基于网络和图的时空智能——概念、方法和应用

doi:10.11947/j.AGCS.2022.20220236

摘要/Abstract

摘要： 当前时空智能(SpaceTimeAI)和地理空间智能(GeoAI)已是热门的话题,该研究领域旨在将计算机科学的最新方法(如深度学习)应用于地理空间问题。虽然深度学习方法因其对栅格数据的自然适用性而在图像处理中取得了巨大成功,但仍未广泛应用于其他空间和时空数据类型。本文提出使用网络和图作为SpaceTimeAI或GeoAI的基本结构的倡议,并将其应用于城市研究中。相比于基于网格的表达,基于网络的结构更加精确和实用。图能实现对点、线、面/多边形/网格和网络等多种空间结构的表达。本文通过时空预测、聚类和时空优化等常用时空分析方法展示基于网络和图的时空智能分析的优势,并介绍其在交通出行、警务和公共卫生等领域的应用。

关键词: 时空智能, 地理空间智能, 网络, 图, 深度学习, 时空预测

Abstract: SpaceTimeAI and GeoAI are currently a hot topic, which apply the latest algorithms in computer science, such as deep learning. Although deep learning algorithms have been successfully applied in raster data processing due to their natural applicability to image processing, their applications in other spatial and space-time data types are still immature. This paper sets up the proposition of using the network (& graph)-based framework as a generic spatial structure to present space-time processes that are usually represented by the point, polyline, and polygon. We illustrate network and graph-based SpaceTimeAI, from graph-based deep learning for prediction, to clustering and optimisation. These demonstrate the advantages of the network (graph)-based SpaceTimeAI in the applications of transport & mobility, crime & policing, and public health.

Key words: SpaceTimeAI, GeoAI, network, graph, deep learning, space-time prediction

中图分类号:

P208

程涛, 张洋, James Haworth. 基于网络和图的时空智能——概念、方法和应用[J]. 测绘学报, 2022, 51(7): 1629-1639.

CHENG Tao, ZHANG Yang, James Haworth. Network and graph-based SpaceTimeAI: conception, method and applications[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(7): 1629-1639.

参考文献

[1] IBRAHIM M R, HAWORTH J, CHENG Tao. Understanding cities with machine eyes:a review of deep computer vision in urban analytics[J]. Cities, 2020, 96:102481.
[2] ZHANG Fan, WU Lun, ZHU Di, et al. Social sensing from street-level imagery:a case study in learning spatio-temporal urban mobility patterns[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 153:48-58.
[3] ZHANG Junbo, ZHENG Yu, QI Dekang, et al. Predicting citywide crowd flows using deep spatio-temporal residual networks[J]. Artificial Intelligence, 2018, 259:147-166.
[4] OPENSHAW S, TAYLOR P. The modifiable areal unit problem[M]//WRIGLEY N, BENNETT R J. Quantitative Geography:A British View. London:Routledge, 1981:60-69.
[5] ROSSER G, DAVIES T, BOWERS K J, et al. Predictive crime mapping:arbitrary grids or street networks?[J]. Journal of Quantitative Criminology, 2017, 33(3):569-594.
[6] CHENG Tao, HAWORTH J, WANG Jiaqiu. Spatio-temporal autocorrelation of road network data[J]. Journal of Geographical Systems, 2012, 14(4):389-413.
[7] CHENG Xingyi, ZHANG Ruiqing, ZHOU Jie, et al. Deeptransport:learning spatial-temporal dependency for traffic condition forecasting[C]//Proceedings of 2018 International Joint Conference on Neural Networks. Rio de Janeiro:IEEE, 2018.
[8] SHIODE S. Street-level spatial scan statistic and STAC for analysing street crime concentrations[J]. Transactions in GIS, 2011, 15(3):365-383.
[9] CHEN Huanfa, CHENG Tao, SHAWE-TAYLOR J. A balanced route design for min-max Multiple-Depot Rural Postman Problem (MMMDRPP):a police patrolling case[J]. International Journal of Geographical Information Science, 2018, 32(1):169-190.
[10] CHENG Tao, HAWORTH J, ANBAROGLU B, et al. Spatio-temporal data mining[M]//FISCHER M, NIJKAMP P. Handbook of Regional Science. Berlin:Springer, 2019.
[11] BOLLOBÁS B. Modern graph theory[M]. New York:Springer, 2019.
[12] ORTEGA A, FROSSARD P, KOVAČEVIC'J, et al. Graph signal processing:overview, challenges, and applications[J]. Proceedings of the IEEE, 2018, 106(5):808-828.
[13] ESTRADA E. Graph and network theory[J]. Developments in Water Science, 1988, 32:317-339.
[14] HASHEMI H, ABDELGHANY K. End-to-end deep learning methodology for real-time traffic network management[J]. Computer-Aided Civil and Infrastructure Engineering, 2018, 33(10):849-863.
[15] ZHANG Yang, CHENG Tao. Graph deep learning model for network-based predictive hotspot mapping of sparse spatio-temporal events[J]. Computers, Environment and Urban Systems, 2020, 79:101403.
[16] HOPFIELD J J. Neural networks and physical systems with emergent collective computational abilities[J]. Proceedings of the National Academy of Sciences of the United States of America, 1982, 79(8):2554-2558.
[17] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
[18] CHO K, VAN MERRIËNBOER B, BAHDANAU D, et al. On the properties of neural machine translation:encoder-decoder approaches[C]//Proceedings of the 8th Workshop on Syntax, Semantics and Structure in Statistical Translation. Doha:Association for Computational Linguistics, 2014:103-111.
[19] LECUN Y, BENGIO Y. Convolutional networks for images, speech, and time-series[M]//ARBIB M A. The Handbook of Brain Theory and Neural Networks. Cambridge:MIT Press, 1995.
[20] MONTI F, OTNESS K, BRONSTEIN M M. Motifnet:a motif-based graph convolutional network for directed graphs[C]//Proceedings of 2018 IEEE Data Science Workshop. Lausanne:IEEE, 2018:225-228.
[21] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]//Proceedings of the 5th International Conference on Learning Representations. Toulon:OpenReview, 2017:1-14.
[22] ZHANG Yang. Graph deep learning models for network-based spatio-temporal data forecasting:from dense to sparse[D]. London:University College London, 2020.
[23] SHI Xingjian, CHEN Zhourong, WANG Hao, et al. Convolutional LSTM network:a machine learning approach for precipitation nowcasting[C]//Proceedings of Annual Conference on Neural Information Processing Systems 2015. Montreal:[s.n.], 2015.
[24] LIANG Ming, HU Xiaolin. Recurrent convolutional neural network for object recognition[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston:IEEE, 2015:3367-3375.
[25] XU Zhenqi, LI Shan, DENG Weihong. Learning temporal features using LSTM-CNN architecture for face anti-spoofing[C]//Proceedings of the 20153rd IAPR Asian Conference on Pattern Recognition, Kuala Lumpur:IEEE, 2015:141-145.
[26] HUANG C J, KUO P H. A deep cnn-lstm model for particulate matter (PM_2.5) forecasting in smart cities[J]. Sensors, 2018, 18(7):2220.
[27] LIU Yipeng, ZHENG Haifeng, FENG Xinxin, et al. Short-term traffic flow prediction with conv-LSTM[C]//Proceedings of the 20179th International Conference on Wireless Communications and Signal Processing (WCSP). Nanjing:IEEE, 2017:1-6.
[28] ADEPEJU M, ROSSER G, CHENG Tao. Novel evaluation metrics for sparse spatio-temporal point process hotspot predictions-a crime case study[J]. International Journal of Geographical Information Science, 2016, 30(11):2133-2154.
[29] REN Yibin, CHENG Tao, ZHANG Yang. Deep spatio-temporal residual neural networks for road-network-based data modeling[J]. International Journal of Geographical Information Science, 2019, 33(9):1894-1912.
[30] REN Yibin, CHEN Hao, HAN Yong, et al. A hybrid integrated deep learning model for the prediction of citywide spatio-temporal flow volumes[J]. International Journal of Geographical Information Science, 2020, 34(4):802-823.
[31] ZHANG Yang, CHENG Tao, REN Yibin. A graph deep learning method for short-term traffic forecasting on large road networks[J]. Computer-Aided Civil and Infrastructure Engineering, 2019, 34(10):877-896.
[32] MHASKAR H N, POGGIO T. Deep vs. shallow networks:an approximation theory perspective[J]. Analysis and Applications, 2016, 14(6):829-848.
[33] KRAWCZYK B. Learning from imbalanced data:open challenges and future directions[J]. Progress in Artificial Intelligence, 2016, 5(4):221-232.
[34] IBRAHIM M R, HAWORTH J, LIPANI A, et al. Variational-LSTM autoencoder to forecast the spread of coronavirus across the globe[J]. PLoS One, 2021, 16(1):e0246120.
[35] LAI Juntao. Urban place profiling using geo-referenced social media data[D]. London:University College London, 2019.
[36] CHENG Tao, SHEN Jianan. Grouping people in cities:from space-time to place-time based profiling[M]//SHAW S L, SUI D. Human Dynamics Research in Smart and Connected Communities. Cham:Springer, 2018:181-201.
[37] SHEN Jianan. Profiling and grouping space-time activity patterns of urban individuals[D]. London:University College London, 2017.
[38] BRUCE C. Districting and resource allocation:a question of balance[J]. Geography&Public Safety, 2009, 1(4):1-3.
[39] WANG Fahui. Why police and policing need GIS:an overview[J]. Annals of GIS, 2012, 18(3):159-171.
[40] MITCHELL P S. Optimal selection of police patrol beats[J]. The Journal of Criminal Law, Criminology, and Police Science, 1972, 63(4):577-584.
[41] ZHANG Yue, BROWN D E. Police patrol districting method and simulation evaluation using agent-based model&GIS[J]. Security Informatics, 2013, 2(1):7.
[42] CHEN Huanfa, CHENG Tao, YE Xinyue. Designing efficient and balanced police patrol districts on an urban street network[J]. International Journal of Geographical Information Science, 2019, 33(2):269-290.
[43] CHEN Huanfa. Developing police patrol strategies based on the urban street network[D]. London:University College London, 2019.
[44] ZHOU Ming, JIN Jiarui, ZHANG Weinan, et al. Multi-agent reinforcement learning for order-dispatching via order-vehicle distribution matching[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Beijing:ACM, 2019:2645-2653.
[45] PARK S. ISPRS WG IV/8(GeoComputation and GeoSimulation) webinar[EB/OL].[2022-03-01].https://www.isprs.org/news/announcements/details.aspx?ID=277.