Predicting availability of berths in ports





Predictive modeling, machine learning, knowledge technology

Rijkswaterstaat is the government organization responsible for the design, construction, management and maintenance of the main infrastructure facilities in the Netherlands. One of the services of Rijkswaterstaat is ‘Blauwe Golf Verbindend‘; real-time data for inland shipping on open bridges and available berths in ports. Information that allows skippers to better plan their journey and arrival, with less inconvenience and annoyance and without unnecessary fuel consumption and exhaust emissions.

In order to better serve inland shipping, Rijkswaterstaat wants to be able to indicate an prediction about the availability of berths in a certain area over a certain period. Numerous factors must be taken into account, such as the ship type, the size of the ship, the cargo, the dimensions of the berth, the presence of extra facilities at the berth, etc.

Commissioned by Rijkswaterstaat, Traffic and Water Management (VWM) and the Central Information Service (CIV), Bolesian developed a pilot system in which various forecasting models were compared. These models were based on both historical data and the expertise of inland shipping experts. The operation of the forecasting models in various scenarios can be viewed here (in Dutch). The pilot system is using Bolesian’s Geonizer for intelligent geographical data processing.