Graph neural networks for multivariate time series regression with application to seismic data

Machine learning, with its advances in deep learning has shown great potential in analyzing time series. In many scenarios, however, additional information that can potentially improve the predictions is available. This is crucial for data that arise from e. g., sensor networks that contain information about sensor locations. Then, such spatial information can be exploited by modeling it via graph structures, along with the sequential (time series) information. Recent advances in adapting deep learning to graphs have shown potential in various tasks. However, these methods have not been adapted for time series tasks to a great extent. Most attempts have essentially consolidated around time series forecasting with small sequence lengths. Generally, these architectures are not well suited for regression or classification tasks where the value to be predicted is not strictly depending on the most recent values, but rather on the whole length of the time series. We propose TISER-GCN, a novel graph neural network architecture for processing, in particular, these long time series in a multivariate regression task. Our proposed model is tested on two seismic datasets containing earthquake waveforms, where the goal is to predict maximum intensity measurements of ground shaking at each seismic station. Our findings demonstrate promising results of our approach—with an average MSE reduction of 16.3%—compared to the best performing baselines. In addition, our approach matches the baseline scores by needing only half the input size. The results are discussed in depth with an additional ablation study.

Interreg North-West Europe program (Interreg NWE), project Di-Plast - Digital Circular Economy for the Plastics Industry (NWE729).
INGV Pianeta Dinamico 2021 Tema 8 SOME (CUP D53J1900017001) funded by Italian Ministry of University and Research “Fondo finalizzato al rilancio degli investimenti delle amministrazioni centrali dello Stato e allo sviluppo del Paese, legge 145/2018.

1. Tilak, S., Abu-Ghazaleh, N.B., Heinzelman, W.: A taxonomy of wireless micro-sensor network models. ACM SIGMOBILE Mob. Comput. Commun. Rev. 6(2), 28–36 (2002) 2. Tubaishat, M., Madria, S.: Sensor networks: an overview. IEEE Potentials 22(2), 20–23 (2003) 3. Aslam, J., Lim, S., Pan, X., Rus, D.: City-scale traffic estimation from a roving sensor network. In: Proceedings of the 10th ACM Conference on Embedded Network Sensor Systems, pp. 141–154 (2012) 4. Hatchett, B.J., Cao, Q., Dawson, P.B., Ellis, C.J., Hecht, C.W., Kawzenuk, B., Lancaster, J., Osborne, T., Wilson, A.M., Anderson, M., et al.: Observations of an extreme atmospheric river storm with a diverse sensor network. Earth Space Sci. 7(8), 2020–001129 (2020) 5. van den Ende, M.P., Ampuero, J.-P.: Automated seismic source characterization using deep graph neural networks. Geophys. Res. Lett. 47(17), 2020–088690 (2020)
6. Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794 (2016) 7. Tan, C.W., Bergmeir, C., Petitjean, F., Webb, G.I.: Time series extrinsic regression. Data Min. Knowl. Discov. 35(3), 1032–1060 (2021) 8. van den Hoogen, J.O.D., Bloemheuvel, S.D., Atzmueller, M.: An improved wide-kernel CNN for classifying multivariate signals in fault diagnosis. In: International Conference on Data Mining Workshops, pp. 275–283 (2020) 9. Ince, T., Kiranyaz, S., Eren, L., Askar, M., Gabbouj, M.: Real-time motor fault detection by 1-d convolutional neural networks. IEEE Trans. Ind. Electron. 63(11), 7067–7075 (2016) 10. Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., Zhang, C.: Connecting the dots: multivariate time series forecasting with graph neural networks. In: Proceedings of KDD, pp. 753–763 (2020) 11. Deng, A., Hooi, B.: Graph neural network-based anomaly detection in multivariate time series. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 4027–4035 (2021) 12. Cini, A., Marisca, I., Alippi, C.: Filling the g_ap_s: multivariate time series imputation by graph neural networks. In: International Conference on Learning Representations (2022). https:// openreview.net/forum?id=kOu3-S3wJ7 13. Yano, K., Shiina, T., Kurata, S., Kato, A., Komaki, F., Sakai, S., Hirata, N.: Graph-partitioning based convolutional neural network for earthquake detection using a seismic array. J. Geophys. Res. Solid Earth 126(5), 2020–020269 (2021) 14. Kim, G., Ku, B., Ahn, J.-K., Ko, H.: Graph convolution networks for seismic events classification using raw waveform data from multiple stations. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2021) 15. Jozinovi ́ c, D., Lomax, A., Štajduhar, I., Michelini, A.: Rapid prediction of earthquake ground shaking intensity using raw waveform data and a convolutional neural network. Geophys. J. Int. 222(2), 1379–1389 (2020) 16. Jozinovi ́ c, D., Lomax, A., Štajduhar, I., Michelini, A.: Transfer learning: Improving neural network based prediction of earthquake ground shaking for an area with insufficient training data. Geophys. J. Int. 229, 704–718 (2021) 17. Veliˇ ckovi ́ c, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (2018) 18. Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986) 19. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016) 20. Sperduti, A., Starita, A.: Supervised neural networks for the classification of structures. IEEE IEEE Trans Neural 8(3), 714–735 (1997) 21. Bruna, J., Zaremba, W., Szlam, A., LeCun, Y.: Spectral networks and deep locally connected networks on graphs. In: 2nd International Conference on Learning Representations, ICLR 2014 (2014) 22. Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., Sun, M.: Graph neural networks: a review of methods and applications. AI Open 1, 57–81 (2020) 23. Chen, Z., Chen, F., Zhang, L., Ji, T., Fu, K., Zhao, L., Chen, F., Wu, L., Aggarwal, C., Lu, C.-T.: Bridging the gap between spatial and spectral domains: a survey on graph neural networks. CoRR (2020) 24. Welling, M., Kipf, T.N.: Semi-supervised classification with graph convolutional networks. In: J. International Conference on Learning Representations (ICLR 2017) (2016) 25. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017). arXiv:1706.03762 26. Cao, D., Wang, Y., Duan, J., Zhang, C., Zhu, X., Huang, C., Tong, Y., Xu, B., Bai, J., Tong, J., et al.: Spectral temporal graph neural network for multivariate time-series forecasting. Adv. Neural. Inf. Process. Syst. 33, 17766–17778 (2020) 27. Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. Adv. Neural. Inf. Process. Syst. 29, 3844–3852 (2016) 28. Li, Y., Yu, R., Shahabi, C., Liu, Y.: Diffusion convolutional recurrent neural network: data-driven traffic forecasting. In: International Conference on Learning Representations (ICLR ’18) (2018) 29. Yu, B., Yin, H., Zhu, Z.: Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI) (2018) 30. Ingate, S., Husebye, E.S.: The IRIS Consortium: Community Based Facilities and Data Management for Seismology (2008) 31. Strollo, A., Cambaz, D., Clinton, J., Danecek, P., Evangelidis, C.P., Marmureanu, A., et al.: EIDA: the European integrated data archive and service infrastructure within ORFEUS. Seismol. Res. Lett. 92(3), 1788–1795 (2021) 32. Ochoa, L.H., Niño, L.F., Vargas, C.A.: Fast magnitude determination using a single seismological station record implementing machine learning techniques. Geod. Geodyn. 9(1), 34–41 (2018) 33. Mousavi, S.M., Ellsworth, W.L., Zhu, W., Chuang, L.Y., Beroza, G.C.: Earthquake transformer-an attentive deep-learning model for simultaneous earthquake detection and phase picking. Nat. Commun. 11(1), 1–12 (2020) 34. Lomax, A., Michelini, A., Jozinovi ́ c, D.: An investigation of rapid earthquake characterization using single-station waveforms and a convolutional neural network. Seismol. Res. Lett. 90(2A), 517–529 (2019) 35. Ross, Z.E., Meier, M.-A., Hauksson, E.: P wave arrival picking and first-motion polarity determination with deep learning. J. Geophys. Res. Solid Earth 123(6), 5120–5129 (2018) 36. Kriegerowski, M., Petersen, G.M., Vasyura-Bathke, H., Ohrnberger, M.: A deep convolutional neural network for localization of clustered earthquakes based on multistation full waveforms. Seismol. Res. Lett. 90(2A), 510–516 (2019) 37. Münchmeyer, J., Bindi, D., Leser, U., Tilmann, F.: The transformer earthquake alerting model: a new versatile approach to earthquake early warning. Geophys. J. Int. 225(1), 646–656 (2021) 38. McBrearty, I.W., Beroza, G.C.: Earthquake location and magnitude estimation with graph neural networks. arXiv preprint arXiv:2203.05144 (accepted at ICIP 2022) (2022) 39. Michelini, A., Margheriti, L., Cattaneo, M., Cecere, G., D’Anna, G., Delladio, A., et al.: The Italian National Seismic Network and the earthquake and tsunami monitoring and surveillance systems. Adv. Geosci. 43, 31–38 (2016). https://doi.org/10.5194/adgeo-4331-2016 40. Danecek, P., Pintore, S., Mazza, S., Mandiello, A., Fares, M., Carluccio, I., Della Bina, E., Franceschi, D., Moretti, M., Lauciani, V., Quintiliani, M., Michelini, A.: The Italian Node of the European Integrated Data Archive. Seismol. Res. Lett. 92(3), 1726–1737 (2021). https://doi.org/10.1785/0220200409 41. van den Hoogen, J., Bloemheuvel, S., Atzmueller, M.: Classifying multivariate signals in rolling bearing fault detection using adaptive wide-kernel CNNs. Appl. Sci. (2021). https://doi.org/10.3390/ app112311429 42. Ying, Z., You, J., Morris, C., Ren, X., Hamilton, W., Leskovec, J.: Hierarchical graph representation learning with differentiable pooling. Adv. Neural. Inf. Process. Syst. 3, 1 (2018) 43. Simonovsky, M., Komodakis, N.: Dynamic edge-conditioned filters in convolutional neural networks on graphs. In: Proceedings of IEEE ICVPR, pp. 3693–3702 (2017)
44. Hinton, G., Srivastava, N., Swersky, K.: Neural networks for machine learning lecture 6a overview of mini-batch gradient descent. Cited on 14(8), 2 (2012) 45. Mazilu, S., Calatroni, A., Gazit, E., Roggen, D., Hausdorff, J.M., Tröster, G.: Feature learning for detection and prediction of freezing of gait in Parkinson’s disease. In: International Workshop on Machine Learning and Data Mining in Pattern Recognition, pp. 144–158. Springer (2013) 46. Masiala, S., Huijbers, W., Atzmueller, M.: Feature-set-engineering for detecting freezing of gait in Parkinson’s disease using deep recurrent neural networks. arXiv preprint arXiv:1909.03428 (2019) 47. Domingos, P.M., Hulten, G.: Catching up with the data: research issues in mining data streams. In: DMKD (2001) 48. Shuman, D.I., Narang, S.K., Frossard, P., Ortega, A., Vandergheynst, P.: The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Process. Mag. 30(3), 83–98 (2013) 49. Luo, D., Cheng, W., Xu, D., Yu, W., Zong, B., Chen, H., Zhang, X.: Parameterized explainer for graph neural network. Adv. Neural. Inf. Process. Syst. 33, 19620–19631 (2020) 50. Schwenke, L., Atzmueller, M.: Constructing global coherence representations: identifying interpretability and coherences of transformer attention in time series data. In: Proceedings of the 8th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2021, Porto, Portugal, October 6–9, 2021, pp. 1–12. IEEE (2021). https://doi.org/10.1109/DSAA53316.2021.9564126 51. Jozinovi ́ c, D., Lomax, A., Štajduhar, I., Michelini, A.: CNNpredIM—dataset for rapid prediction of earthquake ground shaking intensity using raw waveform data and a convolutional neural network. Zenodo (2020). https://doi.org/10.5281/zenodo. 3669969 52. Jozinovi ́ c, D., Lomax, A., Štajduhar, I., Michelini, A.: Datasetseismic data from central-western Italy used in the paper on rapid prediction of ground motion using a convolutional neural network. Zenodo (2021). https://doi.org/10.5281/zenodo.5541083