Accurate cloud classification plays a crucial role in aviation safety,climate monitoring,and localized weather forecasting.Current research has been focusing on machine learning techniques,particularly deep learning b...Accurate cloud classification plays a crucial role in aviation safety,climate monitoring,and localized weather forecasting.Current research has been focusing on machine learning techniques,particularly deep learning based model,for the types identification.However,traditional approaches such as convolutional neural networks(CNNs)encounter difficulties in capturing global contextual information.In addition,they are computationally expensive,which restricts their usability in resource-limited environments.To tackle these issues,we present the Cloud Vision Transformer(CloudViT),a lightweight model that integrates CNNs with Transformers.The integration enables an effective balance between local and global feature extraction.To be specific,CloudViT comprises two innovative modules:Feature Extraction(E_Module)and Downsampling(D_Module).These modules are able to significantly reduce the number of model parameters and computational complexity while maintaining translation invariance and enhancing contextual comprehension.Overall,the CloudViT includes 0.93×10^(6)parameters,which decreases more than ten times compared to the SOTA(State-of-the-Art)model CloudNet.Comprehensive evaluations conducted on the HBMCD and SWIMCAT datasets showcase the outstanding performance of CloudViT.It achieves classification accuracies of 98.45%and 100%,respectively.Moreover,the efficiency and scalability of CloudViT make it an ideal candidate for deployment inmobile cloud observation systems,enabling real-time cloud image classification.The proposed hybrid architecture of CloudViT offers a promising approach for advancing ground-based cloud image classification.It holds significant potential for both optimizing performance and facilitating practical deployment scenarios.展开更多
Cloud base height(CBH) is a crucial parameter for cloud radiative effect estimates, climate change simulations, and aviation guidance. However, due to the limited information on cloud vertical structures included in p...Cloud base height(CBH) is a crucial parameter for cloud radiative effect estimates, climate change simulations, and aviation guidance. However, due to the limited information on cloud vertical structures included in passive satellite radiometer observations, few operational satellite CBH products are currently available. This study presents a new method for retrieving CBH from satellite radiometers. The method first uses the combined measurements of satellite radiometers and ground-based cloud radars to develop a lookup table(LUT) of effective cloud water content(ECWC), representing the vertically varying cloud water content. This LUT allows for the conversion of cloud water path to cloud geometric thickness(CGT), enabling the estimation of CBH as the difference between cloud top height and CGT. Detailed comparative analysis of CBH estimates from the state-of-the-art ECWC LUT are conducted against four ground-based millimeter-wave cloud radar(MMCR) measurements, and results show that the mean bias(correlation coefficient) is0.18±1.79 km(0.73), which is lower(higher) than 0.23±2.11 km(0.67) as derived from the combined measurements of satellite radiometers and satellite radar-lidar(i.e., Cloud Sat and CALIPSO). Furthermore, the percentages of the CBH biases within 250 m increase by 5% to 10%, which varies by location. This indicates that the CBH estimates from our algorithm are more consistent with ground-based MMCR measurements. Therefore, this algorithm shows great potential for further improvement of the CBH retrievals as ground-based MMCR are being increasingly included in global surface meteorological observing networks, and the improved CBH retrievals will contribute to better cloud radiative effect estimates.展开更多
Objective and accurate classification model or method of cloud image is a prerequisite for accurate weather monitoring and forecast.Thus safety of aircraft taking off and landing and air flight can be guaranteed.Thres...Objective and accurate classification model or method of cloud image is a prerequisite for accurate weather monitoring and forecast.Thus safety of aircraft taking off and landing and air flight can be guaranteed.Thresholding is a kind of simple and effective method of cloud classification.It can realize automated ground-based cloud detection and cloudage observation.The existing segmentation methods based on fixed threshold and single threshold cannot achieve good segmentation effect.Thus it is difficult to obtain the accurate result of cloud detection and cloudage observation.In view of the above-mentioned problems,multi-thresholding methods of ground-based cloud based on exponential entropy/exponential gray entropy and uniform searching particle swarm optimization(UPSO)are proposed.Exponential entropy and exponential gray entropy make up for the defects of undefined value and zero value in Shannon entropy.In addition,exponential gray entropy reflects the relative uniformity of gray levels within the cloud cluster and background cluster.Cloud regions and background regions of different gray level ranges can be distinguished more precisely using the multi-thresholding strategy.In order to reduce computational complexity of original exhaustive algorithm for multi-threshold selection,the UPSO algorithm is adopted.It can find the optimal thresholds quickly and accurately.As a result,the real-time processing of segmentation of groundbased cloud image can be realized.The experimental results show that,in comparison with the existing groundbased cloud image segmentation methods and multi-thresholding method based on maximum Shannon entropy,the proposed methods can extract the boundary shape,textures and details feature of cloud more clearly.Therefore,the accuracies of cloudage detection and morphology classification for ground-based cloud are both improved.展开更多
The degree of spatial similarity plays an important role in map generalization, yet there has been no quantitative research into it. To fill this gap, this study first defines map scale change and spatial similarity d...The degree of spatial similarity plays an important role in map generalization, yet there has been no quantitative research into it. To fill this gap, this study first defines map scale change and spatial similarity degree/relation in multi-scale map spaces and then proposes a model for calculating the degree of spatial similarity between a point cloud at one scale and its gener- alized counterpart at another scale. After validation, the new model features 16 points with map scale change as the x coordinate and the degree of spatial similarity as the y coordinate. Finally, using an application for curve fitting, the model achieves an empirical formula that can calculate the degree of spatial similarity using map scale change as the sole independent variable, and vice versa. This formula can be used to automate algorithms for point feature generalization and to determine when to terminate them during the generalization.展开更多
This paper presents an automated method for discontinuity trace mapping using three-dimensional point clouds of rock mass surfaces.Specifically,the method consists of five steps:(1)detection of trace feature points by...This paper presents an automated method for discontinuity trace mapping using three-dimensional point clouds of rock mass surfaces.Specifically,the method consists of five steps:(1)detection of trace feature points by normal tensor voting theory,(2)co ntraction of trace feature points,(3)connection of trace feature points,(4)linearization of trace segments,and(5)connection of trace segments.A sensitivity analysis was then conducted to identify the optimal parameters of the proposed method.Three field cases,a natural rock mass outcrop and two excavated rock tunnel surfaces,were analyzed using the proposed method to evaluate its validity and efficiency.The results show that the proposed method is more efficient and accurate than the traditional trace mapping method,and the efficiency enhancement is more robust as the number of feature points increases.展开更多
The Western Yunnan Earthquake Predication Test Site set up jointly by the China Earthquake Administration,the National Science Foundation Commission of America,and United States Geological Survey has played an importa...The Western Yunnan Earthquake Predication Test Site set up jointly by the China Earthquake Administration,the National Science Foundation Commission of America,and United States Geological Survey has played an important role in development of early earthquake research work in China. Due to various objective reasons, most of the predicted targets in the earthquake prediction test site have not been achieved,and the development has been hindered. In recent years, the experiment site has been reconsidered,and renamed the "Earthquake Science Experimental Site". Combined with the current development of seismology and the practical needs of disaster prevention and mitigation,we propose adding the "Underground Cloud Map"as the new direction of the experimental site. Using highly repeatable, environmentally friendly and safe airgun sources,we could send constant seismic signals,which realizes continuous monitoring of subsurface velocity changes. Utilizing the high-resolution 3-D crustal structure from ambient noise tomography,we could obtain 4-D (3-D space+1-D time) images of subsurface structures, which we termed the "Underground Cloud Map". The"Underground Cloud Map" can reflect underground velocity and stress changes,providing new means for the earthquake monitoring forecast nationwide,which promotes the conversion of experience-based earthquake prediction to physics-based prediction.展开更多
Cloud computing has created a paradigm shift that affects the way in which business applications are developed. Many business organizations use cloud infrastructures as platforms on which to deploy business applicatio...Cloud computing has created a paradigm shift that affects the way in which business applications are developed. Many business organizations use cloud infrastructures as platforms on which to deploy business applications. Increasing numbers of vendors are supplying the cloud marketplace with a wide range of cloud products. Different vendors offer cloud products in different formats. The cost structures for consuming cloud products can be complex. Finding a suitable set of cloud products that meets an application’s requirements and budget can be a challenging task. In this paper, an ontology-based resource mapping mechanism is proposed. Domain-specific ontologies are used to specify high-level application’s requirements. These are then translated into high-level infrastructure ontologies which then can be mapped onto low-level descriptions of cloud resources. Cost ontologies are proposed for cloud resources. An exemplar media transcoding and delivery service is studied in order to illustrate how high-level requirements can be modeled and mapped onto cloud resources within a budget constraint. The proposed ontologies provide an application-centric mechanism for specifying cloud requirements which can then be used for searching for suitable resources in a multi-provider cloud environment.展开更多
The long awaited cloud computing concept is a reality now due to the transformation of computer generations.However,security challenges have become the biggest obstacles for the advancement of this emerging technology...The long awaited cloud computing concept is a reality now due to the transformation of computer generations.However,security challenges have become the biggest obstacles for the advancement of this emerging technology.A well-established policy framework is defined in this paper to generate security policies which are compliant to requirements and capabilities.Moreover,a federated policy management schema is introduced based on the policy definition framework and a multi-level policy application to create and manage virtual clusters with identical or common security levels.The proposed model consists in the design of a well-established ontology according to security mechanisms,a procedure which classifies nodes with common policies into virtual clusters,a policy engine to enhance the process of mapping requests to a specific node as well as an associated cluster and matchmaker engine to eliminate inessential mapping processes.The suggested model has been evaluated according to performance and security parameters to prove the efficiency and reliability of this multilayered engine in cloud computing environments during policy definition,application and mapping procedures.展开更多
同时定位与建图(Simultaneous localization and mapping,SLAM)能够在未知环境中构建地图并为机器人提供定位信息,是移动机器人领域重要研究方向之一.当前,大多数SLAM算法在静态环境中有较好的表现,但是在车辆和行人等运动物体较多的环...同时定位与建图(Simultaneous localization and mapping,SLAM)能够在未知环境中构建地图并为机器人提供定位信息,是移动机器人领域重要研究方向之一.当前,大多数SLAM算法在静态环境中有较好的表现,但是在车辆和行人等运动物体较多的环境中,广泛存在的动态点使激光点云前后帧的配准精度不高,降低了动态场景下定位和建图的准确性.针对激光点云中存在动态点的问题,本文对SLAM的前端特征提取及后端回环检测模块分别进行改进,以去除动态点,提升SLAM在动态环境下的性能.针对SLAM前端,提出了一种分步的地面分割方法,依据点云高度信息完成地面点粗提取以矫正点云,再使用随机采样一致性方法对矫正后的点云进行精细的地面分割,最后根据高度阈值采用种子生长聚类方法提取非地面动态点,并进行特征提取与配准;针对SLAM后端,使用点云描述子替代传统方法中基于空间位置关系的回环检测方法,以减小累计误差、提高回环检测灵敏度.实验结果显示,本方法在M2DGR street_08序列数据集上较现有方法均方根误差最大降低29.8%,在KITTI04序列数据集上均方根误差最大降幅达42.7%,说明本方法能有效增强动态环境下SLAM系统的全局一致性与定位精度.展开更多
基金funded by Innovation and Development Special Project of China Meteorological Administration(CXFZ2022J038,CXFZ2024J035)Sichuan Science and Technology Program(No.2023YFQ0072)+1 种基金Key Laboratory of Smart Earth(No.KF2023YB03-07)Automatic Software Generation and Intelligent Service Key Laboratory of Sichuan Province(CUIT-SAG202210).
文摘Accurate cloud classification plays a crucial role in aviation safety,climate monitoring,and localized weather forecasting.Current research has been focusing on machine learning techniques,particularly deep learning based model,for the types identification.However,traditional approaches such as convolutional neural networks(CNNs)encounter difficulties in capturing global contextual information.In addition,they are computationally expensive,which restricts their usability in resource-limited environments.To tackle these issues,we present the Cloud Vision Transformer(CloudViT),a lightweight model that integrates CNNs with Transformers.The integration enables an effective balance between local and global feature extraction.To be specific,CloudViT comprises two innovative modules:Feature Extraction(E_Module)and Downsampling(D_Module).These modules are able to significantly reduce the number of model parameters and computational complexity while maintaining translation invariance and enhancing contextual comprehension.Overall,the CloudViT includes 0.93×10^(6)parameters,which decreases more than ten times compared to the SOTA(State-of-the-Art)model CloudNet.Comprehensive evaluations conducted on the HBMCD and SWIMCAT datasets showcase the outstanding performance of CloudViT.It achieves classification accuracies of 98.45%and 100%,respectively.Moreover,the efficiency and scalability of CloudViT make it an ideal candidate for deployment inmobile cloud observation systems,enabling real-time cloud image classification.The proposed hybrid architecture of CloudViT offers a promising approach for advancing ground-based cloud image classification.It holds significant potential for both optimizing performance and facilitating practical deployment scenarios.
基金funded by the National Natural Science Foundation of China (Grant Nos. 42305150 and 42325501)the China Postdoctoral Science Foundation (Grant No. 2023M741774)。
文摘Cloud base height(CBH) is a crucial parameter for cloud radiative effect estimates, climate change simulations, and aviation guidance. However, due to the limited information on cloud vertical structures included in passive satellite radiometer observations, few operational satellite CBH products are currently available. This study presents a new method for retrieving CBH from satellite radiometers. The method first uses the combined measurements of satellite radiometers and ground-based cloud radars to develop a lookup table(LUT) of effective cloud water content(ECWC), representing the vertically varying cloud water content. This LUT allows for the conversion of cloud water path to cloud geometric thickness(CGT), enabling the estimation of CBH as the difference between cloud top height and CGT. Detailed comparative analysis of CBH estimates from the state-of-the-art ECWC LUT are conducted against four ground-based millimeter-wave cloud radar(MMCR) measurements, and results show that the mean bias(correlation coefficient) is0.18±1.79 km(0.73), which is lower(higher) than 0.23±2.11 km(0.67) as derived from the combined measurements of satellite radiometers and satellite radar-lidar(i.e., Cloud Sat and CALIPSO). Furthermore, the percentages of the CBH biases within 250 m increase by 5% to 10%, which varies by location. This indicates that the CBH estimates from our algorithm are more consistent with ground-based MMCR measurements. Therefore, this algorithm shows great potential for further improvement of the CBH retrievals as ground-based MMCR are being increasingly included in global surface meteorological observing networks, and the improved CBH retrievals will contribute to better cloud radiative effect estimates.
基金Supported by the National Natural Science Foundation of China(60872065)the Open Foundation of Key Laboratory of Meteorological Disaster of Ministry of Education at Nanjing University of Information Science & Technology(KLME1108)the Priority Academic Program Development of Jiangsu Higher Education Institutions
文摘Objective and accurate classification model or method of cloud image is a prerequisite for accurate weather monitoring and forecast.Thus safety of aircraft taking off and landing and air flight can be guaranteed.Thresholding is a kind of simple and effective method of cloud classification.It can realize automated ground-based cloud detection and cloudage observation.The existing segmentation methods based on fixed threshold and single threshold cannot achieve good segmentation effect.Thus it is difficult to obtain the accurate result of cloud detection and cloudage observation.In view of the above-mentioned problems,multi-thresholding methods of ground-based cloud based on exponential entropy/exponential gray entropy and uniform searching particle swarm optimization(UPSO)are proposed.Exponential entropy and exponential gray entropy make up for the defects of undefined value and zero value in Shannon entropy.In addition,exponential gray entropy reflects the relative uniformity of gray levels within the cloud cluster and background cluster.Cloud regions and background regions of different gray level ranges can be distinguished more precisely using the multi-thresholding strategy.In order to reduce computational complexity of original exhaustive algorithm for multi-threshold selection,the UPSO algorithm is adopted.It can find the optimal thresholds quickly and accurately.As a result,the real-time processing of segmentation of groundbased cloud image can be realized.The experimental results show that,in comparison with the existing groundbased cloud image segmentation methods and multi-thresholding method based on maximum Shannon entropy,the proposed methods can extract the boundary shape,textures and details feature of cloud more clearly.Therefore,the accuracies of cloudage detection and morphology classification for ground-based cloud are both improved.
基金funded by the Natural Science Foundation Committee,China(41364001,41371435)
文摘The degree of spatial similarity plays an important role in map generalization, yet there has been no quantitative research into it. To fill this gap, this study first defines map scale change and spatial similarity degree/relation in multi-scale map spaces and then proposes a model for calculating the degree of spatial similarity between a point cloud at one scale and its gener- alized counterpart at another scale. After validation, the new model features 16 points with map scale change as the x coordinate and the degree of spatial similarity as the y coordinate. Finally, using an application for curve fitting, the model achieves an empirical formula that can calculate the degree of spatial similarity using map scale change as the sole independent variable, and vice versa. This formula can be used to automate algorithms for point feature generalization and to determine when to terminate them during the generalization.
基金supported by the Special Fund for Basic Research on Scientific Instruments of the National Natural Science Foundation of China(Grant No.4182780021)Emeishan-Hanyuan Highway ProgramTaihang Mountain Highway Program。
文摘This paper presents an automated method for discontinuity trace mapping using three-dimensional point clouds of rock mass surfaces.Specifically,the method consists of five steps:(1)detection of trace feature points by normal tensor voting theory,(2)co ntraction of trace feature points,(3)connection of trace feature points,(4)linearization of trace segments,and(5)connection of trace segments.A sensitivity analysis was then conducted to identify the optimal parameters of the proposed method.Three field cases,a natural rock mass outcrop and two excavated rock tunnel surfaces,were analyzed using the proposed method to evaluate its validity and efficiency.The results show that the proposed method is more efficient and accurate than the traditional trace mapping method,and the efficiency enhancement is more robust as the number of feature points increases.
基金sponsored by the National Natural Science Foundation of China(Grant Nos.41790463 and 41674058)
文摘The Western Yunnan Earthquake Predication Test Site set up jointly by the China Earthquake Administration,the National Science Foundation Commission of America,and United States Geological Survey has played an important role in development of early earthquake research work in China. Due to various objective reasons, most of the predicted targets in the earthquake prediction test site have not been achieved,and the development has been hindered. In recent years, the experiment site has been reconsidered,and renamed the "Earthquake Science Experimental Site". Combined with the current development of seismology and the practical needs of disaster prevention and mitigation,we propose adding the "Underground Cloud Map"as the new direction of the experimental site. Using highly repeatable, environmentally friendly and safe airgun sources,we could send constant seismic signals,which realizes continuous monitoring of subsurface velocity changes. Utilizing the high-resolution 3-D crustal structure from ambient noise tomography,we could obtain 4-D (3-D space+1-D time) images of subsurface structures, which we termed the "Underground Cloud Map". The"Underground Cloud Map" can reflect underground velocity and stress changes,providing new means for the earthquake monitoring forecast nationwide,which promotes the conversion of experience-based earthquake prediction to physics-based prediction.
文摘Cloud computing has created a paradigm shift that affects the way in which business applications are developed. Many business organizations use cloud infrastructures as platforms on which to deploy business applications. Increasing numbers of vendors are supplying the cloud marketplace with a wide range of cloud products. Different vendors offer cloud products in different formats. The cost structures for consuming cloud products can be complex. Finding a suitable set of cloud products that meets an application’s requirements and budget can be a challenging task. In this paper, an ontology-based resource mapping mechanism is proposed. Domain-specific ontologies are used to specify high-level application’s requirements. These are then translated into high-level infrastructure ontologies which then can be mapped onto low-level descriptions of cloud resources. Cost ontologies are proposed for cloud resources. An exemplar media transcoding and delivery service is studied in order to illustrate how high-level requirements can be modeled and mapped onto cloud resources within a budget constraint. The proposed ontologies provide an application-centric mechanism for specifying cloud requirements which can then be used for searching for suitable resources in a multi-provider cloud environment.
文摘The long awaited cloud computing concept is a reality now due to the transformation of computer generations.However,security challenges have become the biggest obstacles for the advancement of this emerging technology.A well-established policy framework is defined in this paper to generate security policies which are compliant to requirements and capabilities.Moreover,a federated policy management schema is introduced based on the policy definition framework and a multi-level policy application to create and manage virtual clusters with identical or common security levels.The proposed model consists in the design of a well-established ontology according to security mechanisms,a procedure which classifies nodes with common policies into virtual clusters,a policy engine to enhance the process of mapping requests to a specific node as well as an associated cluster and matchmaker engine to eliminate inessential mapping processes.The suggested model has been evaluated according to performance and security parameters to prove the efficiency and reliability of this multilayered engine in cloud computing environments during policy definition,application and mapping procedures.
文摘同时定位与建图(Simultaneous localization and mapping,SLAM)能够在未知环境中构建地图并为机器人提供定位信息,是移动机器人领域重要研究方向之一.当前,大多数SLAM算法在静态环境中有较好的表现,但是在车辆和行人等运动物体较多的环境中,广泛存在的动态点使激光点云前后帧的配准精度不高,降低了动态场景下定位和建图的准确性.针对激光点云中存在动态点的问题,本文对SLAM的前端特征提取及后端回环检测模块分别进行改进,以去除动态点,提升SLAM在动态环境下的性能.针对SLAM前端,提出了一种分步的地面分割方法,依据点云高度信息完成地面点粗提取以矫正点云,再使用随机采样一致性方法对矫正后的点云进行精细的地面分割,最后根据高度阈值采用种子生长聚类方法提取非地面动态点,并进行特征提取与配准;针对SLAM后端,使用点云描述子替代传统方法中基于空间位置关系的回环检测方法,以减小累计误差、提高回环检测灵敏度.实验结果显示,本方法在M2DGR street_08序列数据集上较现有方法均方根误差最大降低29.8%,在KITTI04序列数据集上均方根误差最大降幅达42.7%,说明本方法能有效增强动态环境下SLAM系统的全局一致性与定位精度.
