Network SpaceTime AI: Concepts, Methods and Applications

doi:10.11947/j.JGGS.2022.0309

Abstract

Abstract:

SpacetimeAI and GeoAI are currently hot topics, applying the latest algorithms in computer science, such as deep learning, to spatiotemporal data. Although deep learning algorithms have been successfully applied to raster data 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 a network (&graph)-based framework as a generic spatial structure to present space-time processes that are usually represented by the points, polylines, and polygons. We illustrate network and graph-based SpaceTimeAI, from graph-based deep learning for prediction, to space-time clustering and optimisation. These applications demonstrate the advantages of network (graph)-based SpacetimeAI in the fields of transport&mobility, crime&policing, and public health.

Key words: spatiotemporal intelligence; network; graph; deep learning; spatiotemporal prediction; spatiotemporal clustering; spatiotemporal optimization

Tao CHENG,Yang ZHANG,James HAWORTH. Network SpaceTime AI: Concepts, Methods and Applications[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(3): 78-92.

Figures/Tables 10

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

References 50

[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. doi: 10.1016/j.cities.2019.102481
[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. doi: 10.1016/j.isprsjprs.2019.04.017
[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. doi: 10.1016/j.artint.2018.03.002
[4]	WANG B, ZHANG D, BRANTINGHAM P.J., et al. Deep learning for real time crime forecasting[EB/OL]. [2022-05-25]. https://arxiv.org/abs/1707.03340.
[5]	OPENSHAW S, TAYLOR P. The modifiable areal unit problem[M]// WRIGLEYN, BENNETTR J. Quantitative Geography: A British View. London:Routledge, 1981:60-69.
[6]	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. doi: 10.1007/s10940-016-9321-x
[7]	CHENG Tao, HAWORTH J, WANG Jiaqiu. Spatio-temporal autocorrelation of road network data[J]. Journal of Geographical Systems, 2012, 14(4):389-413. doi: 10.1007/s10109-011-0149-5
[8]	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.
[9]	SHIODE S. Street-level spatial scan statistic and STAC for analysing street crime concentrations[J]. Transactions in GIS, 2011, 15(3):365-383. doi: 10.1111/j.1467-9671.2011.01255.x
[10]	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. doi: 10.1080/13658816.2017.1380201
[11]	CHENG Tao, HAWORTH J, ANBAROGLU B, et al. Spatio-temporal data mining[M]// FISCHERM, NIJKAMPP. Handbook of Regional Science. Berlin:Springer, 2019.
[12]	BOLLOBÁS B. Modern graph theory[M]. New York: Springer, 2019.
[13]	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. doi: 10.1109/JPROC.2018.2820126
[14]	ESTRADA E. Graph and network theory[J]. Developments in Water Science, 1988, 32:317-339.
[15]	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. doi: 10.1111/mice.12376
[16]	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. doi: 10.1016/j.compenvurbsys.2019.101403
[17]	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. pmid: 6953413
[18]	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780. pmid: 9377276
[19]	GRAVES A. Generating sequences with recurrent neural networks[EB/OL]. [2022-05-25].https://arxiv.org/abs/1308.0850.
[20]	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.
[21]	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.
[22]	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.
[23]	HENAFF M, BRUNA J, LECUN Y. Deep convolutional networks on graph-structured data[EB/OL]. [2022-05-25]. https://arxiv.org/abs/1506.05163.
[24]	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.
[25]	ZHANG Yang. Graph deep learning models for network-based spatio-temporal data forecasting:from dense to sparse[D]. London: University College London, 2020.
[26]	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.
[27]	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.
[28]	XU Zhenqi, LI Shan, DENG Weihong. Learning temporal features using LSTM-CNN architecture for face anti-spoofing[C]// Proceedings of the 2015 3rd IAPR Asian Conference on Pattern Recognition, Kuala Lumpur: IEEE, 2015:141-145.
[29]	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. doi: 10.3390/s18072220
[30]	LIU Yipeng, ZHENG Haifeng, FENG Xinxin, et al. Short-term traffic flow prediction with conv-LSTM[C]// Proceedings of the 2017 9th International Conference on Wireless Communications and Signal Processing (WCSP). Nanjing:IEEE, 2017:1-6.
[31]	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. doi: 10.1080/13658816.2016.1159684
[32]	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. doi: 10.1080/13658816.2019.1599895
[33]	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. doi: 10.1080/13658816.2019.1652303
[34]	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. doi: 10.1111/mice.12450
[35]	MHASKAR H N, POGGIO T. Deep vs. shallow networks:an approximation theory perspective[J]. Analysis and Applications, 2016, 14(6):829-848. doi: 10.1142/S0219530516400042
[36]	KRAWCZYK B. Learning from imbalanced data:open challenges and future directions[J]. Progress in Artificial Intelligence, 2016, 5(4):221-232. doi: 10.1007/s13748-016-0094-0
[37]	BOTHA A E, DEDNAMW. A simple iterative map forecast of the COVID-19 pandemic[EB/OL]. [2022-05-25]. https://arxiv.org/abs/2003.10532.
[38]	Z HU Q GE, S LI, et al. Forecasting and evaluating intervention of COVID-19 in the world. [EB/OL]. [2022-05-25].https://arxiv.org/abs/2003.09800.
[39]	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. doi: 10.1371/journal.pone.0246120
[40]	LAI Juntao. Urban place profiling using geo-referenced social media data[D]. London: University College London, 2019.
[41]	CHENG Tao, SHEN Jianan. Grouping people in cities:from space-time to place-time based profiling[M]// SHAWS L, SUID. Human Dynamics Research in Smart and Connected Communities. Cham:Springer, 2018:181-201.
[42]	SHEN Jianan. Profiling and grouping space-time activity patterns of urban individuals[D]. London: University College London, 2017.
[43]	BRUCE C. Districting and resource allocation:a question of balance[J]. Geography&Public Safety, 2009, 1(4):1-3.
[44]	WANG Fahui. Why police and policing need GIS:an overview[J]. Annals of GIS, 2012, 18(3):159-171. doi: 10.1080/19475683.2012.691900
[45]	MITCHELL P S. Optimal selection of police patrol beats[J]. The Journal of Criminal Law, Criminology, and Police Science, 1972, 63(4):577-584. doi: 10.2307/1141814
[46]	ZHANG Yue, BROWN D E. Police patrol districting method and simulation evaluation using agent-based model&GIS[J]. Security Informatics, 2013, 2(1):7. doi: 10.1186/2190-8532-2-7
[47]	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. doi: 10.1080/13658816.2018.1525493
[48]	CHEN Huanfa. Developing police patrol strategies based on the urban street network[D]. London: University College London, 2019.
[49]	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.
[50]	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.