为了解决直推式支持向量机(transductive support vector machines,TSVM)在样本选择自动化程度低和特征学习充分性不足的问题,提出了一种融合深度空间特征与传统影像对象特征的TSVM自动高分遥感影像变化检测方法。首先,采用基于分形网...为了解决直推式支持向量机(transductive support vector machines,TSVM)在样本选择自动化程度低和特征学习充分性不足的问题,提出了一种融合深度空间特征与传统影像对象特征的TSVM自动高分遥感影像变化检测方法。首先,采用基于分形网络演化算法的叠置分割获取多时相高分遥感影像的影像对象,通过卷积神经网络提取遥感影像的深度空间特征,并与灰度、指数和纹理等传统影像对象特征联合构建特征空间;然后,利用卡方变换计算多维特征的加权特征差异度,采用最大期望算法和贝叶斯最小错误判别规则得到二值分割结果,依据变化概率自动将分割结果中准确率较高的部分标记为训练样本;最后,采用标记训练样本获得TSVM的多维特征空间二值分割超平面,进而完成自动变化检测。选择武汉市的两组高分数据集作为实验数据。实验结果表明,该方法能够实现样本自动选择,并且通过融合深度空间特征可以有效提高特征学习的充分性,平均准确率达到了88.84%,平均漏检率较仅利用传统影像对象特征的TSVM法降低了3.29个百分点,在定性和定量的变化检测有效性评价中均得到了提高。展开更多
无线层析成像(radio tomographic imaging,RTI)技术作为无设备目标定位(device-free localization,DFL)的主要方式之一,在被定位目标不携带任何定位装置的情况下仍能实现定位,具有广泛的应用前景.但由于接收信号强度(received signal st...无线层析成像(radio tomographic imaging,RTI)技术作为无设备目标定位(device-free localization,DFL)的主要方式之一,在被定位目标不携带任何定位装置的情况下仍能实现定位,具有广泛的应用前景.但由于接收信号强度(received signal strength,RSS)信息容易受到环境变化和噪声的影响,RTI成像图上往往不可避免地存在着背景噪点,有时甚至还有伪目标出现在图像上.为了提高RTI成像质量,本文提出一种基于核主成分分析(kernel principal component analysis,KPCA)的增强型RTI方法,该方法利用KPCA的学习能力来提取有效受目标影响的链路特征信息,从而达到克服噪声影响和提高定位精度的目的.室内外实验结果表明,该方法的成像质量和定位精度都要优于现有RTI方法.展开更多
Identifying ecologically vulnerable areas is critical for constructing ecological barriers and precisely controlling ecological risks.With the rapid development of big data and Artificial Intelligence(AI)technologies,...Identifying ecologically vulnerable areas is critical for constructing ecological barriers and precisely controlling ecological risks.With the rapid development of big data and Artificial Intelligence(AI)technologies,many intelligent methods have been developed to support the identification of vulnerable ecological areas.This paper reviews the methodological advancements in identifying ecologically vulnerable areas,including geographic zoning,expert integration,mathematical statistics,geographic information visualization,artificial neural networks,and unsupervised deep learning clustering methods.Additionally,we assessed several classic software tools used in ecology and natural resource management.Based on the review,several urgent research challenges for ecological function zoning research are proposed,such as the application of ecological vulnerability assessment intelligent algorithms,big data collaborative analysis,and the development of automated identification software.Considering the requirements in the Mongolian Plateau,this study proposes future development prospects of methods for identifying ecologically vulnerable area zoning,combined with the new AI research paradigm.They include enhancing the comprehensive analysis of multimodal data,increasing ecological barrier big data collaborative processing,advancing the interpretability of ecological function partitioning algorithms,developing automatic zoning software tools,and pushing the collaborative analysis of geographic big data and citizen science data.展开更多
Evapotranspiration(ET)is of great significance for the ecological environment and water resource utilization in arid and semi-arid regions.The Mongolian Plateau,owing to drought,low rainfall,and extremely uneven distr...Evapotranspiration(ET)is of great significance for the ecological environment and water resource utilization in arid and semi-arid regions.The Mongolian Plateau,owing to drought,low rainfall,and extremely uneven distribution of water resources,has a typical temperate continental climate.A refined understanding of the spatiotemporal distribution of ET in this region will help in establishing regulatory strategies for climate change responses,regional livestock regulation,and grassland degradation suppression.In this study,meteorological station data,precipitation data,and the Penman-Monteith model were used to study the temporal and spatial distribution characteristics of actual ET over the Mongolian Plateau from 2011 to 2022.Results found that:(1)The spatial distribution of ET in the Mongolian Plateau showed a high trend in the north and east and a low trend in the middle and south.There was a significant difference in the regional annual ET,with the highest ET reaching over 500 mm and the lowest being only approximately 70 mm.(2)The annual ET values in 2013,2018,and 2019 were relatively large,varying between 80 and 500 mm,and the overall ET of the Mongolian Plateau first decreased,then increased,and then decreased.(3)The temporal distribution exhibits a unimodal trend of increasing and then decreasing,with July being the turning point.May-September was a period of high ET,with the highest ET exceeding 100 mm.When vegetation coverage was high,precipitation was abundant,and the vegetation ET effect was strong.Winter was a period of low ET,with a maximum ET of approximately 10 mm in January and December;the ET for the month with the lowest value was approximately zero.The quantitative inversion method proposed in this study can provide method and data support for north and central Asia,and other large arid and semi-arid areas.展开更多
The permafrost region is one of the most sensitive areas to climate change.With global warming,the Mongolian Plateau permafrost is rapidly degrading,and its vegetation ecosystem is seriously threatened.To address this...The permafrost region is one of the most sensitive areas to climate change.With global warming,the Mongolian Plateau permafrost is rapidly degrading,and its vegetation ecosystem is seriously threatened.To address this challenge,it is essential to understand the impact of climate change on vegetation at different permafrost degradation stages on the Mongolian Plateau.Based on the general permafrost distribution,in this study,we divided different permafrost regions and explored the response of vegetation to climate change at different stages of permafrost degradation by the idea of“space instead of time”from 2014 to 2023.The results of the study showed that:(1)Normalized difference vegetation index(NDVI)values showed a decreasing trend,and the proportion of the decreasing region was in the order of sporadic permafrost region>isolated and sparse permafrost region>continuous and discontinuous permafrost regions.(2)The main controlling factors of vegetation growth in permafrost regions are different,air temperature is the main controlling factor of vegetation growth in isolated and sparse permafrost region(r=-0.736)and sporadic permafrost regions(r=-0.522),and precipitation is the main controlling factor of vegetation growth in continuous and discontinuous permafrost region(r=-0.498).(3)The response of NDVI to climate change varies at different stages of permafrost degradation.In the early stages of permafrost degradation,increased land surface temperature(LST)and air temperature favored vegetation growth and increased vegetation cover,whereas increased precipitation impeded vegetation growth;as the permafrost degraded,increased LST and air temperature impeded vegetation growth,whereas increased precipitation promoted vegetation growth.展开更多
文摘为了解决直推式支持向量机(transductive support vector machines,TSVM)在样本选择自动化程度低和特征学习充分性不足的问题,提出了一种融合深度空间特征与传统影像对象特征的TSVM自动高分遥感影像变化检测方法。首先,采用基于分形网络演化算法的叠置分割获取多时相高分遥感影像的影像对象,通过卷积神经网络提取遥感影像的深度空间特征,并与灰度、指数和纹理等传统影像对象特征联合构建特征空间;然后,利用卡方变换计算多维特征的加权特征差异度,采用最大期望算法和贝叶斯最小错误判别规则得到二值分割结果,依据变化概率自动将分割结果中准确率较高的部分标记为训练样本;最后,采用标记训练样本获得TSVM的多维特征空间二值分割超平面,进而完成自动变化检测。选择武汉市的两组高分数据集作为实验数据。实验结果表明,该方法能够实现样本自动选择,并且通过融合深度空间特征可以有效提高特征学习的充分性,平均准确率达到了88.84%,平均漏检率较仅利用传统影像对象特征的TSVM法降低了3.29个百分点,在定性和定量的变化检测有效性评价中均得到了提高。
文摘无线层析成像(radio tomographic imaging,RTI)技术作为无设备目标定位(device-free localization,DFL)的主要方式之一,在被定位目标不携带任何定位装置的情况下仍能实现定位,具有广泛的应用前景.但由于接收信号强度(received signal strength,RSS)信息容易受到环境变化和噪声的影响,RTI成像图上往往不可避免地存在着背景噪点,有时甚至还有伪目标出现在图像上.为了提高RTI成像质量,本文提出一种基于核主成分分析(kernel principal component analysis,KPCA)的增强型RTI方法,该方法利用KPCA的学习能力来提取有效受目标影响的链路特征信息,从而达到克服噪声影响和提高定位精度的目的.室内外实验结果表明,该方法的成像质量和定位精度都要优于现有RTI方法.
基金The National Key Research and Development Program(2022YFE0119200)The Key Research and Development and Achievement Transformation Plan Project of Inner Mongolia Autonomous Region(2023KJHZ0027)+1 种基金The Key Project of Innovation LREIS(KPI006)The Construction Project of China Knowledge Center for Engineering Sciences and Technology(CKCEST-2023-1-5)。
文摘Identifying ecologically vulnerable areas is critical for constructing ecological barriers and precisely controlling ecological risks.With the rapid development of big data and Artificial Intelligence(AI)technologies,many intelligent methods have been developed to support the identification of vulnerable ecological areas.This paper reviews the methodological advancements in identifying ecologically vulnerable areas,including geographic zoning,expert integration,mathematical statistics,geographic information visualization,artificial neural networks,and unsupervised deep learning clustering methods.Additionally,we assessed several classic software tools used in ecology and natural resource management.Based on the review,several urgent research challenges for ecological function zoning research are proposed,such as the application of ecological vulnerability assessment intelligent algorithms,big data collaborative analysis,and the development of automated identification software.Considering the requirements in the Mongolian Plateau,this study proposes future development prospects of methods for identifying ecologically vulnerable area zoning,combined with the new AI research paradigm.They include enhancing the comprehensive analysis of multimodal data,increasing ecological barrier big data collaborative processing,advancing the interpretability of ecological function partitioning algorithms,developing automatic zoning software tools,and pushing the collaborative analysis of geographic big data and citizen science data.
基金The National Natural Science Foundation of China(32161143025)The Science&Technology Fundamental Resources Investigation Program of China(2022FY101905)+4 种基金The National Key R&D Program of China(2022YFE0119200)The Mongolian Foundation for Science and Technology(NSFC_2022/01,CHN2022/276)The Key R&D and Achievement Transformation Plan Project in Inner Mongolia Autonomous Region(2023KJHZ0027)The Key Project of Innovation LREIS(KPI006)The Construction Project of China Knowledge Center for Engineering Sciences and Technology(CKCEST-2023-1-5)。
文摘Evapotranspiration(ET)is of great significance for the ecological environment and water resource utilization in arid and semi-arid regions.The Mongolian Plateau,owing to drought,low rainfall,and extremely uneven distribution of water resources,has a typical temperate continental climate.A refined understanding of the spatiotemporal distribution of ET in this region will help in establishing regulatory strategies for climate change responses,regional livestock regulation,and grassland degradation suppression.In this study,meteorological station data,precipitation data,and the Penman-Monteith model were used to study the temporal and spatial distribution characteristics of actual ET over the Mongolian Plateau from 2011 to 2022.Results found that:(1)The spatial distribution of ET in the Mongolian Plateau showed a high trend in the north and east and a low trend in the middle and south.There was a significant difference in the regional annual ET,with the highest ET reaching over 500 mm and the lowest being only approximately 70 mm.(2)The annual ET values in 2013,2018,and 2019 were relatively large,varying between 80 and 500 mm,and the overall ET of the Mongolian Plateau first decreased,then increased,and then decreased.(3)The temporal distribution exhibits a unimodal trend of increasing and then decreasing,with July being the turning point.May-September was a period of high ET,with the highest ET exceeding 100 mm.When vegetation coverage was high,precipitation was abundant,and the vegetation ET effect was strong.Winter was a period of low ET,with a maximum ET of approximately 10 mm in January and December;the ET for the month with the lowest value was approximately zero.The quantitative inversion method proposed in this study can provide method and data support for north and central Asia,and other large arid and semi-arid areas.
基金The National Natural Science Foundation of China(32161143025)The Science&Technology Fundamental Resources Investigation Program of China(2022FY101905)+4 种基金The National Key R&D Program of China(2022YFE0119200)The Mongolian Foundation for Science and Technology(NSFC_2022/01,CHN2022/276)The Key R&D and Achievement Transformation Plan Project in Inner Mongolia Autonomous Region(2023KJHZ0027)The Key Project of Innovation LREIS(KPI006)The Construction Project of China Knowledge Center for Engineering Sciences and Technology(CKCEST-2023-1-5)。
文摘The permafrost region is one of the most sensitive areas to climate change.With global warming,the Mongolian Plateau permafrost is rapidly degrading,and its vegetation ecosystem is seriously threatened.To address this challenge,it is essential to understand the impact of climate change on vegetation at different permafrost degradation stages on the Mongolian Plateau.Based on the general permafrost distribution,in this study,we divided different permafrost regions and explored the response of vegetation to climate change at different stages of permafrost degradation by the idea of“space instead of time”from 2014 to 2023.The results of the study showed that:(1)Normalized difference vegetation index(NDVI)values showed a decreasing trend,and the proportion of the decreasing region was in the order of sporadic permafrost region>isolated and sparse permafrost region>continuous and discontinuous permafrost regions.(2)The main controlling factors of vegetation growth in permafrost regions are different,air temperature is the main controlling factor of vegetation growth in isolated and sparse permafrost region(r=-0.736)and sporadic permafrost regions(r=-0.522),and precipitation is the main controlling factor of vegetation growth in continuous and discontinuous permafrost region(r=-0.498).(3)The response of NDVI to climate change varies at different stages of permafrost degradation.In the early stages of permafrost degradation,increased land surface temperature(LST)and air temperature favored vegetation growth and increased vegetation cover,whereas increased precipitation impeded vegetation growth;as the permafrost degraded,increased LST and air temperature impeded vegetation growth,whereas increased precipitation promoted vegetation growth.
