Experience of Forecasting Maritime Traffic Intensity Based on Computer Analysis of Online Marine Charts of the Panama Canal
Abstract
The article discusses the results of forecasting time series compiled from the number of ships in the Panama Canal based on the use of primary information on the number of ships that passed through the selected sea straits during one hour in the period from March 1 to March 31, 2021. The information necessary for compiling the discussed time series was extracted automatically using a software tool developed by the authors from publicly available online nautical charts posted on the Internet. The obtained time series compiled from the number of sea vessels are presented. A time series forecasting technique is described that integrates formal forecasting methods and the Data Assimilation method. A comparative analysis of the forecasting accuracy of selected time series obtained using formal time series models (AR, etc.) and the integration technique is performed. It is demonstrated that the forecasting accuracy based on the integration of formal time series forecasting methods and the DA method is higher than the similar value in the case of forecasting based on an AR model of a time series of any order.
Full Text:
PDF (Russian)References
Ship & Container Tracking – Vessel Finder [Online]. Available: https://www.vesselfinder.com
AIS Marine Traffic: Global Ship Tracking Intelligence [Online]. Available: https://www.marinetraffic.com
Otslezhivanie sudov po vsemu miru v real'nom vremeni. Monitoring. Poisk. Dannye AIS [Online]. Available: https://www.shippingexplorer.net/ru
Grammatchikov A. Pandemija, kitajskij faktor i sujeckij krizis // Jekspert 2021 #15 (1202). S 5-10
Kuzhbanova E. A., Porshnev S. V. Opyt analiza informacii o dvizhenii morskih sudov, izvlechennoj iz jelektronnyh online morskih kart // International Journal of Open Information Technologies. 2021. #4
Timoshenkova Ju. S., Porshnev S. V., Safiullin N. T. Metodika Integracii Formal'nyh Metodov Prognozirovanija Vremennyh Rjadov v Data Assimilation // International Journal of Open Information Technologies. 2022. # 4 (10). C. 15–23.
Timoshenkova Ju. S., Porshnev S. V., Safiullin N. T. Algoritmicheskoe i programmnoe obespechenie metodiki integracii formal'nyh metodov prognozirovanija vremennyh rjadov i metoda assimiljacii dannyh / Ju. S. Timoshenkova, S. V. Porshnev, N. T. Safiullin, Nauchno-tehnicheskoe izdatel'stvo «Gorjachaja linija-Telekom»,.
Bocquet M. Introduction to the principles and methods of data assimilation in geosciences // Notes de cours, École des Ponts ParisTech. 2014.
Box G. E. [и др.]. Time series analysis: forecasting and control / G. E. Box, G. M. Jenkins, G. C. Reinsel, G. M. Ljung, John Wiley & Sons, 2015.
Demuth H. B. [и др.]. Neural network design / H. B. Demuth, M. H. Beale, O. De Jess, M. T. Hagan, Martin Hagan, 2014.
Evensen G. Data assimilation: the ensemble Kalman filter / G. Evensen, Springer Science & Business Media, 2009.
Houtekamer P. L., Mitchell H. L. Data assimilation using an ensemble Kalman filter technique // Monthly Weather Review. 1998. № 3 (126). C. 796–811.
Kalnay E. Atmospheric modeling, data assimilation and predictability / E. Kalnay, Cambridge university press, 2003.
Kamruzzaman J., Begg R., Sarker R. Artificial neural networks in finance and manufacturing / J. Kamruzzaman, R. Begg, R. Sarker, IGI Global, 2006.
Moradkhani H. [и др.]. Uncertainty assessment of hydrologic model states and parameters: Sequential data assimilation using the particle filter // Water resources research. 2005. № 5 (41).
Morariu N., Iancu E., Vlad S. A neural network model for time series forecasting // Romanian journal of economic forecasting. 2009. № 4 (12). C. 213–223.
Muzaffar S., Afshari A. Short-term load forecasts using LSTM networks // Energy Procedia. 2019. (158). C. 2922–2927.
Nerger L. [и др.]. SANGOMA: Stochastic Assimilation for the Next Generation Ocean Model Applications EU FP7 SPACE-2011-1 project 283580.
Timoshenkova Y., Porshnev S., Safiullin N. Method of Integration of Formal Forecasting Methods into Data Assimilation on the Example of Autoregressive Time Series Yekaterinburg, Russian Federation: IEEE, 2022.C. 224–227.
Timoshenkova Y. S., Safiullin N. T., Porshnev S. V. Application of Data Assimilation Algorithms Based on Kalman Ensemble Filters for the Lorenz Attractor CEUR-WS, 2018.C. 82–87.
Yulia T., Sergey P., Nikolai S. On the possibility of correction of the forecasting of the Lorenz attractor dynamic characteristics using experimental data and data assimilation IOP Publishing, 2018.C. 012004.
Zhang G. P. Time series forecasting using a hybrid ARIMA and neural network model // Neurocomputing. 2003. (50). C. 159–175.
Yang Zhou, Winnie Daamen, Tiedo Vellinga, Serge Hoogendoorn,Review of maritime traffic models from vessel behavior modeling perspective,Transportation Research Part C: Emerging Technologies,Volume 105, 2019, Pages 323-345, ISSN 0968-090X,https://doi.org/10.1016/j.trc.2019.06.004
Y. Nie, K. Liu, X. Xin & Q. Yu A Novel Through Capacity Model for One-way Channel Based on Characteristics of the Vessel Traffic Flow // TransNav the International Journal on Marine Navigation and Safety of Sea Transportation - 2017 - 11(3) С:495-502 DOI:10.12716/1001.11.03.16
Muirhead, J.R., Minton, M.S., Miller, W.A. and Ruiz, G.M. (2015), Projected effects of the Panama Canal expansion on shipping traffic and biological invasions. Diversity Distrib., 21: 75-87. https://doi.org/10.1111/ddi.12260
Refbacks
- There are currently no refbacks.
Abava Кибербезопасность ИБП для ЦОД
ISSN: 2307-8162