Shipment size is unavailable and important in AIS-based trade volume estimates. A method of shipment size estimates based on AIS (Automatic Identification System) data and BP neural network is proposed. The ship's length, width, designed draught, current draught and deadweight ton are input parameters, the actual shipment size of the ship is output value, and the BP neural network is trained to estimate the actual shipment size of the iron ore carriers. Then, the AIS data is used to calculate the iron ore trade volume in 2018. Compared with customs data, the annual error of import volume of China is less than 0.5%. The result shows that the proposed method is accurate and practical.


    Access

    Download


    Export, share and cite



    International Seaborne Trade

    Tamvakis, Michael | Wiley | 2012


    Seaborne Grains Trade Stagnates

    British Library Online Contents | 1992


    Downwards Trade in Seaborne Iron Ore Trade Held in Check

    British Library Online Contents | 1994


    Seaborne Trade Rises Again

    British Library Online Contents | 1997


    Seaborne Coal Trade - Slide Continues

    British Library Online Contents | 1994