This page has only limited features, please log in for full access.
Accurate high spatial resolution snow depth mapping in arid and semi-arid regions is of great importance for snow disaster assessment and hydrological modeling. However, due to the complex topography and low spatial-resolution microwave remote-sensing data, the existing snow depth datasets have large errors and uncertainty, and actual spatiotemporal heterogeneity of snow depth cannot be effectively detected. This paper proposed a deep learning approach based on downscaling snow depth retrieval by fusion of satellite remote-sensing data with multiple spatial scales and diverse characteristics. The (Fengyun-3 Microwave Radiation Imager) FY-3 MWRI data were downscaled to 500 m resolution to match Moderate-resolution Imaging Spectroradiometer (MODIS) snow cover, meteorological and geographic data. A deep neural network was constructed to capture detailed spectral and radiation signals and trained to retrieve the higher spatial resolution snow depth from the aforementioned input data and ground observation. Verified by in situ measurements, downscaled snow depth has the lowest root mean square error (RMSE) and mean absolute error (MAE) (8.16 cm, 4.73 cm respectively) among Environmental and Ecological Science Data Center for West China Snow Depth (WESTDC_SD, 9.38 cm and 5.36 cm), the Microwave Radiation Imager (MWRI) Ascend Snow Depth (MWRI_A_SD, 9.45 cm and 5.49 cm) and MWRI Descend Snow Depth (MWRI_D_SD, 10.55 cm and 6.13 cm) in the study area. Meanwhile, downscaled snow depth could provide more detailed information in spatial distribution, which has been used to analyze the decrease of retrieval accuracy by various topography factors.
Linglong Zhu; Yonghong Zhang; Jiangeng Wang; Wei Tian; Qi Liu; Guangyi Ma; Xi Kan; Ya Chu. Downscaling Snow Depth Mapping by Fusion of Microwave and Optical Remote-Sensing Data Based on Deep Learning. Remote Sensing 2021, 13, 584 .
AMA StyleLinglong Zhu, Yonghong Zhang, Jiangeng Wang, Wei Tian, Qi Liu, Guangyi Ma, Xi Kan, Ya Chu. Downscaling Snow Depth Mapping by Fusion of Microwave and Optical Remote-Sensing Data Based on Deep Learning. Remote Sensing. 2021; 13 (4):584.
Chicago/Turabian StyleLinglong Zhu; Yonghong Zhang; Jiangeng Wang; Wei Tian; Qi Liu; Guangyi Ma; Xi Kan; Ya Chu. 2021. "Downscaling Snow Depth Mapping by Fusion of Microwave and Optical Remote-Sensing Data Based on Deep Learning." Remote Sensing 13, no. 4: 584.
Nowcasting is really important for citizen and industry since it matters to everyone on social and economic activities and is significant for monitoring and forecasting disasters. As the foundation of the task, radar extrapolation is the most difficulty to be solved. However, the accuracy of the extrapolation is in a large bias. With the rapid development of computing power, recent researches show that artificial intelligence is a promising approach, especially deep learning approaches in learning accurate patterns and appear well suited for the task of extrapolation, given an ample account of radar echo maps. Since ConvLSTM has successfully introduced spatiotemporal sequence into the traditional LSTM, in this study, we modified a recurrent neural network (RNN) called bidirectional ConvLSTM (Bi-ConvLSTM) based on the ConvLSTM and used a reversed encoding-forecasting structure. The experiments show that the Bi-ConvLSTM achieved a better performance than the ConvLSTM.
Lei Yi; Wei Tian; Xiang Wang; Xiaolong Xu. A Deep Learning Approach to Radar Extrapolation. Transactions on Petri Nets and Other Models of Concurrency XV 2020, 454 -463.
AMA StyleLei Yi, Wei Tian, Xiang Wang, Xiaolong Xu. A Deep Learning Approach to Radar Extrapolation. Transactions on Petri Nets and Other Models of Concurrency XV. 2020; ():454-463.
Chicago/Turabian StyleLei Yi; Wei Tian; Xiang Wang; Xiaolong Xu. 2020. "A Deep Learning Approach to Radar Extrapolation." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 454-463.
Accurate estimation of tropical cyclone (TC) intensity is the key to understanding and forecasting the behavior of TC and is crucial for initialization in forecast models and disaster management in the meteorological industry. TC intensity estimation is a challenge because it requires domain knowledge to manually extract TC cloud structure features and form various sets of parameters obtained from satellites. In this paper, a novel hybrid model is proposed based on convolutional neural networks (CNNs) for TC intensity estimation with satellite remote sensing. According to the intensity of TCs, we divide them into three types and use three submodels for intensity regression, respectively. The results show that the use of regression submodels can improve the accuracy of estimation for TCs of different intensity levels. A classification model is provided to classify unlabeled TC samples before TC regression, whose results would determine which regression model to estimate these samples. Finally, the estimation values are sent to the backpropagation (BP) neural network to fit the suitable intensity values. Experimental results demonstrate that our model achieves high accuracy and low root-mean-square error (RMSE up to 8:91 kts) by just using inferred images.
Wei Tian; Wei Huang; Lei Yi; Liguang Wu; Chao Wang. A CNN-Based Hybrid Model for Tropical Cyclone Intensity Estimation in Meteorological Industry. IEEE Access 2020, 8, 59158 -59168.
AMA StyleWei Tian, Wei Huang, Lei Yi, Liguang Wu, Chao Wang. A CNN-Based Hybrid Model for Tropical Cyclone Intensity Estimation in Meteorological Industry. IEEE Access. 2020; 8 (99):59158-59168.
Chicago/Turabian StyleWei Tian; Wei Huang; Lei Yi; Liguang Wu; Chao Wang. 2020. "A CNN-Based Hybrid Model for Tropical Cyclone Intensity Estimation in Meteorological Industry." IEEE Access 8, no. 99: 59158-59168.
Debris flows have been always a serious problem in the mountain areas. Research on the assessment of debris flows susceptibility (DFS) is useful for preventing and mitigating debris flow risks. The main purpose of this work is to study the DFS in the Shigatse area of Tibet, by using machine learning methods, after assessing the main triggering factors of debris flows. Remote sensing and geographic information system (GIS) are used to obtain datasets of topography, vegetation, human activities and soil factors for local debris flows. The problem of debris flow susceptibility level imbalances in datasets is addressed by the Borderline-SMOTE method. Five machine learning methods, i.e., back propagation neural network (BPNN), one-dimensional convolutional neural network (1D-CNN), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost) have been used to analyze and fit the relationship between debris flow triggering factors and occurrence, and to evaluate the weight of each triggering factor. The ANOVA and Tukey HSD tests have revealed that the XGBoost model exhibited the best mean accuracy (0.924) on ten-fold cross-validation and the performance was significantly better than that of the BPNN (0.871), DT (0.816), and RF (0.901). However, the performance of the XGBoost did not significantly differ from that of the 1D-CNN (0.914). This is also the first comparison experiment between XGBoost and 1D-CNN methods in the DFS study. The DFS maps have been verified by five evaluation methods: Precision, Recall, F1 score, Accuracy and area under the curve (AUC). Experiments show that the XGBoost has the best score, and the factors that have a greater impact on debris flows are aspect, annual average rainfall, profile curvature, and elevation.
Yonghong Zhang; Taotao Ge; Wei Tian; Yuei-An Liou. Debris Flow Susceptibility Mapping Using Machine-Learning Techniques in Shigatse Area, China. Remote Sensing 2019, 11, 2801 .
AMA StyleYonghong Zhang, Taotao Ge, Wei Tian, Yuei-An Liou. Debris Flow Susceptibility Mapping Using Machine-Learning Techniques in Shigatse Area, China. Remote Sensing. 2019; 11 (23):2801.
Chicago/Turabian StyleYonghong Zhang; Taotao Ge; Wei Tian; Yuei-An Liou. 2019. "Debris Flow Susceptibility Mapping Using Machine-Learning Techniques in Shigatse Area, China." Remote Sensing 11, no. 23: 2801.
The Qinghai-Tibetan Plateau (QTP) snow cover information acquisition of the high precision spatial and temporal characteristics is of great significance for the research on its land surface atmosphere coupled system and global climate change effects. The Moderate Resolution Imaging Spectro-radiometer (MODIS) daily snow cover products (MOD10A1 and MYD10A1) have been widely used in long time series of spatial and temporal variation analysis, but they are limited to be used because of high cloud cover ratio. In this paper, a 7-day rolling combination algorithm was presented to eliminate cloud obscuration, and the whole cloud amount falls below 7 %. The ground station in situ measurements verify that the overall precision is more than 90 %. The presented algorithm guaranteed the same spatial resolution and temporal resolution, and has higher precision than products MOD10A1 and MYD10A1. The MODIS 7-day rolling combination snow cover datasets products were obtained between 2003 and 2014 in the QTP, and the snow cover area of spatial and temporal variation was analyzed. The change characteristics of snow cover duration was also studied combining with the Digital Elevation Model data. Results show that the snow cover area of the whole QTP has a slowly decreased trend, but increases in autumn. Thus, the snow cover proportion of annual periodic and unstable in different elevations has the highest correlation with area of the elevation.
Yonghong Zhang; Ting Cao; Xi Kan; Jiangeng Wang; Wei Tian. Spatial and Temporal Variation Analysis of Snow Cover Using MODIS over Qinghai-Tibetan Plateau during 2003–2014. Journal of the Indian Society of Remote Sensing 2016, 45, 887 -897.
AMA StyleYonghong Zhang, Ting Cao, Xi Kan, Jiangeng Wang, Wei Tian. Spatial and Temporal Variation Analysis of Snow Cover Using MODIS over Qinghai-Tibetan Plateau during 2003–2014. Journal of the Indian Society of Remote Sensing. 2016; 45 (5):887-897.
Chicago/Turabian StyleYonghong Zhang; Ting Cao; Xi Kan; Jiangeng Wang; Wei Tian. 2016. "Spatial and Temporal Variation Analysis of Snow Cover Using MODIS over Qinghai-Tibetan Plateau during 2003–2014." Journal of the Indian Society of Remote Sensing 45, no. 5: 887-897.
Yonghong Zhang; Xi Kan; Wei Ren; Ting Cao; Wei Tian; Jiangeng Wang. Snow Cover Monitoring in Qinghai-Tibetan Plateau Based on Chinese Fengyun-3/VIRR Data. Journal of the Indian Society of Remote Sensing 2016, 45, 271 -283.
AMA StyleYonghong Zhang, Xi Kan, Wei Ren, Ting Cao, Wei Tian, Jiangeng Wang. Snow Cover Monitoring in Qinghai-Tibetan Plateau Based on Chinese Fengyun-3/VIRR Data. Journal of the Indian Society of Remote Sensing. 2016; 45 (2):271-283.
Chicago/Turabian StyleYonghong Zhang; Xi Kan; Wei Ren; Ting Cao; Wei Tian; Jiangeng Wang. 2016. "Snow Cover Monitoring in Qinghai-Tibetan Plateau Based on Chinese Fengyun-3/VIRR Data." Journal of the Indian Society of Remote Sensing 45, no. 2: 271-283.
The tensor-driven curvature-preserving partial differential equation is an outstanding anisotropic diffusion filtering model. To effectively preserve image edge well, a weighted curvature-preserving PDE based filtering method is proposed, which employ local image directional information to design weight coefficient for different vector fields. Experimental results indicate that new approach shows superior performance on preserving image edge and curvature geometric structure.
Wei Tian; Tinghuai Ma; Yuhui Zheng; Xin Wang; Yuan Tian; Abdullah Al-Dhelaan; Mznah Al-Rodhaan. Weighted curvature-preserving PDE image filtering method. Computers & Mathematics with Applications 2015, 70, 1336 -1344.
AMA StyleWei Tian, Tinghuai Ma, Yuhui Zheng, Xin Wang, Yuan Tian, Abdullah Al-Dhelaan, Mznah Al-Rodhaan. Weighted curvature-preserving PDE image filtering method. Computers & Mathematics with Applications. 2015; 70 (6):1336-1344.
Chicago/Turabian StyleWei Tian; Tinghuai Ma; Yuhui Zheng; Xin Wang; Yuan Tian; Abdullah Al-Dhelaan; Mznah Al-Rodhaan. 2015. "Weighted curvature-preserving PDE image filtering method." Computers & Mathematics with Applications 70, no. 6: 1336-1344.
Yang Xu; Tinghuai Ma; Meili Tang; Wei Tian. A Survey of Privacy Preserving Data Publishing using Generalization and Suppression. Applied Mathematics & Information Sciences 2014, 8, 1103 -1116.
AMA StyleYang Xu, Tinghuai Ma, Meili Tang, Wei Tian. A Survey of Privacy Preserving Data Publishing using Generalization and Suppression. Applied Mathematics & Information Sciences. 2014; 8 (3):1103-1116.
Chicago/Turabian StyleYang Xu; Tinghuai Ma; Meili Tang; Wei Tian. 2014. "A Survey of Privacy Preserving Data Publishing using Generalization and Suppression." Applied Mathematics & Information Sciences 8, no. 3: 1103-1116.
Tinghuai Ma; Chenghui Wu; Wei Tian; Wenhai Shen. The performance improvements of highly-concurrent grid-based server. Simulation Modelling Practice and Theory 2014, 42, 129 -146.
AMA StyleTinghuai Ma, Chenghui Wu, Wei Tian, Wenhai Shen. The performance improvements of highly-concurrent grid-based server. Simulation Modelling Practice and Theory. 2014; 42 ():129-146.
Chicago/Turabian StyleTinghuai Ma; Chenghui Wu; Wei Tian; Wenhai Shen. 2014. "The performance improvements of highly-concurrent grid-based server." Simulation Modelling Practice and Theory 42, no. : 129-146.
Today, the management of massive data collections draws much attention as data grids have been developed to deal with large computational problems and provide the opportunity for sharing geographically distributed resources for large‒scale data‒intensive applications. Therefore, finding an effective approach to discover data resources in order to promote better interactions between application communities or virtual organizations becomes a critical challenge. Traditional grid resource discovery models are mostly based on central and hierarchical architecture that can lead to bottlenecking with the expansion of the grid scale. Although the Peer‒to‒Peer (P2P) technique is integrated into the grid in order to improve the performance in recent years, each P2P structure still has drawbacks that require several compensatory strategies. In this paper, based on the unstructured super‒node‒based architecture from the P2P system, we design a structured logic resource tree in each domain in order to effectively alleviate the load on the super‒node, and we propose a query recording learning algorithm based on this hybrid architecture to reduce traffic in the network and greatly shorten the response time. The model and algorithm are validated by simulations and compared with the traditional super‒peer model and the flooding‒based approach. Copyright © 2014 John Wiley & Sons, Ltd.
Tinghuai Ma; Yinhua Lu; Sunyuan Shi; Wei Tian; Xin Wang; Donghai Guan. Data resource discovery model based on hybrid architecture in data grid environment. Concurrency and Computation: Practice and Experience 2014, 27, 507 -525.
AMA StyleTinghuai Ma, Yinhua Lu, Sunyuan Shi, Wei Tian, Xin Wang, Donghai Guan. Data resource discovery model based on hybrid architecture in data grid environment. Concurrency and Computation: Practice and Experience. 2014; 27 (3):507-525.
Chicago/Turabian StyleTinghuai Ma; Yinhua Lu; Sunyuan Shi; Wei Tian; Xin Wang; Donghai Guan. 2014. "Data resource discovery model based on hybrid architecture in data grid environment." Concurrency and Computation: Practice and Experience 27, no. 3: 507-525.
As a research branch of grid computing, data grid focuses on the management of large-scale distributed data sets. Replica management is one of the most important issues in the data grid, which can offer fast data access time, high data availability and low bandwidth consumption. Computing Intelligent Algorithm (CIA) has been proved to be effective in the solution of large-scale distributed computing problems, whereas Quantum Evolutionary Algorithm (QEA) is one of these excellent optimization algorithms and little literatures are made for its application in Data Grid Replica Management (DGRM). This paper focuses on the application of the QEA in data grid replica creation strategy. A QEA-based global replica creation strategy is proposed after reviewing the replica creation strategies. The optimization model is divided into single and multi data replica creation two parts. The representation, evaluation and constraint procedure three key technologies problems for each part are discussed in detail. The detail algorithm of QEA based replica creation is provided. The experiments were carried out with OptorSim, and the results have shown that QEA-based replica creation strategy can effectively reduce the job response time and network bandwidth consumption, comparing to Genetic Algorithms (GAs), Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO) algorithms. Especially, its performance becomes better and better with the incensement of the number of jobs. The non-parametric statistical tests are used to verify the significant of QEA.
Tinghuai Ma; Qiaoqiao Yan; Wei Tian; Donghai Guan; Sungyoung Lee. Replica creation strategy based on quantum evolutionary algorithm in data gird. Knowledge-Based Systems 2013, 42, 85 -96.
AMA StyleTinghuai Ma, Qiaoqiao Yan, Wei Tian, Donghai Guan, Sungyoung Lee. Replica creation strategy based on quantum evolutionary algorithm in data gird. Knowledge-Based Systems. 2013; 42 ():85-96.
Chicago/Turabian StyleTinghuai Ma; Qiaoqiao Yan; Wei Tian; Donghai Guan; Sungyoung Lee. 2013. "Replica creation strategy based on quantum evolutionary algorithm in data gird." Knowledge-Based Systems 42, no. : 85-96.
Sunyuan Shi; Wei Tian; Tinghuai Ma; Hao Cao; Jin Wang. Review on Grid Resource Discovery: Models and Strategies. IETE Technical Review 2012, 29, 213 .
AMA StyleSunyuan Shi, Wei Tian, Tinghuai Ma, Hao Cao, Jin Wang. Review on Grid Resource Discovery: Models and Strategies. IETE Technical Review. 2012; 29 (3):213.
Chicago/Turabian StyleSunyuan Shi; Wei Tian; Tinghuai Ma; Hao Cao; Jin Wang. 2012. "Review on Grid Resource Discovery: Models and Strategies." IETE Technical Review 29, no. 3: 213.
Semi-supervised leaning deals with methods for automatically exploiting unlabeled samples in addition to labeled set. The data selection is an important topic in active learning. It addresses the selection the valuable unlabeled data to label, considering that labeling data is a costly job. In this paper, we want to discuss in detail three aspects of technology in data selection, which includes how to select the unlabeled sample, how many unlabeled samples should be selected and how to define the capacity of the training pool. Experiments which use self-training based on C4.5 show that while the L labeled ratio lager continuous, the initial error value becomes smaller. Also when L labeled ratio is less than 10%, the selection ratio value should be set in less than 0.8.The error value has no significant change while selection ratio value larger than 1.0.
Jian Ge; Tinghuai Ma; Qiaoqiao Yan; Yonggang Yan; Wei Tian. Training Pool Selection for Semi-supervised Learning. Computer Vision 2012, 7367, 524 -532.
AMA StyleJian Ge, Tinghuai Ma, Qiaoqiao Yan, Yonggang Yan, Wei Tian. Training Pool Selection for Semi-supervised Learning. Computer Vision. 2012; 7367 ():524-532.
Chicago/Turabian StyleJian Ge; Tinghuai Ma; Qiaoqiao Yan; Yonggang Yan; Wei Tian. 2012. "Training Pool Selection for Semi-supervised Learning." Computer Vision 7367, no. : 524-532.
Severe weather causes human disasters. The most useful way to decrease a national disaster is by building more atmospheric sensing equipments to monitor the climate change. The data produced by these sensing equipments are of a huge amount and play an important role for weather prediction. Moreover, new sensing equipments enrich weather data. Everyday terabyte and petabyte-scale data are collected. Retrieval of such information requires access to large volumes of data; thus an efficient organisation is necessary both to reduce access time and to allow for efficient knowledge extraction. A new class of ‘data grid’ infrastructure is efficient to support management, transportation, distributed access and analysis of these data sets by thousands of potential users. Intelligent agents can play an important role in helping achieve the ‘data grid’ vision. In this study, the authors present a multi-agent-based framework to implement manage, share and query weather data in a geographical distributed environment, named weather data sharing system (WDSS). In each node, some services are designed for querying and accessing data sets based on agent environment. Information retrieval can be conducted locally, by considering portions of weather data, or in a distributed scenario, by exploiting global metadata. The agents' local and remote search is evaluated. The transfer speeds for different file types are also evaluated. From the presented platform, the system extensibility is analysed. The authors believe that this will be a useful platform for research on WDSS in a national area.
T.H. Ma; W. Tian; B. Wang; D.H. Guan; S.Y. Lee. Weather data sharing system: an agent-based distributed data management. IET Software 2011, 5, 21 -31.
AMA StyleT.H. Ma, W. Tian, B. Wang, D.H. Guan, S.Y. Lee. Weather data sharing system: an agent-based distributed data management. IET Software. 2011; 5 (1):21-31.
Chicago/Turabian StyleT.H. Ma; W. Tian; B. Wang; D.H. Guan; S.Y. Lee. 2011. "Weather data sharing system: an agent-based distributed data management." IET Software 5, no. 1: 21-31.
Tinghuai Ma; Jian Ge -; Wei Tian -; Yali Wang -; Erasmus Sowah -. Virtual Resource Management Based Meteorological Computational Grid. Journal of Convergence Information Technology 2010, 5, 131 -140.
AMA StyleTinghuai Ma, Jian Ge -, Wei Tian -, Yali Wang -, Erasmus Sowah -. Virtual Resource Management Based Meteorological Computational Grid. Journal of Convergence Information Technology. 2010; 5 (10):131-140.
Chicago/Turabian StyleTinghuai Ma; Jian Ge -; Wei Tian -; Yali Wang -; Erasmus Sowah -. 2010. "Virtual Resource Management Based Meteorological Computational Grid." Journal of Convergence Information Technology 5, no. 10: 131-140.
The current status of Chinese question answering system (QA) was introduced in the paper firstly. QA is the study on the methodology that returns exact answers to natural language questions. This paper attempts to increase the speed of the system responding to the users and accuracy of QA systems. To achieve this objective, the processing includes: Firstly, it introduces the conceptual theory and parts of intelligent question-answering system in detail. Secondly, it researches the Chinese word segmentation algorithm and its relevant technology. Thirdly, it puts forward the method of calculating sum of word frequency based on the whole sentence. It makes a better improvement for processing the problems. Fourthly, it brings forward the classification problem of specific fields, which is convenient for result matching according to the kind of problem of the system. In the end, this system completes the results extraction by calculating the weight. On the basis of theory and algorithm mentioned above, a question-answering system in the course ASP.Net field is implemented.
Wei Tian; Wenjie Liu; Tinghuai Ma. Study and Implementation of Chinese Intelligent Question Answering System Based on Restricted Domain. 2009 Third International Conference on Genetic and Evolutionary Computing 2009, 217 -220.
AMA StyleWei Tian, Wenjie Liu, Tinghuai Ma. Study and Implementation of Chinese Intelligent Question Answering System Based on Restricted Domain. 2009 Third International Conference on Genetic and Evolutionary Computing. 2009; ():217-220.
Chicago/Turabian StyleWei Tian; Wenjie Liu; Tinghuai Ma. 2009. "Study and Implementation of Chinese Intelligent Question Answering System Based on Restricted Domain." 2009 Third International Conference on Genetic and Evolutionary Computing , no. : 217-220.
Tinghuai Ma; Sen Yang; Wei Tian; Wenjie Liu. Privacy Preserving in Ubiquitous Computing: Architecture. Information Technology Journal 2009, 8, 910 -916.
AMA StyleTinghuai Ma, Sen Yang, Wei Tian, Wenjie Liu. Privacy Preserving in Ubiquitous Computing: Architecture. Information Technology Journal. 2009; 8 (6):910-916.
Chicago/Turabian StyleTinghuai Ma; Sen Yang; Wei Tian; Wenjie Liu. 2009. "Privacy Preserving in Ubiquitous Computing: Architecture." Information Technology Journal 8, no. 6: 910-916.