in this series,on topics such as:Remote Sensing of Coastal Environments,Remote Sensing of Global Croplands for Food Security,Global Mapping of Human Settlement,Hyperspectral Remote Sensing,etc.
文摘This paper introduces an improved convolutional neural network based on the conventional U-Net for simulating built-up land expansion.The proposed method hires a pixel-wise semantic segmentation approach considering the spatial drivers affecting urbanization as data cubes.Independent variables including altitude,slope,and distance from barren,crop,greenery,roads,and urban areas for 1998,2008,and 2018 were considered as covariates for the simulation of built-up land expansion in Tehran and Karaj regions in Iran.The proposed method was compared with the random forest(RF)algorithm as the baseline model.Evaluation using the area under the total operating characteristic indicated the superiority of our modified U-Net(0.87)over the RF(0.82)algorithm.Furthermore,evaluation using the percent correct metric indicated that our proposed model is capable of learning neighborhood effects effectively leading to simulate built-up land expansion accurately,independent from applying a cellular automata(CA)model.Therefore,the modified U-Net independent from the CA which can consider the neighborhood effects is recommended for the simulation of built-up land expansion precisely.
文摘This is a most interesting and useful book for readers of this Journal,as it is very relevant to the Digital Earth topic of monitoring changes at global,regional and local levels.The book has eight chapters,which describe and discuss the occurrence of global drought events,their characteristics,causes and impacts,going from the Holocene(the last 12,000 years),through the twentieth century to the present day.It also gives expected trends to the end of the twenty-first century.The chapters describe the physical processes of drought development and the science behind drought reconstruction,observation and modelling.The book also places drought into the broader issue of Global Change.
文摘Only one Earth:the long road via Rio to sustainable development,edited by F.Dodds and M.Strauss,London and New York,Routledge,Taylor&Francis Group,2012,312 pp.,(hbk),ISBN 978-0-415-54025-4 This well-written book traces the history and development of the long,and often painful,journey from the original Stockholm Summit of 1972,via the Rio Conference of 1992,to the‘RIO+20’held this year.