检索结果-内蒙古大学图书馆

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Yu, Wentao Li, Jing Liu, Qinhuo Beijing Normal Univ Chinese Acad Sci Aerosp Informat Res Inst State Key Lab Remote Sensing Sci Beijing 100101 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

ISBN: (纸本)9781728163741

Normalized difference vegetation index (NDVI) is a key parameter in land use/cover change and terrestrial modelling studies. With the accumulation of satellite records in the past few decades, the spatial-temporal prediction of vegetation index becomes feasible. In this paper, we established a convolutional GRU network (ConvGRU) to predict the short-term vegetation index considering the spatial and temporal patterns in the NDVI records. The predictive performance of the proposed method is evaluated for several vegetation types in different regions globally. The results demonstrate that the proposed model has sufficient ability in predicting satellite recorded NDVI. The validation on the MODIS NDVI datasets achieved an average RMSE around 0.06. And, the model performs better in regions of Australia while worse in North Europe.

关键词： vegetation index spatial-temporal prediction convolution networks GRU

来源：评论

学校读者我要写书评

暂无评论

Federated meta-learning for spatial-temporal prediction

引用

NEURAL COMPUTING & APPLICATIONS 2022年第13期34卷 10355-10374页

作者： Li, Wenzhu Wang, Shuang Northeastern Univ Shenyang Peoples R China

spatial-temporal prediction is a fundamental problem for constructing smart city, and existing approaches by deep learning models have achieved excellent success based on a large volume of datasets. However, data privacy of cities becomes the public concerns in recent years. Therefore, how to develop accurate spatial-temporal prediction while preserving privacy is a significant problem. To address this challenge, we propose a privacy-preserving spatial-temporal prediction technique via federated learning (FL). Due to inherent non-independent identically distributed (non-IID) characteristic of spatial-temporal data, the basic FL-based method cannot deal with this data heterogeneity well by sharing global model;furthermore, we propose the personalized federated learning methods based on meta-learning. We automatically construct the global spatial-temporal pattern graph under a data federation. This global pattern graph incorporates and memorizes the local learned patterns of all of the clients, and each client leverages those global patterns to customize its own model by evaluating the difference between global and local pattern graph. Then, each client could use this customized parameters as its model initialization parameters for spatial-temporal prediction tasks. We conduct extensive experiments on bike sharing datasets to demonstrate the superiority and effectiveness of our methods in privacy protection settings.

关键词： spatial-temporal prediction Meta-learning Federated learning

来源：评论

学校读者我要写书评

暂无评论

spatial-temporal prediction of Vegetation Index With Deep Recurrent Neural Networks

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷 1页

作者： Yu, Wentao Li, Jing Liu, Qinhuo Zhao, Jing Dong, Yadong Wang, Cong Lin, Shangrong Zhu, Xinran Zhang, Hu Beijing Normal Univ Chinese Acad Sci Jointly Sponsored Aerosp Informat Res Inst State Key Lab Remote Sensing Sci Beijing 100101 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Vegetation index (VI) derived from remotely sensed images is a proxy of terrestrial vegetation information and widely used in land monitoring and global change studies. Recently, the prediction of vegetation properties has been an interest in related communities. With the accumulation of satellite records over the past few decades, the spatial-temporal prediction of VI becomes feasible. In this letter, we developed deep recurrent neural networks (RNNs) with long short-term memory (LSTM) and gated recurrent units (GRUs) to predict the short-term VI based on historical observations. The pixel-based fully connected networks GRU and LSTM (FCGRU and FCLSTM) and patch-based convolutional networks (ConvGRU and ConvLSTM) are established and compared with the traditional multilayer perceptron (MLP) model. Moderate Resolution Imaging Spectroradiometer (MODIS) and Sentinel-2 normalized difference VI (NDVI) data sets were used in the experiments. The prediction performance is evaluated globally in different regions, different vegetation types, and different growing seasons. Results demonstrate that the RNN models can predict VI with high accuracy (average root mean square error (RMSE) around 0.03), which is superior to the MLP model. In general, the pixel-based RNN models performed better than the patch-based models especially in regions with a larger proportion of outliers. And the prediction accuracy is stable over different vegetation types and growing seasons.

关键词： Time series analysis Remote sensing Predictive models Vegetation mapping Logic gates Recurrent neural networks MODIS Gated recurrent unit (GRU) recurrent neural networks (RNNs) spatial-temporal prediction vegetation index (VI)

来源：评论

学校读者我要写书评

暂无评论

Learning from Multiple Cities: A Meta-Learning Approach for spatial-temporal prediction 19

Learning from Multiple Cities: A Meta-Learning Approach for ...

引用

World Wide Web Conference (WWW)

作者： Yao, Huaxiu Liu, Yiding Wei, Ying Tang, Xianfeng Li, Zhenhui Penn State Univ University Pk PA 16802 USA Nanyang Technol Univ Singapore Singapore Tencent AI Lab Shenzhen Peoples R China

ISBN: (纸本)9781450366748

spatial-temporal prediction is a fundamental problem for constructing smart city, which is useful for tasks such as traffic control, taxi dispatching, and environment policy making. Due to data collection mechanism, it is common to see data collection with unbalanced spatial distributions. For example, some cities may release taxi data for multiple years while others only release a few days of data;some regions may have constant water quality data monitored by sensors whereas some regions only have a small collection of water samples. In this paper, we tackle the problem of spatial-temporal prediction for the cities with only a short period of data collection. We aim to utilize the long-period data from other cities via transfer learning. Different from previous studies that transfer knowledge from one single source city to a target city, we are the first to leverage information from multiple cities to increase the stability of transfer. Specifically, our proposed model is designed as a spatial-temporal network with a meta-learning paradigm. The meta-learning paradigm learns a well-generalized initialization of the spatial-temporal network, which can be effectively adapted to target cities. In addition, a pattern-based spatial-temporal memory is designed to distill long-term temporal information (i.e., periodicity). We conduct extensive experiments on two tasks: traffic (taxi and bike) prediction and water quality prediction. The experiments demonstrate the effectiveness of our proposed model over several competitive baseline models.

关键词： spatial-temporal prediction periodicity meta-learning

来源：评论

学校读者我要写书评

暂无评论

U-shape spatial-temporal prediction Network based on 3D Convolution and BDLSTM 4

U-shape Spatial-Temporal Prediction Network based on 3D Conv...

引用

4th IEEE International Conference on Software Engineering and Artificial Intelligence (SEAI)

作者： Peng, Ge Shi, Chunchao Zhong, Yujing Ai, Xinyu Baoshan Univ Sch Big Data Baoshan Yunnan Peoples R China

ISBN: (纸本)9798350374353;9798350374346

spatial-temporal prediction is widely used in data prediction tasks such as video, weather, traffic flow prediction. How to utilize the time domain and spatial domain information effectively or predicting accurate data is the difficulty of spatial-temporal data prediction algorithms. A spatial-temporal data prediction algorithm based on 3D U-shaped network and bi-directional LSTM is proposed in this paper, in which 3D convolution network is used to extract the temporal and spatial feature information on the image sequences, bi-directional long-short term memory (BDLSTM) module to finish the regression prediction in the temporal domain, and then up-sampling module to finish the reconstruction of spatial-temporal data. A group of experiments on Moving MNIST dataset is utilized to demonstrate the effectiveness of the proposed algorithm. The validation scores on MSE, MAE, SSIM, PSNR, and training time cost are 47.86, 119.72, 0.892, 37.42, 12s/epoch. It can be seen that he proposed algorithm exhibits excellent performance on spatial-temporal prediction tasks.

关键词： spatial-temporal prediction video prediction 3D convolution U-shape network

来源：评论

学校读者我要写书评

暂无评论

Improved LSTM spatial-temporal prediction Method for Power Grid IoT Analysis

Improved LSTM Spatial-temporal Prediction Method for Power G...

引用

IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)

作者： Li, Ming Han, Xingwang Huang, Hua Ni, Jinchao Cui, Bo Cheng, Hui Liu, Mingfeng Wang, Xie State Grid Shandong Elect Power Co Jinan Shandong Peoples R China State Grid Qingdao Power Supply Co Qingdao Shandong Peoples R China Nanjing Univ Finance & Econ Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781450391870

Along with the development of IoT (Internet of Things), many sensors have been equipped in power grid system to monitor the status of the electricity infrastructure. It is necessary to predict the possible changes from recorded IoT data. In this paper, we propose an improved LSTM algorithm to analyze the spatial-temporal data from power grid IoT devices. Prophet-XGBoost algorithm is combined with LSTM algorithm to improve the prediction accuracy of the IoT datasets. The proposed method is implemented and compared with SVR, XGBoost, and general LSTM methods in different IoT datasets. The experimental results indicate that the proposed method can improve the prediction results and achieve better performance than these existing methods.

关键词： Improved LSTM Power Gird IoT spatial-temporal prediction

来源：评论

学校读者我要写书评

暂无评论

A robust spatial-temporal prediction model for photovoltaic power generation based on deep learning

引用

COMPUTERS & ELECTRICAL ENGINEERING 2023年第1期110卷

作者： Wang, Zun Wang, Yashun Cao, Shenglei Fan, Siyuan Zhang, Yanhui Liu, Yuning CLP Huachuang Power Technol Res Co Ltd Suzhou 215123 Peoples R China Northeast Elect Power Univ Sch Automat Engn Jilin 132012 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518055 Peoples R China Adv Micro Devices Inc Shanghai 200131 Peoples R China

The accurate spatial-temporal prediction of photovoltaic (PV) power generation helps the power system dispatching department to make reasonable dispatching plans. In this paper, a robust spatial-temporal prediction model for PV power generation based on a denoising autoencoder (DAE) combining Gramian angular summation fields (GASF) and convolutional neural network (CNN) is proposed. First, the downscaling and modeling of power data use Pearson correlation to reduce inaccurate and inefficient predictions due to large-scale sparse data. Second, the model training data are encoded with noise reduction using a denoising autoencoder. Finally, the performance of the proposed model is experimentally verified. The results show that the model still performs well when the data exist in different degrees of contamination, with an average mean square error (MSE) of 71.58. Experiments based on China and the USA PV power generation datasets with mean absolute error (MAE) of 4.26 and 3.96, respectively.

关键词： Photovoltaic power spatial-temporal prediction Deep learning Data pollution Robustness

来源：评论

学校读者我要写书评

暂无评论

An adaptive spatial-temporal prediction model for landslide displacement based on decomposition architecture

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartB期137卷

作者： Xu, Man Zhang, Dongmei Li, Jiang Wu, Yiping China Univ Geosci Sch Comp Sci Wuhan 430074 Hubei Peoples R China Minist Educ Engn Res Ctr Nat Resource Informat Management & Di Wuhan 430074 Hubei Peoples R China Informat Ctr Dept Nat Resources Hubei Prov Wuhan 430074 Hubei Peoples R China China Univ Geosci Sch Engn Wuhan 430074 Hubei Peoples R China

Landslide displacement forecasting is a core issue in geohazard research, it is particularly challenging for accumulation-type landslides with complex geological patterns. Traditional landslide displacement prediction methods use single-point modeling and often fail to consider the spatial correlation characteristics of each deformation point on the surface of a landslide. On the other hand, they have difficulty in learning the changes caused by rainfall and reservoir water level. To tackle these obstacles, we introduce an adaptive spatial-temporal landslide displacement prediction model based on a decomposition architecture, named Self- Adaptive Unet with Decomposed temporal Attention Encoder(SAU-DTAE). To effectively separate the features of different scales in time series changes and model them separately, we employ a progressive decomposition architecture based on a Lightweight temporal Attention Encoder(LTAE). Furthermore, we design a gating mechanism with Sample Entropy (SampEn) to adaptively extract global and local spatial features at multiple scales. By quantifying the spatial complexity, we can achieve adaptive extraction of spatial correlation features. Relevant experiments were conducted with the 2016-2023 Interferometry Synthetic Aperture Radar (InSAR) landslide displacement dataset of the Three Gorges area. The new proposed algorithm was compared and validated against several classical time-series prediction models: Back Propagation(BP) neural network, Long Short Term Memory(LSTM) neural network, Gated Recurrent Unit(GRU), Convolutional LSTM(ConvLSTM), Informer, and Autoformer. The findings from the experiment indicated that our model surpassed the benchmark models, achieving superior prediction results on the test set. The Mean Absolute Error (MAE) was 5.516 millimeters(mm), the Root Mean Square Error (RMSE) was 3.856 mm, and the R-Square(R-2) was 0.896.

关键词： Landslide displacement spatial-temporal prediction Decomposition architecture Multi-scale Gating mechanism

来源：评论

学校读者我要写书评

暂无评论

Adaptive Dual-View WaveNet for urban spatial-temporal event prediction

引用

INFORMATION SCIENCES 2022年 588卷 315-330页

作者： Jin, Guangyin Liu, Chenxi Xi, Zhexu Sha, Hengyu Liu, Yanyun Huang, Jincai Natl Univ Def Technol Coll Syst Engn Changsha Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha Peoples R China Univ Bristol Bristol Ctr Funct Nanomat Bristol Avon England Harbin Inst Technol Coll Econ & Management Harbin Peoples R China

spatial-temporal event prediction is a particular task for multivariate time series forecasting. Therefore, the complex entangled dynamics of space and time need to be considered. This task is an essential but crucial loop in future smart cities construction, which can be widely applied in urban traffic management, disaster monitoring and mobility analysis. In recent years, video-like spatial-temporal modelling has been the most common approach in many deep learning models. However, the video-like modelling approach cannot consider some latent region-wise correlations other than geographic spatial distance information. To overcome the limitation, we propose a novel neural network framework, Adaptive Dual-View WaveNet (ADVW-Net), for the urban spatial-temporal event prediction. By integrating the spatial representations from Convolutional Neural Network (CNN) and that from adaptive Graph convolutional neural network (GCN), our proposed model can capture not only the geographic correlations but also some latent region-wise dependencies from the input data. In addition, the effective architecture, WaveNet, can be transferred to region-wise spatial-temporal prediction scenarios for long-range temporal dependencies learning. Experimental results on three urban datasets demonstrate the superior performance of our proposed model.(c) 2021 Elsevier Inc. All rights reserved.

关键词： spatial-temporal prediction Representation learning WaveNet Graph convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

spatial and temporal prediction of radiation dose rates near Fukushima Daiichi Nuclear Power Plant

引用

JOURNAL OF ENVIRONMENTAL RADIOACTIVITY 2022年 251卷 106946页

作者： Sun, Dajie Wainwright, Haruko Suresh, Ishita Seki, Akiyuki Takemiya, Hiroshi Saito, Kimiaki Univ Calif Berkeley Berkeley CA 94720 USA Lawrence Berkeley Natl Lab Berkeley CA USA MIT 77 Massachusetts Ave Cambridge MA 02139 USA Alameda High Sch Lawrence Berkeley Natl Lab Berkeley CA USA Japan Atom Energy Agcy Tokyo Japan

In this paper, we have developed a methodology to estimate the spatiotemporal distribution of radiation air dose rates around the Fukushima Daiichi Nuclear Power Plant (FDNPP). In our exploratory data analysis, we found that (1) the temporal evolution of dose rates is composed of a log-linear decay trend and fluctuations of air dose rates that are spatially correlated among adjacent monitoring posts;and (2) the slope of the log-linear environmental decay trend can be represented as a function of the apparent initial dose rates, coordinate position, land-use type, and soil type. From these observations, we first estimated the log-linear decay trend at each location based on these predictors, using the random forest method. We then developed a modified Kalman filter coupled with a Gaussian process model to estimate the dose-rate time series at a given location and time. We applied this method to the Fukushima evacuation zone (as of March 2017), which included 17 monitoring post locations (with monitoring datasets collected between 2014 and 2018) and generated a time series of dose-rate maps. Our results show that this approach allows us to produce accurate spatial and temporal predictions of radiation dose-rate maps using limited spatiotemporal measurements.

关键词： Dose-rate time-series spatial-temporal prediction Fukushima daiichi nuclear power plant Modified Kalman filter Gaussian process model

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：