Abstract
The paper aims to forecast the Philippine storm frequencies using nonlinear Poisson autoregressive model with exogenous variables. The nonlinearity is defined by its kernel which is an artificial neural network (ANN) with one hidden layer and two output neurons, and is trained to simultaneously forecast two semesters ahead for a given input. Furthermore, the covariates studied were the Average Sea Surface Temperatures in the NINO3.4 region (5∘− 5∘S,170∘− 120∘W) and the Average Sea Surface Temperatures in the eastern pole (0∘− 10∘S,90∘− 110∘E) of the Dipole Mode Index. The data, taken from the Japan Meteorological Agency’s Regional Specialized Meteorological Center with time points running from 1950 to October 2021, is modeled at a semester-level granularity. The estimation is done using maximum likelihood estimation by minimizing the negative log-likelihood function. Furthermore, Bayesian hyper-parameter optimization was used to tune the model across different activation functions, number of hidden neurons, training optimizers, and train and validation splits. Lastly, the best model from the hyper-parameter optimization was then compared to univariate Poisson autoregressive model (and its Bayesian counterpart) and Negative Binomial Autoregressive model. The proposed model captures well the characteristics of the data both in terms of the point forecast and the associated uncertainties.
Similar content being viewed by others
Data availability
The RSMC Best Track Data can be downloaded here: https://www.jma.go.jp/jma/jma-eng/jma-center/rsmc-hp-pub-eg/besttrack.html
References
Abadi M, Agarwal A, Barham P et al (2015) TensorFlow: large-scale machine learning on heterogeneous systems. https://www.tensorflow.org/, software available from tensorflow.org
Asaad AAB (2021) Circular characteristics of the philippine storm tracks. Spatial Information Research https://doi.org/10.1007/s41324-021-00415-4
Asaad AAB (2022) Bayesian log-linear Poisson autoregressive model. 15th National Convention on Statistics, Quezon City, Philippines, https://psa.gov.ph/sites/default/files/kmcd/Bayesian_Log_Linear_Poisson_Autoregressive_Model_0.pdf
Bezanson J, Edelman A, Karpinski S et al (2017) Julia: a fresh approach to numerical computing. SIAM Rev 59(1):65–98. https://doi.org/10.1137/141000671
Blanc E, Strobl E (2016) Assessing the impact of typhoons on rice production in the Philippines. J Appl Meteorol Climatol 55 (4):993–1007. https://doi.org/10.1175/JAMC-D-15-0214.1https://journals.ametsoc.org/view/journals/apme/55/4/jamc-d-15-0214.1.xml
Cassidy RM (1964) Annual typhoon report. Guam, Mariana Islands: Fleet Weather Central/Joint Typhoon Warning Center. Guam, Mariana Islands, https://www.metoc.navy.mil/jtwc/products/atcr/1964atcr.pdf. Accessed 31 Dec 2022
Chand SS, Walsh KJE, Chan JCL (2010) A Bayesian regression approach to seasonal prediction of tropical cyclones affecting the Fiji region. J Climate 23(13):3425–3445. https://doi.org/10.1175/2010JCLI3521.1
Choi KS, Moon JY, Kim DW et al (2010) Seasonal prediction of tropical cyclone genesis frequency over the western North Pacific using teleconnection patterns. Theor Appl Climatol 100:191–206. https://doi.org/10.1007/s00704-009-0182-1
Christou V, Fokianos K (2014) Quasi-likelihood inference for negative binomial time series models. J Time Ser Anal 35(1):55–78. https://doi.org/10.1111/jtsa.12050, https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12050
Dillon JV, Langmore I, Tran D et al (2017) Tensorflow distributions. arXiv:1711.10604
Dozat T (2016) Incorporating Nesterov momentum into Adam. https://openreview.net/pdf/OM0jvwB8jIp57ZJjtNEZ.pdf. Accessed 3 January 2022
Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12(61):2121–2159. http://jmlr.org/papers/v12/duchi11a.html
Elsaraiti M, Merabet A (2021) A comparative analysis of the ARIMA and LSTM predictive models and their effectiveness for predicting wind speed. Energies 14(20). https://doi.org/10.3390/en14206782, https://www.mdpi.com/1996-1073/14/20/6782
Fallah N, Gu H, Mohammad K et al (2009) Nonlinear Poisson regression using neural networks: a simulation study. Neural Comput Appl 18(8):939. https://doi.org/10.1007/s00521-009-0277-8
Fan K (2007) New predictors and a new prediction model for the typhoon frequency over western North Pacific. Sci China Ser D Earth Sci 50(8):1417–1423. https://doi.org/10.1007/s11430-007-0105-x
Fan K, Wang H (2009) A new approach to forecasting typhoon frequency over the western North Pacific. Weather Forecast 24(4):974–986. https://doi.org/10.1175/2009WAF2222194.1
Fokianos K, Tjøstheim D (2011) Log-linear Poisson autoregression. J Multivar Anal 102 (3):563–578. https://doi.org/10.1016/j.jmva.2010.11.002
Fokianos K, Rahbek A, Tjøstheim D (2009) Poisson autoregression. J Am Stat Assoc 104 (488):1430–1439. https://doi.org/10.1198/jasa.2009.tm08270
Hinton G, Srivasta N, Swersky K (2012) RMSprop. http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf. Accessed 3 January2022
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Huang H, Jiang M, Ding Z et al (2019) Forecasting emergency calls with a Poisson neural network-based assemble model. IEEE Access 7:18,061–18,069. https://doi.org/10.1109/ACCESS.2019.2896887
Ihaka R, Gentleman R (1996) R: A language for data analysis and graphics. J Comput Graph Stat 5(3):299–314. https://doi.org/10.1080/10618600.1996.10474713
Kendall A, Gal Y (2017) What uncertainties do we need in Bayesian deep learning for computer vision?. In: Proceedings of the 31st international conference on neural information processing systems, NIPS’17. Curran Associates Inc., Red Hook, pp 5580–5590
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: Bengio Y, LeCun Y (eds) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. arXiv:1412.6980
Lagmay AMF, Agaton RP, Bahala MAC et al (2015) Devastating storm surges of typhoon Haiyan. Int J Disaster Risk Reduction 11:1–12. https://doi.org/10.1016/j.ijdrr.2014.10.006
Liboschik T, Fokianos K, Fried R (2017) tscount: an R package for analysis of count time series following generalized linear models. J Stat Softw 82(5):1–51. https://doi.org/10.18637/jss.v082.i05. https://www.jstatsoft.org/index.php/jss/article/view/v082i05
Lim B, Arık SO, Loeff N et al (2021) Temporal fusion transformers for interpretable multi-horizon time series forecasting. Int J Forecast 37(4):1748–1764. https://doi.org/10.1016/j.ijforecast.2021.03.012.https://www.sciencedirect.com/science/article/pii/S0169207021000637
Magee AD, Kiem AS, Chan JCL (2021) A new approach for location-specific seasonal outlooks of typhoon and super typhoon frequency across the Western North Pacific region. Sci Rep 11:19,439. https://doi.org/10.1038/s41598-021-98329-6
McDonnell KA, Holbrook NJ (2004a) A Poisson regression model approach to predicting tropical cyclogenesis in the Australian/Southwest Pacific Ocean region using the SOI and saturated equivalent potential temperature gradient as predictors. Geophys Res Lett 31(20). https://doi.org/10.1029/2004GL020843
McDonnell KA, Holbrook NJ (2004b) A Poisson regression model of tropical cyclogenesis for the Australian–Southwest Pacific Ocean region. Weather Forecast 19(2):440–455. https://doi.org/10.1175/1520-0434(2004)019<0440:APRMOT>2.0.CO;2
McMahan HB (2011) Follow-the-regularized-leader and mirror descent: equivalence theorems and l1 regularization. In: International conference on artificial intelligence and statistics
Montesinos-López OA, Montesinos-López JC, Singh P et al (2020) A multivariate Poisson deep learning model for genomic prediction of count data. G3 GenesGenomes Genetics 10(11):4177–4190. https://doi.org/10.1534/g3.120.401631
Muirhead RJ (2005) Aspects of multivariate statistical theory. Wiley, Hoboken
Nath S, Kotal S, Kundu P (2015) Seasonal prediction of tropical cyclone activity over the North Indian Ocean using the neural network model. Atmósfera 28(4):271–281. https://doi.org/10.20937/ATM.2015.28.04.06
Oreshkin BN, Carpov D, Chapados N et al (2020) N-beats: neural basis expansion analysis for interpretable time series forecasting. In: International conference on learning representations. https://openreview.net/forum?id=r1ecqn4YwB
Robbins H, Monro S (1951) A stochastic approximation method. Ann Math Stat 22(3):400–407. https://doi.org/10.1214/aoms/1177729586
Rodrigo H, Tsokos C (2020) Bayesian modelling of nonlinear Poisson regression with artificial neural networks. J Appl Stat 47(5):757–774. https://doi.org/10.1080/02664763.2019.1653268
Rüttgers M, Lee S, Jeon S et al (2019) Prediction of a typhoon track using a generative adversarial network and satellite images. Sci Rep 9(1). https://doi.org/10.1038/s41598-019-42339-y
Seriño M N V, Cavero JA, Cuizon J et al (2021) Impact of the 2013 super typhoon Haiyan on the livelihood of small-scale coconut farmers in Leyte Island, Philippines. Int J Disaster Risk Reduction 52:101,939. https://doi.org/10.1016/j.ijdrr.2020.101939
Van Rossum G, Drake FL (2009) Python 3 reference manual CreateSpace, Scotts Valley, CA
Wang QA, Wang CB, Ma ZG et al (2022) Bayesian dynamic linear model framework for structural health monitoring data forecasting and missing data imputation during typhoon events. Struct Health Monit 21(6):2933–2950. https://doi.org/10.1177/14759217221079529
Werner A, Holbrook NJ (2011) A Bayesian forecast model of Australian region tropical cyclone formation. J Climate 24(23):6114–6131. https://doi.org/10.1175/2011JCLI4231.1
Yi CJ, Suppasri A, Kure S et al (2015) Storm surge mapping of typhoon Haiyan and its impact in Tanauan, Leyte, Philippines. Int J Disaster Risk Reduction 13:207–214. https://doi.org/10.1016/j.ijdrr.2015.05.007.https://www.sciencedirect.com/science/article/pii/S2212420915300078
Zhang X, Zhong S, Wu Z et al (2018) Seasonal prediction of the typhoon genesis frequency over the western North Pacific with a Poisson regression model. Climate Dyn 51:4585–4600. https://doi.org/10.1007/s00382-017-3654-5
Zhang YM, Wang H, Mao JX et al (2021) Probabilistic framework with Bayesian optimization for predicting typhoon-induced dynamic responses of a long-span bridge. J Struct Eng 147(1):04020,297. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002881
Zhang YM, Wang H, Bai Y et al (2022) Bayesian dynamic regression for reconstructing missing data in structural health monitoring. Struct Health Monit 21(5):2097–2115. https://doi.org/10.1177/14759217211053779
Zhu F (2011) A negative binomial integer-valued GARCH model. J Time Ser Anal 32(1):54–67. https://doi.org/10.1111/j.1467-9892.2010.00684.x
Acknowledgements
The author would like to acknowledge the reviewers for their valuable comments and suggestions which have helped in improving the paper.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interests
The author declares no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Asaad, AA.B. Multi-step forecasting of the Philippine storm frequencies using Poisson neural network. Theor Appl Climatol 152, 293–305 (2023). https://doi.org/10.1007/s00704-023-04394-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00704-023-04394-4