Trajectory prediction based on long short-term memory network and Kalman filter using hurricanes as an example. (English) Zbl 1460.86044
Summary: Trajectory data can objectively reflect the moving law of moving objects. Therefore, trajectory prediction has high application value. Hurricanes often cause incalculable losses of life and property, trajectory prediction can be an effective means to mitigate damage caused by hurricanes. With the popularization and wide application of artificial intelligence technology, from the perspective of machine learning, this paper trains a trajectory prediction model through historical trajectory data based on a long short-term memory (LSTM) network. An improved LSTM (ILSTM) trajectory prediction algorithm that improves the prediction of the simple LSTM is proposed, and the Kalman filter is used to filter the prediction results of the improved LSTM algorithm, which is called LSTM-KF. Through simulation experiments of Atlantic hurricane data from 1851 to 2016, compared to other LSTM and ILSTM algorithms, it is found that the LSTM-KF trajectory prediction algorithm has the lowest prediction error and the best prediction effect.
Software:
Dlib-mlReferences:
| [1] | Zheng, Y., Trajectory data mining: an overview, ACM Trans. Intell. Syst. Technol. (TIST), 6, 3, 1-41 (2015) · doi:10.1145/2743025 |
| [2] | Tang, J., Conflict detection and resolution for civil aviation: a literature survey, IEEE Aerosp. Electron. Syst. Mag., 34, 10, 20-35 (2019) · doi:10.1109/MAES.2019.2914986 |
| [3] | Meuel, T.; Prado, G.; Seychelles, F.; Bessafi, M.; Kellay, H., Hurricane track forecast cones from fluctuations, Sci. Rep., 2, 446 (2012) · doi:10.1038/srep00446 |
| [4] | Lee, RS; Liu, JN, Tropical cyclone identification and tracking system using integrated neural oscillatory elastic graph matching and hybrid RBF network track mining techniques, IEEE Trans. Neural Netw., 11, 3, 680-689 (2000) · doi:10.1109/72.846739 |
| [5] | Rajasekaran, S.; Lee, T.; Jeng, D-S, Tidal level forecasting during typhoon surge using functional and sequential learning neural networks, J. Waterway Port Coastal Ocean Eng., 131, 6, 321-324 (2005) · doi:10.1061/(ASCE)0733-950X(2005)131:6(321) |
| [6] | Rozanova, OS; Yu, J-L; Hu, C-K, Typhoon eye trajectory based on a mathematical model: comparing with observational data, Nonlinear Anal.: Real World Appl., 11, 3, 1847-1861 (2010) · Zbl 1192.35134 · doi:10.1016/j.nonrwa.2009.04.011 |
| [7] | DeMaria, M.; Mainelli, M.; Shay, LK; Knaff, JA; Kaplan, J., Further improvements to the statistical hurricane intensity prediction scheme (SHIPS), Weather Forecast., 20, 4, 531-543 (2005) · doi:10.1175/WAF862.1 |
| [8] | Rekabdarkolaee, HM; Krut, C.; Fuentes, M.; Reich, BJ, A Bayesian multivariate functional model with spatially varying coefficient approach for modeling hurricane track data, Spatial Stat., 29, 351-365 (2019) · doi:10.1016/j.spasta.2018.12.006 |
| [9] | Mitchell, R.; Michalski, J.; Carbonell, T., An Artificial Intelligence Approach (2013), Berlin: Springer, Berlin |
| [10] | King, DE, Dlib-ml: a machine learning toolkit, J. Mach. Learn. Res., 10, 1755-1758 (2009) |
| [11] | Alemany, S., Beltran, J., Perez, A., Ganzfried, S.: Predicting hurricane trajectories using a recurrent neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 468-475 (2019) |
| [12] | Kim, H-S; Kim, J-H; Ho, C-H; Chu, P-S, Pattern classification of typhoon tracks using the fuzzy c-means clustering method, J. Clim., 24, 2, 488-508 (2011) · doi:10.1175/2010JCLI3751.1 |
| [13] | Gao, S.; Zhao, P.; Pan, B.; Li, Y.; Zhou, M.; Xu, J.; Zhong, S.; Shi, Z., A nowcasting model for the prediction of typhoon tracks based on a long short term memory neural network, Acta Oceanol. Sin., 37, 5, 8-12 (2018) · doi:10.1007/s13131-018-1219-z |
| [14] | Kordmahalleh, M.M., Sefidmazgi, M.G., Homaifar, A., Liess, S.: Hurricane trajectory prediction via a sparse recurrent neural network. In: Proceedings of the 5th International Workshop on Climate Informatics, pp. 2-3. ACM, Denver (2015) |
| [15] | Baik, J-J; Hwang, H-S, Tropical cyclone intensity prediction using regression method and neural network, J. Meteorol. Soc. Jpn. Ser. II, 76, 5, 711-717 (1998) · doi:10.2151/jmsj1965.76.5_711 |
| [16] | Baik, J-J; Paek, J-S, A neural network model for predicting typhoon intensity, J. Meteorol. Soc. Jpn. Ser. II, 78, 6, 857-869 (2000) · doi:10.2151/jmsj1965.78.6_857 |
| [17] | Formentin, S., Bianchessi, A.G., Savaresi, S.M.: On the prediction of future vehicle locations in free-floating car sharing systems. In: 2015 IEEE Intelligent Vehicles Symposium (iv), pp. 1006-1011. IEEE (2015) |
| [18] | Qiao, S.; Han, N.; Zhu, W.; Gutierrez, LA, TraPlan: an effective three-in-one trajectory-prediction model in transportation networks, IEEE Trans. Intell. Transp. Syst., 16, 3, 1188-1198 (2014) · doi:10.1109/TITS.2014.2353302 |
| [19] | Chen, M., Liu, Y., Yu, X.: Nlpmm: a next location predictor with markov modeling. In: Pacific-Asia conference on knowledge discovery and data mining, pp. 186-197. Springer, Cham (2014) |
| [20] | Figueiredo, F., Ribeiro, B., Almeida, J.M., Faloutsos, C.: TribeFlow: mining & predicting user trajectories. In: Proceedings of the 25th International Conference on World Wide Web, pp. 695-706 (2016) |
| [21] | Tang, J.; Piera, MA; Guasch, T., Coloured Petri net-based traffic collision avoidance system encounter model for the analysis of potential induced collisions, Transp. Res. Part C: Emerg. Technol., 67, 357-377 (2016) · doi:10.1016/j.trc.2016.03.001 |
| [22] | Tang, J.; Zhu, F.; Piera, MA, A causal encounter model of traffic collision avoidance system operations for safety assessment and advisory optimization in high-density airspace, Transp. Res. Part C: Emerg. Technol., 96, 347-365 (2018) · doi:10.1016/j.trc.2018.10.006 |
| [23] | Wiest, J., Höffken, M., Kreßel, U., Dietmayer, K.: Probabilistic trajectory prediction with gaussian mixture models. In: 2012 IEEE Intelligent Vehicles Symposium, pp. 141-146. IEEE, Alcala (2012) |
| [24] | Chapuis, B., Moro, A., Kulkarni, V., Garbinato, B.: Capturing complex behaviour for predicting distant future trajectories. In: Proceedings of the 5th ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems, pp 64-73. ACM, California (2016) |
| [25] | Wolfson, O., Xu, B., Chamberlain, S., Jiang, L.: Moving objects databases: issues and solutions. In: Proceedings. Tenth International Conference on Scientific and Statistical Database Management (Cat. No. 98TB100243), pp 111-122. IEEE, DC (1998) |
| [26] | Junghans, C., Gertz, M.: Modeling and prediction of moving region trajectories. In: Proceedings of the ACM SIGSPATIAL International Workshop on GeoStreaming 2010, pp 23-30. ACM, New York (2010) |
| [27] | Prevost, C.G., Desbiens, A., Gagnon, E.: Extended Kalman filter for state estimation and trajectory prediction of a moving object detected by an unmanned aerial vehicle. In: 2007 American Control Conference, pp 1805-1810. IEEE, New York (2007) |
| [28] | Jeung, H., Liu, Q., Shen, H.T., Zhou, X.: A hybrid prediction model for moving objects. In: 2008 IEEE 24th International Conference on Data Engineering, pp 70-79. IEEE, Cancun (2008) |
| [29] | Monreale, A., Pinelli, F., Trasarti, R., Giannotti, F.: Wherenext: a location predictor on trajectory pattern mining. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 637-646. ACM, Paris (2009) |
| [30] | Long, T., Qiao, S., Tang, C., Liu, L., Li, T., Wu, J.: E 3 TP: a novel trajectory prediction algorithm in moving objects databases. In: Pacific-Asia Workshop on Intelligence and Security Informatics, pp 76-88. Springer, Heidelberg (2009) |
| [31] | Kim, S.-W., Won, J.-I., Kim, J.-D., Shin, M., Lee, J., Kim, H.: Path prediction of moving objects on road networks through analyzing past trajectories. In: International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, pp 379-389. Springer, Heidelberg (2007) |
| [32] | Qiao, S.; Shen, D.; Wang, X.; Han, N.; Zhu, W., A self-adaptive parameter selection trajectory prediction approach via hidden Markov models, IEEE Trans. Intell. Transp. Syst., 16, 1, 284-296 (2014) · doi:10.1109/TITS.2014.2331758 |
| [33] | Li, M.; Lu, F.; Zhang, H.; Chen, J., Predicting future locations of moving objects with deep fuzzy-LSTM networks, Transportmetrica A: Transp. Sci., 16, 1, 119-136 (2020) · doi:10.1080/23249935.2018.1552334 |
| [34] | De Leege, A., van Paassen, M., Mulder, M.: A machine learning approach to trajectory prediction. In: AIAA Guidance, Navigation, and Control (GNC) Conference 2013, p 4782. AIAA, MA (2013) |
| [35] | Chen, M., Liu, Y., Yu, X.: Predicting next locations with object clustering and trajectory clustering. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp 344-356. Springer, Heidelberg (2015) |
| [36] | Shah, R., Romijnders, R.: Applying deep learning to basketball trajectories. Applying deep learning to basketball trajectories. Last revised 16 Aug 2016 (2016) |
| [37] | Plaut, D.C.: Experiments on Learning by Back Propagation. Technical Report CMU-CS-86-126. Department of Computer Science Carnegie-Mellon University (1986) |
| [38] | Werbos, P.: Beyond regression: new tools for prediction and analysis in the behavioral sciences. Ph.D. dissertation, Harvard University (1974) |
| [39] | Rumelhart, DE; Hinton, GE; Williams, RJ, Learning representations by back-propagating errors, Nature, 323, 6088, 533-536 (1986) · Zbl 1369.68284 · doi:10.1038/323533a0 |
| [40] | Hochreiter, S.; Schmidhuber, J., Long short-term memory, Neural Comput., 9, 8, 1735-1780 (1997) · doi:10.1162/neco.1997.9.8.1735 |
| [41] | Mann, ME; Woodruff, JD; Donnelly, JP; Zhang, Z., Atlantic hurricanes and climate over the past 1,500 years, Nature, 460, 7257, 880-883 (2009) · doi:10.1038/nature08219 |
| [42] | Elsner, JB, Tracking hurricanes, Bull. Am. Meteorol. Soc., 84, 3, 353-356 (2003) · doi:10.1175/BAMS-84-3-353 |
| [43] | Kalman, RE, A new approach to linear filtering and prediction problems, J. Basic Eng., 82D, 1, 35-45 (1960) · doi:10.1115/1.3662552 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
