Tropical Cyclone Track Prediction with an Encoding-to-Forecasting Deep Learning Model

Pingping Dong aCollege of Economics and Management, Tongji University, Shanghai, China
bShanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China

Search for other papers by Pingping Dong in
Current site
Google Scholar
PubMed
Close
https://orcid.org/0000-0003-3138-4900
,
Jie Lian bShanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China

Search for other papers by Jie Lian in
Current site
Google Scholar
PubMed
Close
,
Hui Yu cShanghai Typhoon Institute, China Meteorological Administration, Shanghai, China

Search for other papers by Hui Yu in
Current site
Google Scholar
PubMed
Close
,
Jianguo Pan bShanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China

Search for other papers by Jianguo Pan in
Current site
Google Scholar
PubMed
Close
,
Yuping Zhang bShanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University, Shanghai, China

Search for other papers by Yuping Zhang in
Current site
Google Scholar
PubMed
Close
, and
Guomin Chen cShanghai Typhoon Institute, China Meteorological Administration, Shanghai, China

Search for other papers by Guomin Chen in
Current site
Google Scholar
PubMed
Close
Restricted access

Abstract

Recently, with the accumulation of remote sensing data, the traditional tropical cyclone (TC) track prediction methods (e.g., dynamic methods and statistical methods) have limitations in prediction efficiency and accuracy when dealing with a large amount of data. However, deep learning methods begin to show their advantages to capture the complex spatiotemporal features in high-dimensional data. The task of TC track prediction based on remote sensing images can be formulated as a spatiotemporal sequence-to-sequence problem. Therefore, a novel encoding-to-forecasting model with convolutional long short-term memory (ConvLSTM) and spatial attention network (SAN-EFSModel) was proposed to predict TC tracks in this paper, which can fully extract the long-term spatial and temporal features. The proposed model was evaluated on the real remote sensing images in the western North Pacific Ocean to forecast 24-h TC tracks. Compared with ECMWF-HRES model and NCEP-GFS model, the proposed method has a better prediction accuracy in the testing set with an average position error about 30 km less. Compared with the deep learning methods, the proposed method also has the best performance.

Significance Statement

Tropical cyclones have a great impact on human life and natural environment due to their high frequency of occurrence, heavy degree of harm, wide impact range, and long disaster chain. In this article, we propose an encoding-to-forecasting model with convolutional long short-term memory (ConvLSTM) and spatial attention network (SAN-EFSModel) to predict tropical cyclone tracks, in which the SAN module and the convolution module of ConvLSTM have the ability to extract spatial features, and the long short-term memory (LSTM) module of ConvLSTM can extract temporal features from remote sensing images and tropical cyclone tracks. The results show that the average position error (APE) of our proposed method has about 30% improvement in a 24-h forecast compared with prevailing numerical weather prediction models.

© 2022 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Jie Lian, lianjie@shnu.edu.cn

Abstract

Recently, with the accumulation of remote sensing data, the traditional tropical cyclone (TC) track prediction methods (e.g., dynamic methods and statistical methods) have limitations in prediction efficiency and accuracy when dealing with a large amount of data. However, deep learning methods begin to show their advantages to capture the complex spatiotemporal features in high-dimensional data. The task of TC track prediction based on remote sensing images can be formulated as a spatiotemporal sequence-to-sequence problem. Therefore, a novel encoding-to-forecasting model with convolutional long short-term memory (ConvLSTM) and spatial attention network (SAN-EFSModel) was proposed to predict TC tracks in this paper, which can fully extract the long-term spatial and temporal features. The proposed model was evaluated on the real remote sensing images in the western North Pacific Ocean to forecast 24-h TC tracks. Compared with ECMWF-HRES model and NCEP-GFS model, the proposed method has a better prediction accuracy in the testing set with an average position error about 30 km less. Compared with the deep learning methods, the proposed method also has the best performance.

Significance Statement

Tropical cyclones have a great impact on human life and natural environment due to their high frequency of occurrence, heavy degree of harm, wide impact range, and long disaster chain. In this article, we propose an encoding-to-forecasting model with convolutional long short-term memory (ConvLSTM) and spatial attention network (SAN-EFSModel) to predict tropical cyclone tracks, in which the SAN module and the convolution module of ConvLSTM have the ability to extract spatial features, and the long short-term memory (LSTM) module of ConvLSTM can extract temporal features from remote sensing images and tropical cyclone tracks. The results show that the average position error (APE) of our proposed method has about 30% improvement in a 24-h forecast compared with prevailing numerical weather prediction models.

© 2022 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Jie Lian, lianjie@shnu.edu.cn
Save
  • Alemany, S., J. Beltran, A. Perez, and S. Ganzfried, 2019: Predicting hurricane trajectories using a recurrent neural network. Proc. Conf. AAAI Artif. Intell., 33, 468475, https://doi.org/10.1609/aaai.v33i01.3301468.

    • Search Google Scholar
    • Export Citation
  • Ali, M. M., C. M. Kishtawal, and S. Jain, 2007: Predicting cyclone tracks in the North Indian Ocean: An artificial neural network approach. Geophys. Res. Lett., 34, 545559, https://doi.org/10.1029/2006GL028353.

    • Search Google Scholar
    • Export Citation
  • Bengio, Y., P. Simard, and P. Frasconi, 1994: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Network, 5, 157166, https://doi.org/10.1109/72.279181.

    • Search Google Scholar
    • Export Citation
  • Chen, R., X. Wang, W. Zhang, X. Zhu, A. Li, and C. Yang, 2019: A hybrid CNN-LSTM model for typhoon formation forecasting. GeoInformatica, 23, 375396, https://doi.org/10.1007/s10707-019-00355-0.

    • Search Google Scholar
    • Export Citation
  • Chung, J., C. Gulcehre, K. Cho, and Y. Bengio, 2015: Gated feedback recurrent neural networks. ICML′15: Proc. of the 32nd Int. Conf. on Machine Learning, Lille, France, International Machine Learning Society, 20672075, http://proceedings.mlr.press/v37/chung15.pdf.

  • Doyle, J. D., and Coauthors, 2014: Tropical cyclone prediction using coamps-tc. Oceanography, 27, 104115, https://doi.org/10.5670/oceanog.2014.72.

    • Search Google Scholar
    • Export Citation
  • Heming, J. T., and Coauthors, 2019: Review of recent progress in tropical cyclone track forecasting and expression of uncertainties. Trop. Cyclone Res. Rev., 8, 181218, https://doi.org/10.1016/j.tcrr.2020.01.001.

    • Search Google Scholar
    • Export Citation
  • Hochreiter, S., and J. Schmidhuber, 1997: Long short-term memory. Neural Comput., 9, 17351780, https://doi.org/10.1162/neco.1997.9.8.1735.

    • Search Google Scholar
    • Export Citation
  • Kim, S., H. Kim, J. Lee, S. Yoon, S. E. Kahou, K. Kashinath, and M. Prabhat, 2019a: Deep-hurricane-tracker: Tracking and forecasting extreme climate events. 2019 IEEE Winter Conf. on Applications of Computer Vision, Waikoloa, HI, IEEE, 17611769, https://doi.org/10.1109/WACV.2019.00192.

  • Kim, S., S. Park, S. Chung, J. Lee, Y. Lee, H. Kim, M. Prabhat, and J. Choo, 2019b: Learning to focus and track extreme climate events. 30th British Machine Vision Conf., Cardiff, United Kingdom, British Machine Vision Association, 11 pp.

  • Kingma, D. P., and J. Ba, 2014: Adam: A method for stochastic optimization. arXiv, 1412.6980, https://doi.org/10.48550/arXiv.1412.6980.

  • Knaff, J. A., and R. T. DeMaria, 2017: Forecasting tropical cyclone eye formation and dissipation in infrared imagery. Wea. Forecasting, 32, 21032116, https://doi.org/10.1175/WAF-D-17-0037.1.

    • Search Google Scholar
    • Export Citation
  • Knapp, K. R., M. C. Kruk, D. H. Levinson, H. J. Diamond, and C. J. Neumann, 2010: The International Best Track Archive for Climate Stewardship (IBTRACS) unifying tropical cyclone data. Bull. Amer. Meteor. Soc., 91, 363376, https://doi.org/10.1175/2009BAMS2755.1.

    • Search Google Scholar
    • Export Citation
  • Knapp, K. R., and Coauthors, 2011: Globally gridded satellite observations for climate studies. Bull. Amer. Meteor. Soc., 92, 893907, https://doi.org/10.1175/2011BAMS3039.1.

    • Search Google Scholar
    • Export Citation
  • Kordmahalleh, M. M., M. G. Sefidmazgi, A. Homaifar, and S. Liess, 2015: Hurricane trajectory prediction via a sparse recurrent neural network. Proc. of the Fifth Int. Workshop on Climate Informatics, Boulder, CO, NCAR, 2–3.

  • Li, Y., R. Yu, C. Shahabi, and Y. Liu, 2017: Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv, 1707.01926, https://doi.org/10.48550/arXiv.1707.01926.

    • Search Google Scholar
    • Export Citation
  • Lin, Z., M. Li, Z. Zheng, Y. Cheng, and C. Yuan, 2020: Self-attention convlstm for spatiotemporal prediction. Proc. Conf. AAAI Artif. Intell., 34, 11 53111 538, https://doi.org/10.1609/aaai.v34i07.6819.

    • Search Google Scholar
    • Export Citation
  • Mahmoud, H., and N. Akkari, 2016: Shortest path calculation: A comparative study for location-based recommender system. 2016 World Symp. on Computer Applications and Research, Cairo, Egypt, IEEE, 1–5, https://doi.org/10.1109/WSCAR.2016.16.

  • NOAA, 2017: National Hurricane Center forecast verification. Accessed 5 July 2020, https://www.nhc.noaa.gov/verification/verify6.shtml.

  • Pascanu, R., T. Mikolov, and Y. Bengio, 2013: On the difficulty of training recurrent neural networks. Proc. of the 30th Int. Conf. on Machine Learning, Atlanta, GA, International Machine Learning Society, 13101318, http://proceedings.mlr.press/v28/pascanu13.pdf.

  • Pineda, F. J., 1987: Generalization of back-propagation to recurrent neural networks. Phys. Rev. Lett., 59, 22292232, https://doi.org/10.1103/PhysRevLett.59.2229.

    • Search Google Scholar
    • Export Citation
  • Rüttgers, M., S. Lee, S. Jeon, and D. You, 2019: Prediction of a typhoon track using a generative adversarial network and satellite images. Sci. Rep., 9, 6057, https://doi.org/10.1038/s41598-019-42339-y.

    • Search Google Scholar
    • Export Citation
  • Shi, X., Z. Chen, H. Wang, D.-Y. Yeung, W.-K. Wong, and W.-c. Woo, 2015: Convolutional LSTM network: A machine learning approach for precipitation nowcasting. arXiv, 1506.04214, https://doi.org/10.48550/arXiv.1506.04214.

    • Search Google Scholar
    • Export Citation
  • Surgi, N., Q. Gopalkrishnan, R. Tuleya, and W. O’Connor, 2006: The hurricane WRF (HWRF): Addressing our nation’s next generation hurricane forecast problems. 27th Conf. on Hurricanes and Tropical Cyclone Meteorology, Monterey, CA, Amer. Meteor. Soc., 7A.2, https://ams.confex.com/ams/27Hurricanes/techprogram/paper_108536.htm.

  • Tran, D., L. Bourdev, R. Fergus, L. Torresani, and M. Paluri, 2015: Learning spatiotemporal features with 3D convolutional networks. Proc. of the IEEE Int. Conf. on Computer Vision (ICCV), Santiago, Chile, IEEE, 44894497, https://doi.org/10.1109/ICCV.2015.510.

  • Wang, F., M. Jiang, C. Qian, S. Yang, C. Li, H. Zhang, X. Wang, and X. Tang, 2017: Residual attention network for image classification. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Honolulu, HI, IEEE, 31563164, https://doi.org/10.1109/CVPR.2017.683.

  • Wang, Y.-f., W. Zhang, and W. Fu, 2011: Back propogation (BP)-neural network for tropical cyclone track forecast. 19th Int. Conf. on Geoinformatics, Shanghai, China, IEEE, 1–4, https://doi.org/10.1109/GeoInformatics.2011.5981095.

  • Wang, Y., M. Long, J. Wang, Z. Gao, and P. S. Yu, 2017: PredRNN: Recurrent neural networks for predictive learning using spatiotemporal LSTMs. Proc. of the 31st Int. Conf. on Neural Information Processing Systems, Long Beach, CA, NeurIPS, 879888.

  • Wang, Y., Z. Gao, M. Long, J. Wang, and S. Y. Philip, 2018: PredRNN++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. Proc. 35th Int. Conf. on Machine Learning, Stockholm, Sweden, International Machine Learning Society, 51235132, http://proceedings.mlr.press/v80/wang18b/wang18b.pdf.

  • Wang, Y., L. Jiang, M.-H. Yang, L.-J. Li, M. Long, and L. Fei-Fei, 2019: Eidetic 3D LSTM: A model for video prediction and beyond. Seventh Int. Conf. on Learning Representations , New Orleans, LA, ICLR, 14 pp., https://openreview.net/forum?id=B1lKS2AqtX.

    • Search Google Scholar
    • Export Citation
  • Woo, S., J. Park, J.-Y. Lee, and I. So Kweon, 2018: CBAM: Convolutional block attention module. Computer Vision—ECCV 2018, Lecture Notes in Computer Science, Vol. 11211, Springer, 319, https://doi.org/10.1007/978-3-030-01234-2_1.

    • Search Google Scholar
    • Export Citation
  • Yu, H., and L. Chen, 2019: Impact assessment of landfalling tropical cyclones: Introduction to the special issue. Front. Earth Sci., 13, 669671, https://doi.org/10.1007/s11707-019-0809-1.

    • Search Google Scholar
    • Export Citation
  • Yu, H., and Coauthors, 2022: Are we reaching the limit of tropical cyclone track predictability in the western North Pacific? Bull. Amer. Meteor. Soc., 103, E410E428, https://doi.org/10.1175/BAMS-D-20-0308.1.

    • Search Google Scholar
    • Export Citation
  • Zhang, S., and K. Nishijima, 2012: Statistics-based investigation on typhoon transition modeling. Seventh Int. Colloquium on Bluff Body Aerodynamics and Applications, Shanghai, China, International Association for Wind Engineering, 364373, http://www.iawe.org/Proceedings/BBAA7/S.Y.Zhang.pdf.

    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 1257 0 0
Full Text Views 1408 958 104
PDF Downloads 1195 771 109