融合空间尺度特征的时空序列预测建模方法

邓敏; 陈倜; 杨文涛

doi:10.13203/j.whugis20130842

融合空间尺度特征的时空序列预测建模方法

中南大学地球科学与信息物理学院, 湖南长沙, 410083

基金项目: 国家863计划资助项目(2013AA122301);湖南省自然科学杰出青年基金资助项目(14JJ1007);湖南省研究生创新基金资助项目(CX2014B051)。

详细信息

作者简介:
邓敏,博士,教授,从事时空数据挖掘、推理与分析研究。E-mail:dengmin208@tom.com

中图分类号: P208
计量
- 文章访问数: 02122
- HTML全文浏览量: 067
- PDF下载量: 0739
出版历程
- 收稿日期: 2015-05-03
- 发布日期: 2015-12-04

A New Method of Modeling Spatio-temporal Sequence by Considering Spatial Scale Characteristics

School of Geosciences and Info-Physics, Central South University, Changsha 410083, China

Funds: The National High Technology Research and Development Program of China (863 Program), No. 2013AA122301; Hunan Province Science Fund for Distinguished Young Scholars, No.14JJ1007; Hunan Provincial Innovation Foundation for Postgraduate, No. CX2014B051.

摘要

摘要: 假定原始的时空数据由较大尺度下的全局趋势项与较小尺度下的局部偏差项构成,提出了融合空间尺度特性的时空序列建模方法。首先,将原始数据转换为较大尺度下的数据,此部分反映原始数据的趋势特征。然后,将趋势部分剔除,剩余部分反映原始数据的偏差特征。最后,用灰色系统模型和BP神经网络模型分别对趋势项和偏差项建模,它们的组合预测结果即为原始时空序列预测值。采用该方法对实际的年降水数据以及日平均PM2.5浓度数据进行预测建模分析,实验结果表明:融合空间尺度特性的时空序列预测模型可以用于多空间尺度预测,并且预测精度优于不考虑空间尺度特性的建模方法。
- 空间尺度 /
- 时间序列 /
- 预测模型 /
- 时空序列
Abstract: The paper presents a new method of modeling spatio-temporal sequence data by considering spatial scale characteristics, where original data is regarded as the combination of a general trend term representing at a larger scale and a local bias term representing at a smaller scale. The original data is first converted into a larger-scale data that represents the general trend of original data. Then, this general trend term is removed and the left part is the bias term of original data. Finally, prediction models of the trend term and the bias term are respectively built, and the combination of the two models is used to predict the original spatio-temporal sequence. Application in annual precipitation and daily average of PM2.5 concentration shows that this proposed method can be used to obtain multi-scale spatial predictions, and is better in accuracy than those models without consideration of spatial scale characteristics.
- spatial scale /
- spatio-temporal sequence /
- prediction model /
- time sequence

HTML全文

参考文献(16)

[1]	Martin R L,Oeppen J E. The Identification of Regional Forecasting Models Using Space: Time Correlation Functions[J]. Transactions of the Institute of British Geographers, 1975, 66: 95-118
[2]	Cliff A D,Ord J K. Space-time Modeling with an Application to Regional Forecasting[J]. Transactions of the Institute of British Geographers, 1975, 64: 119-128
[3]	Kamarianakis Y, Prastacos P. Space-time Modeling of Traffic Flow [J]. Computers & Geosciences, 2005, 31(2): 119-133
[4]	Cheng T, Wang J Q, Li X. Space-time Series Modeling by Artificial Neural Network[C]. International Conference on Earth Observation Data Processing and Analysis (ICEODPA), Wuhan,China, 2008
[5]	Wang J, Cheng T, Haworth J. Space-time Kernels[J]. International Archives of the Photogrammetry, 2010, 38: 57-62
[6]	Wang Jiaqiu, Deng Min, Cheng Tao, et al. Spatio-temporal Series Data Analysis and Modeling[M]. Beijing: Science Press, 2012(王佳璆, 邓敏, 程涛, 等. 时空序列数据分析和建模[M]. 北京: 科学出版社, 2012)
[7]	Pei Tao, Zhou Chenghu, Luo Jiancheng, et al. Review on the Proceeding of Spatial Data Mining Research[J]. Journal of Image and Graphics, 2001, 6(9): 854-870(裴韬, 周成虎, 骆剑承, 等. 空间数据知识发现研究进展评述[J]. 中国图像图形学报, 2001, 6(9): 854-870)
[8]	Li Lin, Ying Shen. Fundamental Problem on Spatial Scale[J]. Geomatics and Information Science of Wuhan University, 2005, 30(3): 199-203(李霖, 应申. 空间尺度基础性问题研究[J]. 武汉大学学报·5信息科学版, 2005, 30(3): 199-203)
[9]	Turner M G, O'Neill R V, Gardner R H, et al. Effects of Changing Spatial Scale on the Analysis of Landscape Pattern[J]. Landscape Ecology, 1989, 3(3-4): 153-162
[10]	Liu Kai, Wu Hehai, Ai Tinghua, et al. Three-tiered Concept of Scale of Geographical Information and Its Transformation[J]. Geomatics and Information Science of Wuhan University, 2008, 33(11): 1 178-1 181(刘凯, 毋河海, 艾廷华, 等. 地理信息尺度的三重概念及其变换[J]. 武汉大学学报·5信息科学版, 2008, 33(11): 1 178-1 181)
[11]	Hu Yunfeng, Xu Zhiying, Liu Yue, et al. A Review of the Scaling Issues of Geospatial Data[J]. Advances in Earth Science, 2013, 28(3): 297-304(胡云锋, 徐芝英, 刘越, 等. 地理空间数据的尺度转换[J]. 地球科学进展, 2013, 28(3): 297-304)
[12]	Meng Bin, Wang Jinfeng. A Review on the Methodology of Scaling with Geo-data[J]. Acta Geographica Sinica, 2005, 60(2): 277-288(孟斌, 王劲峰. 地理数据尺度转换方法研究进展[J]. 地理学报, 2005, 60(2): 277-288)
[13]	Luo Jiancheng, Zhou Chenghu, Liang Yi, et al. Scale-space Theory Based Regionalization for Spatial Cells[J]. Acta Geographica Sinica, 2002, 57(2): 167-173(骆剑承, 周成虎, 梁怡, 等. 多尺度空间单元区域划分方法[J]. 地理学报, 2002, 57(2): 167-173)
[14]	Wang Haiqi, Wang Jinfeng. A K-means Adapted Algorithm Based Spatial Contiguity Relations[J]. Computer Engineering, 2006, 32(31): 50-51(王海起, 王劲峰. 一种基于空间邻接关系的k-means聚类改进算法[J]. 计算机工程, 2006, 32(21): 50-51)
[15]	Wei Erhu, Li Zhiqiang, Gong Guangyu. et al. Fitting Prediction of Pole Motion Time Series Model[J]. Geomatics and Information Science of Wuhan University, 2013, 38(12): 1 420-1 424(魏二虎, 李智强, 龚光裕, 等. 极移时间序列模型的拟合与预测[J]. 武汉大学学报·5信息科学版, 2013, 38(12): 1 420-1 424)
[16]	Peng Ling, Niu Ruiqing, Zhao Yannan. et al. Prediction of Landslide Displacement Based on KPCA and PSO-SRR[J]. Geomatics and Information Science of Wuhan University, 2013, 38(2): 148-152(彭令, 牛瑞卿, 赵艳南, 等. 基于核主成分分析和粒子群优化支持向量机的滑坡位移预测[J]. 武汉大学学报·5信息科学版, 2013, 38(2): 148-152)

施引文献

资源附件(0)

计量

文章访问数:
HTML全文浏览量:
PDF下载量:
被引次数: 0

融合空间尺度特征的时空序列预测建模方法

作者简介: 邓敏,博士,教授,从事时空数据挖掘、推理与分析研究。E-mail:dengmin208@tom.com

计量

出版历程

A New Method of Modeling Spatio-temporal Sequence by Considering Spatial Scale Characteristics

计量

出版历程

目录

作者简介:
邓敏,博士,教授,从事时空数据挖掘、推理与分析研究。E-mail:dengmin208@tom.com