Liu, J., 2020. Prediction method of ship's track based on mathematical model. In: Li, L. and Huang, X. (eds.), Sustainable Development in Coastal Regions: A Perspective of Environment, Economy, and Technology. Journal of Coastal Research, Special Issue No. 112, pp. 379-382. Coconut Creek (Florida), ISSN 0749-0208.
Real-time and accurate acquisition of ship navigation dynamic information plays an important role in maritime traffic research and management, and ship intelligent collision avoidance. This paper proposes to convert ship automatic identification system (AIS) data into navigation dynamics time series data for training and testing of LSTM network. The prediction results are compared with the prediction results of the traditional track estimation algorithm and the BP (back propagation) neural network method. The results prove that the ship navigation dynamic prediction model based on the mathematical model has high accuracy, strong robustness and good versatility. Features. The prediction results can provide a reference for the supervision of the ship traffic management center, and have high practical application value in early warning of ship collisions and groundings.