Nothing Special   »   [go: up one dir, main page]
Skip to main content

Advertisement

Springer Nature Link
Log in

On the inclusion of spatial information for spatio-temporal neural networks

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

When confronting a spatio-temporal regression, it is sensible to feed the model with any available prior information about the spatial dimension. For example, it is common to define the architecture of neural networks based on spatial closeness, adjacency, or correlation. A common alternative, if spatial information is not available or is too costly to introduce it in the model, is to learn it as an extra step of the model. While the use of prior spatial knowledge, given or learned, might be beneficial, in this work we question this principle by comparing traditional forms of convolution-based neural networks for regression with their respective spatial agnostic versions. Our results show that the typical inclusion of prior spatial information is not really needed in most cases. In order to validate this counterintuitive result, we perform thorough experiments over ten different datasets related to sustainable mobility and air quality, substantiating our conclusions on real world problems with direct implications for public health and economy. By comparing the performance over these datasets between traditional and their respective agnostic models, we can confirm the statistical significance of our findings with a confidence of 95%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availibility

specified through the manuscript.

Code availability

https://github.com/rdemedrano/SANN

Notes

  1. Portal de datos abiertos del Ayuntamiento de Madrid: https://datos.madrid.es/portal/site/egob/

  2. Portal de datos abiertos EMT: https://opendata.emtmadrid.es/Datos-estaticos/Datos-generales-(1)

  3. NYCTaxi and Limousine Commission (TLC) Trip Record Data: https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page

References

  1. Leung Y, Zhou Y, Lam KY, Fung T, Cheung KY, Kim T, Jung H (2019) Integration of air pollution data collected by mobile sensors and ground-based stations to derive a spatiotemporal air pollution profile of a city. Int J Geograph Inf Sci 33(11):2218–2240. https://doi.org/10.1080/13658816.2019.1633468

    Article  Google Scholar 

  2. LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural comput 1(4):541–551

    Article  Google Scholar 

  3. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems. Curran Associates, Inc., New York

    Google Scholar 

  4. Taigman Y, Yang M, Ranzato M, Wolf L (2014) DeepFace: closing the gap to human-level performance in face verification. IEEE Conf Comput Vis Pattern Recognit. https://doi.org/10.1109/CVPR.2014.220

    Article  Google Scholar 

  5. Zhao B, Lu H, Chen S, Liu J, Wu D (2017) Convolutional neural networks for time series classification. J Syst Eng Electron 28(1):162–169. https://doi.org/10.21629/JSEE.2017.01.18

    Article  Google Scholar 

  6. Cui Z, Chen W, Chen Y (2016) Multi-scale convolutional neural networks for time series classification. arXiv:1603.06995 [cs] . ArXiv: 1603.06995

  7. Rodrigues F, Pereira FC (2020) Beyond expectation: deep joint mean and quantile regression for spatiotemporal problems. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2020.2966745

    Article  Google Scholar 

  8. Tu E, Kasabov N, Yang J (2017) Mapping temporal variables into the neucube for improved pattern recognition, predictive modeling, and understanding of stream data. IEEE Trans Neural Netw Learn Syst 28(6):1305–1317. https://doi.org/10.1109/TNNLS.2016.2536742

    Article  MathSciNet  Google Scholar 

  9. Nam H, Han B (2016) Learning multi-domain convolutional neural networks for visual tracking. pp. 4293–4302

  10. Kappeler A, Yoo S, Dai Q, Katsaggelos AK (2016) Video super-resolution with convolutional neural networks. IEEE Trans Comput Imag 2(2):109–122. https://doi.org/10.1109/TCI.2016.2532323

    Article  MathSciNet  Google Scholar 

  11. Liu Z, Li Z, Wang R, Zong M, Ji W (2020) Spatiotemporal saliency-based multi-stream networks with attention-aware LSTM for action recognition. Neural Comput Appl 32(18):14593–14602. https://doi.org/10.1007/s00521-020-05144-7

    Article  Google Scholar 

  12. Jo D, Yu B, Jeon H, Sohn K (2019) Image-to-image learning to predict traffic speeds by considering area-wide spatio-temporal dependencies. IEEE Trans Veh Technol 68(2):1188–1197. https://doi.org/10.1109/TVT.2018.2885366

    Article  Google Scholar 

  13. Guo S, Lin Y, Li S, Chen Z, Wan H (2019) Deep spatial-temporal 3D convolutional neural networks for traffic data forecasting. IEEE Trans Intell Transp Syst 20(10):3913–3926. https://doi.org/10.1109/TITS.2019.2906365

    Article  Google Scholar 

  14. Ai Y, Li Z, Gan M, Zhang Y, Yu D, Chen W, Ju Y (2019) A deep learning approach on short-term spatiotemporal distribution forecasting of dockless bike-sharing system. Neural Comput Appl 31(5):1665–1677. https://doi.org/10.1007/s00521-018-3470-9

    Article  Google Scholar 

  15. Wu Y, Tan H, Qin L, Ran B, Jiang Z (2018) A hybrid deep learning based traffic flow prediction method and its understanding. Transp Res Part C Emerg Technol 90:166–180. https://doi.org/10.1016/j.trc.2018.03.001

    Article  Google Scholar 

  16. de Medrano R, Aznarte JL (2020) A spatio-temporal attention-based spot-forecasting framework for urban traffic prediction. Appl Soft Comput 96:106615. https://doi.org/10.1016/j.asoc.2020.106615

    Article  Google Scholar 

  17. Li Y, Yu R, Shahabi C, Liu Y (2018) Diffusion convolutional recurrent neural network: data-driven traffic forecasting. arXiv:1707.01926 [cs, stat] . ArXiv: 1707.01926

  18. Guo S, Lin Y, Feng N, Song C, Wan H (2019) Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In: Proceedings of the AAAI conference on artificial intelligence 33(01): 922–929. https://doi.org/10.1609/aaai.v33i01.3301922

  19. Zhang Y, Cheng T (2020) Graph deep learning model for network-based predictive hotspot mapping of sparse spatio-temporal events. Comput Environ Urban Syst 79:101403. https://doi.org/10.1016/j.compenvurbsys.2019.101403

    Article  Google Scholar 

  20. Zhang Y, Cheng T, Ren Y, Xie K (2020) A novel residual graph convolution deep learning model for short-term network-based traffic forecasting. Int J Geograph Inf Sci. https://doi.org/10.1080/13658816.2019.1697879

    Article  Google Scholar 

  21. Zhou Z, Li X (2017) Graph convolution: a high-order and adaptive approach. arXiv:1706.09916 [cs, stat] . ArXiv: 1706.09916

  22. Lu F, Liu K, Duan Y, Cheng S, Du F (2018) Modeling the heterogeneous traffic correlations in urban road systems using traffic-enhanced community detection approach. Phys A Stat Mech Appl 501:227–237. https://doi.org/10.1016/j.physa.2018.02.062

    Article  Google Scholar 

  23. Asadi R, Regan AC (2020) A spatio-temporal decomposition based deep neural network for time series forecasting. Appl Soft Comput 87:105963. https://doi.org/10.1016/j.asoc.2019.105963

    Article  Google Scholar 

  24. Aram P, Kadirkamanathan V, Anderson SR (2015) Spatiotemporal system identification with continuous spatial maps and sparse estimation. IEE Trans Neural Netw Learn Syst 26(11):2978–2983. https://doi.org/10.1109/TNNLS.2015.2392563

    Article  MathSciNet  Google Scholar 

  25. Do LNN, Vu HL, Vo BQ, Liu Z, Phung D (2019) An effective spatial-temporal attention based neural network for traffic flow prediction. Transp Res Part C Emerg Technol 108:12–28. https://doi.org/10.1016/j.trc.2019.09.008

    Article  Google Scholar 

  26. Yu B, Lee Y, Sohn K (2020) Forecasting road traffic speeds by considering area-wide spatio-temporal dependencies based on a graph convolutional neural network (GCN). Transp Res Part C Emerg Technoloies 114:189–204. https://doi.org/10.1016/j.trc.2020.02.013

    Article  Google Scholar 

  27. Wu Z, Pan S, Long G, Jiang J, Chang X, Zhang C (2020) Connecting the dots: multivariate time series forecasting with graph neural networks. KDD 2020 . ArXiv: 2005.11650

  28. Uselis A, Lukoševičius M, Stasytis L (2020) Localized convolutional neural networks for geospatial wind forecasting. arXiv:2005.05930 [cs, stat] . ArXiv: 2005.05930

  29. Shi X, Chen Z, Wang H, Yeung DY, Wong WK, Woo WC (2015) Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Cortes C, Lawrence ND, Lee DD, Sugiyama M, Garnett R (eds) Advances in neural information processing systems. Curran Associates, Inc., New York

    Google Scholar 

  30. Lee SI (2017) Correlation and spatial autocorrelation. Springer, Berlin

    Book  Google Scholar 

  31. Moran PAP (1950) Notes on continuous stochastic phenomena. Biometrika 37(1/2):17–23

    Article  MathSciNet  Google Scholar 

  32. Chouakria AD, Nagabhushan PN (2007) Adaptive dissimilarity index for measuring time series proximity. Adv Data Anal Classif 1(1):5–21. https://doi.org/10.1007/s11634-006-0004-6

    Article  MathSciNet  MATH  Google Scholar 

  33. Liao B, Zhang J, Wu C, McIlwraith D, Chen T, Yang S, Guo Y, Wu F (2018) Deep sequence learning with auxiliary information for traffic prediction. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining. ACM

  34. Cui Z, Henrickson K, Ke R, Wang Y (2019) Traffic graph convolutional recurrent neural network: a deep learning framework for network-scale traffic learning and forecasting. IEEE Trans Intell Transp Syst. https://doi.org/10.1109/TITS.2019.2950416

    Article  Google Scholar 

  35. Bergmeir C, Hyndman RJ, Koo B (2018) A note on the validity of cross-validation for evaluating autoregressive time series prediction. Comput Stat Data Anal 120:70–83. https://doi.org/10.1016/j.csda.2017.11.003

    Article  MathSciNet  MATH  Google Scholar 

  36. Wikle C.K, Zammit-Mangion A, Cressie, N (2019) Spatio-temporal statistics with R, 1 edn. Chapman and Hall/CRC, Boca Raton, Florida : CRC Press, [2019] . https://doi.org/10.1201/9781351769723. https://www.taylorfrancis.com/books/9780429649783

  37. Navares R, Aznarte JL (2020) Predicting air quality with deep learning LSTM: towards comprehensive models. Ecol Inf 55:101019. https://doi.org/10.1016/j.ecoinf.2019.101019

    Article  Google Scholar 

Download references

Acknowledgements

This research has been partially funded by the Empresa Municipal de Transportes (EMT) of Madrid under the chair Aula Universitaria EMT/UNED de Calidad del Aire y Movilidad Sostenible.The authors are grateful to the anonymous reviewers for their constructive and helpful suggestions and comments. Especially to reviewer # 3, whose suggestions have directly contributed to the theoretical foundations of the article.

Funding

Partially funded by the Empresa Municipal de Transportes (EMT) of Madrid.

Author information

Authors and Affiliations

  1. Artificial Intelligence Department, Universidad Nacional de Educación a Distancia—UNED, 28041, Madrid, Spain

    Rodrigo de Medrano & José L. Aznarte

Authors
  1. Rodrigo de Medrano
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. José L. Aznarte
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to José L. Aznarte.

Ethics declarations

Conflict of interest

None.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Medrano, R.d., Aznarte, J.L. On the inclusion of spatial information for spatio-temporal neural networks. Neural Comput & Applic 33, 14723–14740 (2021). https://doi.org/10.1007/s00521-021-06111-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-06111-6

Keywords

Search

Navigation