The Lhasa River Basin forms an essential human settlement area in the southern part of the Qinghai-Tibet Plateau.This study employed ecosystem service value(ESV)evaluation model,terrain gradient grading,and Geodetecto...The Lhasa River Basin forms an essential human settlement area in the southern part of the Qinghai-Tibet Plateau.This study employed ecosystem service value(ESV)evaluation model,terrain gradient grading,and Geodetector to analyze land use and ESV in the Lhasa River Basin from 1985 to 2020.The findings reveal that:(1)From 1985 to 2020,grassland was the dominant land use.There was a trend of grassland reduction and the expansion of other land types.(2)ESV has increased over the research period(with a total increase of 0.84%),with higher values in the southeast and lower values in the northwest.Grassland contributed the most to ESV,and climate regulation and hydrological regulation were the ecosystem services that contribute the most to ESV.(3)Natural factors like NDVI and altitude,as well as economic factors like population density and distance from roads,influenced the spatial differentiation of ESV,the explanatory power of NDVI reached up to 0.47.The interaction between factors had a greater impact than individual factors.These research results can provide theoretical support for national spatial planning and ecological environment protection in the Lhasa River Basin and other similar areas.展开更多
The Da-Xiao Liangshan mountains are critical ecological function areas and essential ecological barriers in the upper reaches of the Yangtze River in China.This study selected a total of six periods of land use land c...The Da-Xiao Liangshan mountains are critical ecological function areas and essential ecological barriers in the upper reaches of the Yangtze River in China.This study selected a total of six periods of land use land cover(LULC)data from 1995 to 2020,to estimate the ecosystem service value(ESV)and analyzed its spatiotemporal evolution and topographic gradient divergence.The results showed that:(1)The ESV increased by 1.1 billion yuan,with an increase rate of 1.47%from 1995 to 2020.Two time periods,2005–2010 and 2015–2020,showed more significant increases than other periods.(2)The elevation and slope of mountainous areas determine the type of land use and further influence the spatial pattern of ESV.(3)Although woodland and grassland are the main land use types of the study area(more than 90%),the hydrological regulation function of the water area partially compensated for the impact of the encroachment of the built-up area on the ESV of grassland.(4)The spatial distribution of ESVs showed an inverted V-shaped characteristic as the topographic gradient increased,with the dominant position being the 5th topographic gradient zone.Finally,this study provided relevant recommendations for ecosystem protection and optimization.The findings of this study clarified the influence of topographical factors on the spatial differentiation of ESV and provided novel insights into ecosystem protection.展开更多
From 700 m to 1900 m on the northern slope of Changbai Mountain, 13 plots with an interval of 100 m in elevation were investigated to study the variations of population structure and important value of the main edific...From 700 m to 1900 m on the northern slope of Changbai Mountain, 13 plots with an interval of 100 m in elevation were investigated to study the variations of population structure and important value of the main edificators along the elevation gradient. In their core distribution areas, most of the edificators had healthy population structure and could regenerate smoothly except Larix olgensis, but important value of Larix olgensis had no obvious variations with elevation changes, which showed that Larix olgensis had its own particularity and strong adaptability. At high elevation above 1800 m, Betula ermanii was the only species that could form a mono-dominant community. Important values of Pinus koraiensis and Acer mono had similar changing trends, and they had the similar ecological adaptabilities.展开更多
This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting de...This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting decision tree(GBDT), random forest(RF) and information value(InV) models, were used, and the performances were assessed and compared. In total, 202 landslides were mapped by using a series of field surveys, aerial photographs, and reviews of historical and bibliographical data. Nine causative factors were then considered in landslide susceptibility map generation by using the GBDT, RF and InV models. All of the maps of the causative factors were resampled to a resolution of 28.5 m. Of the 486289 pixels in the area,28526 pixels were landslide pixels, and 457763 pixels were non-landslide pixels. Finally, landslide susceptibility maps were generated by using the three machine learning models, and their performances were assessed through receiver operating characteristic(ROC) curves, the sensitivity, specificity,overall accuracy(OA), and kappa coefficient(KAPPA). The results showed that the GBDT, RF and In V models in overall produced reasonable accurate landslide susceptibility maps. Among these three methods, the GBDT method outperforms the other two machine learning methods, which can provide strong technical support for producing landslide susceptibility maps in TGR.展开更多
The metal and nano-ceramic composite coatings were formed on gray cast iron surface by electrodepositon method.The Ni-Co was used as metal matrix,and the nano-Al2O3 was chosen as second-phase particulates.The gradient...The metal and nano-ceramic composite coatings were formed on gray cast iron surface by electrodepositon method.The Ni-Co was used as metal matrix,and the nano-Al2O3 was chosen as second-phase particulates.The gradient structure of biology material was the model to avoid bad interface bonding and stress distribution,therefore the gradient composite coating was prepared.The morphology of composite coatings was flatter and the microstructure was more com-pact than the pure Ni-Co coatings.Effect of pH value on surface morphology was analyzed,which some microcracks appeared when pH value was greater than 5.The content of codeposition na-no-Al2O3 reached a maximum value at pH value of 3-4,at the same time the properties including mi-crohardness and wear-resistance were analyzed.The result indicated that the mirohardness reached a maximum value and the wear loss volume was less at pH value 3-4.展开更多
The wavelet multiresolution interpolation for continuous functions defined on a finite interval is developed in this study by using a simple alternative of transformation matrix.The wavelet multiresolution interpolati...The wavelet multiresolution interpolation for continuous functions defined on a finite interval is developed in this study by using a simple alternative of transformation matrix.The wavelet multiresolution interpolation Galerkin method that applies this interpolation to represent the unknown function and nonlinear terms independently is proposed to solve the boundary value problems with the mixed Dirichlet-Robin boundary conditions and various nonlinearities,including transcendental ones,in which the discretization process is as simple as that in solving linear problems,and only common two-term connection coefficients are needed.All matrices are independent of unknown node values and lead to high efficiency in the calculation of the residual and Jacobian matrices needed in Newton’s method,which does not require numerical integration in the resulting nonlinear discrete system.The validity of the proposed method is examined through several nonlinear problems with interior or boundary layers.The results demonstrate that the proposed wavelet method shows excellent accuracy and stability against nonuniform grids,and high resolution of localized steep gradients can be achieved by using local refined multiresolution grids.In addition,Newton’s method converges rapidly in solving the nonlinear discrete system created by the proposed wavelet method,including the initial guess far from real solutions.展开更多
Existing explanation methods for Convolutional Neural Networks(CNNs)lack the pixel-level visualization explanations to generate the reliable fine-grained decision features.Since there are inconsistencies between the e...Existing explanation methods for Convolutional Neural Networks(CNNs)lack the pixel-level visualization explanations to generate the reliable fine-grained decision features.Since there are inconsistencies between the explanation and the actual behavior of the model to be interpreted,we propose a Fine-Grained Visual Explanation for CNN,namely F-GVE,which produces a fine-grained explanation with higher consistency to the decision of the original model.The exact backward class-specific gradients with respect to the input image is obtained to highlight the object-related pixels the model used to make prediction.In addition,for better visualization and less noise,F-GVE selects an appropriate threshold to filter the gradient during the calculation and the explanation map is obtained by element-wise multiplying the gradient and the input image to show fine-grained classification decision features.Experimental results demonstrate that F-GVE has good visual performances and highlights the importance of fine-grained decision features.Moreover,the faithfulness of the explanation in this paper is high and it is effective and practical on troubleshooting and debugging detection.展开更多
随着国家大力推进能源供给侧结构性改革,新能源装机容量不断提升,电力市场竞争愈加激烈。另一方面,全球煤炭市场的复杂多变,导致以煤炭为能量来源的发电企业成本上涨。燃煤发热量是衡量煤质的重要评价标准之一,也是采购煤炭最重要的依据...随着国家大力推进能源供给侧结构性改革,新能源装机容量不断提升,电力市场竞争愈加激烈。另一方面,全球煤炭市场的复杂多变,导致以煤炭为能量来源的发电企业成本上涨。燃煤发热量是衡量煤质的重要评价标准之一,也是采购煤炭最重要的依据,对燃煤发热量进行准确预测能够有效地控制电厂运行采购成本。为了实现燃煤发热量的高效预测,采用Pearson系数对相关变量进行特征选取,采用基于密度的噪点空间聚类(Density-Based Spatial Clustering of Applications with Noise,DBSCAN)算法对某电厂自备煤厂近2年1733条化验数据进行去噪,对去噪后数据进行谱聚类(Spectral Clustering,SC)分析。将分类后的子样本集采用极致梯度提升(Extreme Gradient Boosting,XGBoost)算法分别建立预测模型,并与最小二乘法回归(Ordinary Least Squares,OLS)、支持向量机(Support Vector Machines,SVM)模型进行性能比较。结果表明,基于XGBoost的电站燃煤发热量预测模型相较于其他算法准确性有明显提升,泛化能力更强。对经过SC算法分类后的燃煤分别建立预测模型能够进一步提高模型的精细化水平,为燃煤电站发热量预测提供一种可靠高效的方法。展开更多
LED lights have been widely used in urban night space lighting in recent years as they are small,energy-saving,and efficient.This article explores the use of LEDs in bridge night space lighting and their application s...LED lights have been widely used in urban night space lighting in recent years as they are small,energy-saving,and efficient.This article explores the use of LEDs in bridge night space lighting and their application strategies.The aim is to offer valuable insights and references for urban planners and bridge lighting designers in China.By advancing the application of LED technology in bridge night lighting,the goal is to enhance the city’s nighttime ambiance,making the bridge an iconic landmark and a defining feature of the city.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.U20A20112)Construction of Talent Innovation Team and Laboratory Platform of Tibet University-Construction of Plateau Geothermal New Energy Innovation Team and Laboratory Platform(Grant No.2022ZDTD10)Central Support for Local Ministry and Regional Joint Construction/First-class Everest Construction Project-Construction of Geological Resources and Geological Engineering Characteristics(Grant No.Tibetan Finance Pre-indication[2022]No.1).
文摘The Lhasa River Basin forms an essential human settlement area in the southern part of the Qinghai-Tibet Plateau.This study employed ecosystem service value(ESV)evaluation model,terrain gradient grading,and Geodetector to analyze land use and ESV in the Lhasa River Basin from 1985 to 2020.The findings reveal that:(1)From 1985 to 2020,grassland was the dominant land use.There was a trend of grassland reduction and the expansion of other land types.(2)ESV has increased over the research period(with a total increase of 0.84%),with higher values in the southeast and lower values in the northwest.Grassland contributed the most to ESV,and climate regulation and hydrological regulation were the ecosystem services that contribute the most to ESV.(3)Natural factors like NDVI and altitude,as well as economic factors like population density and distance from roads,influenced the spatial differentiation of ESV,the explanatory power of NDVI reached up to 0.47.The interaction between factors had a greater impact than individual factors.These research results can provide theoretical support for national spatial planning and ecological environment protection in the Lhasa River Basin and other similar areas.
基金supported by the National Natural Science Foundation of China(Grant No.52078423)the Sichuan Province Science and Technology Support Program(Grant No.2020YFS0309 and 2020YFS0054)+1 种基金the China Engineering Science and Technology Strategic Consulting Project(Grant No.2022JDR0356)the Key Research Institution of Philosophy and Social Sciences in Sichuan Province:Research Center of National Parks(Grant No.GJGY2023-YB001)。
文摘The Da-Xiao Liangshan mountains are critical ecological function areas and essential ecological barriers in the upper reaches of the Yangtze River in China.This study selected a total of six periods of land use land cover(LULC)data from 1995 to 2020,to estimate the ecosystem service value(ESV)and analyzed its spatiotemporal evolution and topographic gradient divergence.The results showed that:(1)The ESV increased by 1.1 billion yuan,with an increase rate of 1.47%from 1995 to 2020.Two time periods,2005–2010 and 2015–2020,showed more significant increases than other periods.(2)The elevation and slope of mountainous areas determine the type of land use and further influence the spatial pattern of ESV.(3)Although woodland and grassland are the main land use types of the study area(more than 90%),the hydrological regulation function of the water area partially compensated for the impact of the encroachment of the built-up area on the ESV of grassland.(4)The spatial distribution of ESVs showed an inverted V-shaped characteristic as the topographic gradient increased,with the dominant position being the 5th topographic gradient zone.Finally,this study provided relevant recommendations for ecosystem protection and optimization.The findings of this study clarified the influence of topographical factors on the spatial differentiation of ESV and provided novel insights into ecosystem protection.
基金This research was supported by Chinese Academy of Sciences '100 people'project National Natural Science Foundation of China (39970123) and Changbai Mountain Open Research Station.
文摘From 700 m to 1900 m on the northern slope of Changbai Mountain, 13 plots with an interval of 100 m in elevation were investigated to study the variations of population structure and important value of the main edificators along the elevation gradient. In their core distribution areas, most of the edificators had healthy population structure and could regenerate smoothly except Larix olgensis, but important value of Larix olgensis had no obvious variations with elevation changes, which showed that Larix olgensis had its own particularity and strong adaptability. At high elevation above 1800 m, Betula ermanii was the only species that could form a mono-dominant community. Important values of Pinus koraiensis and Acer mono had similar changing trends, and they had the similar ecological adaptabilities.
基金This work was supported in part by the National Natural Science Foundation of China(61601418,41602362,61871259)in part by the Opening Foundation of Hunan Engineering and Research Center of Natural Resource Investigation and Monitoring(2020-5)+1 种基金in part by the Qilian Mountain National Park Research Center(Qinghai)(grant number:GKQ2019-01)in part by the Geomatics Technology and Application Key Laboratory of Qinghai Province,Grant No.QHDX-2019-01.
文摘This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting decision tree(GBDT), random forest(RF) and information value(InV) models, were used, and the performances were assessed and compared. In total, 202 landslides were mapped by using a series of field surveys, aerial photographs, and reviews of historical and bibliographical data. Nine causative factors were then considered in landslide susceptibility map generation by using the GBDT, RF and InV models. All of the maps of the causative factors were resampled to a resolution of 28.5 m. Of the 486289 pixels in the area,28526 pixels were landslide pixels, and 457763 pixels were non-landslide pixels. Finally, landslide susceptibility maps were generated by using the three machine learning models, and their performances were assessed through receiver operating characteristic(ROC) curves, the sensitivity, specificity,overall accuracy(OA), and kappa coefficient(KAPPA). The results showed that the GBDT, RF and In V models in overall produced reasonable accurate landslide susceptibility maps. Among these three methods, the GBDT method outperforms the other two machine learning methods, which can provide strong technical support for producing landslide susceptibility maps in TGR.
基金Funded by the National Natural Science Foundation of China(No.50635030)the National Basic Research of China (No.2007CB616913)
文摘The metal and nano-ceramic composite coatings were formed on gray cast iron surface by electrodepositon method.The Ni-Co was used as metal matrix,and the nano-Al2O3 was chosen as second-phase particulates.The gradient structure of biology material was the model to avoid bad interface bonding and stress distribution,therefore the gradient composite coating was prepared.The morphology of composite coatings was flatter and the microstructure was more com-pact than the pure Ni-Co coatings.Effect of pH value on surface morphology was analyzed,which some microcracks appeared when pH value was greater than 5.The content of codeposition na-no-Al2O3 reached a maximum value at pH value of 3-4,at the same time the properties including mi-crohardness and wear-resistance were analyzed.The result indicated that the mirohardness reached a maximum value and the wear loss volume was less at pH value 3-4.
基金supported by the National Natural Science Foundation of China(Nos.12172154 and 11925204)the 111 Project of China(No.B14044)the National Key Project of China(No.GJXM92579)。
文摘The wavelet multiresolution interpolation for continuous functions defined on a finite interval is developed in this study by using a simple alternative of transformation matrix.The wavelet multiresolution interpolation Galerkin method that applies this interpolation to represent the unknown function and nonlinear terms independently is proposed to solve the boundary value problems with the mixed Dirichlet-Robin boundary conditions and various nonlinearities,including transcendental ones,in which the discretization process is as simple as that in solving linear problems,and only common two-term connection coefficients are needed.All matrices are independent of unknown node values and lead to high efficiency in the calculation of the residual and Jacobian matrices needed in Newton’s method,which does not require numerical integration in the resulting nonlinear discrete system.The validity of the proposed method is examined through several nonlinear problems with interior or boundary layers.The results demonstrate that the proposed wavelet method shows excellent accuracy and stability against nonuniform grids,and high resolution of localized steep gradients can be achieved by using local refined multiresolution grids.In addition,Newton’s method converges rapidly in solving the nonlinear discrete system created by the proposed wavelet method,including the initial guess far from real solutions.
基金This work was partially supported by Beijing Natural Science Foundation(No.4222038)by Open Research Project of the State Key Laboratory of Media Convergence and Communication(Communication University of China),by the National Key RD Program of China(No.2021YFF0307600)and by Fundamental Research Funds for the Central Universities.
文摘Existing explanation methods for Convolutional Neural Networks(CNNs)lack the pixel-level visualization explanations to generate the reliable fine-grained decision features.Since there are inconsistencies between the explanation and the actual behavior of the model to be interpreted,we propose a Fine-Grained Visual Explanation for CNN,namely F-GVE,which produces a fine-grained explanation with higher consistency to the decision of the original model.The exact backward class-specific gradients with respect to the input image is obtained to highlight the object-related pixels the model used to make prediction.In addition,for better visualization and less noise,F-GVE selects an appropriate threshold to filter the gradient during the calculation and the explanation map is obtained by element-wise multiplying the gradient and the input image to show fine-grained classification decision features.Experimental results demonstrate that F-GVE has good visual performances and highlights the importance of fine-grained decision features.Moreover,the faithfulness of the explanation in this paper is high and it is effective and practical on troubleshooting and debugging detection.
文摘随着国家大力推进能源供给侧结构性改革,新能源装机容量不断提升,电力市场竞争愈加激烈。另一方面,全球煤炭市场的复杂多变,导致以煤炭为能量来源的发电企业成本上涨。燃煤发热量是衡量煤质的重要评价标准之一,也是采购煤炭最重要的依据,对燃煤发热量进行准确预测能够有效地控制电厂运行采购成本。为了实现燃煤发热量的高效预测,采用Pearson系数对相关变量进行特征选取,采用基于密度的噪点空间聚类(Density-Based Spatial Clustering of Applications with Noise,DBSCAN)算法对某电厂自备煤厂近2年1733条化验数据进行去噪,对去噪后数据进行谱聚类(Spectral Clustering,SC)分析。将分类后的子样本集采用极致梯度提升(Extreme Gradient Boosting,XGBoost)算法分别建立预测模型,并与最小二乘法回归(Ordinary Least Squares,OLS)、支持向量机(Support Vector Machines,SVM)模型进行性能比较。结果表明,基于XGBoost的电站燃煤发热量预测模型相较于其他算法准确性有明显提升,泛化能力更强。对经过SC算法分类后的燃煤分别建立预测模型能够进一步提高模型的精细化水平,为燃煤电站发热量预测提供一种可靠高效的方法。
文摘LED lights have been widely used in urban night space lighting in recent years as they are small,energy-saving,and efficient.This article explores the use of LEDs in bridge night space lighting and their application strategies.The aim is to offer valuable insights and references for urban planners and bridge lighting designers in China.By advancing the application of LED technology in bridge night lighting,the goal is to enhance the city’s nighttime ambiance,making the bridge an iconic landmark and a defining feature of the city.
