Maritime Data Analytics
Powerful algorithms feeding on different types of data sources that improve the business intelligence at the port, enhancing the planning department efficiency with machine learning methods towards port digitalisation.
Unique Value Proposition:
The Maritime Data Analytics (MDA) is an ICT toolset based on powerful algorithms feeding on different types of data sources (AIS, FAL forms and smart cameras) that improve the business intelligence at the port from the traffic at the sea (enhancing ETA/ETD and other optimizations of vessel traffic and manouvering) and on the road (forecasting and avoiding congestion at the port gate and throughout the city using better the parking availability) with machine learning methods.
PIXEL is using AI-based algorithms capable to forecast traffic at sea (turnaround time from FAL forms, and vessel short-term ETA based on AIS data) and on the road (managing parking area and avoiding congestion). It improves ETA/ETD, helping to plan arrival/departure times to minimize congestion at the port, optimising costs/gains, and can improve resources and monitor waiting times for vessel voyage, as well as port operation resources; and identify unusual behaviour in the port area, improving port/shipping operations.
Schema of the product:
1. Allows for further insight on the operations held in the overall maritime ecosystem around the port and on the road to the port.
2. Allows to compare economic and environmental time impacts of different transport mode improving the planning of port transport operations monitoring the environmental impacts.
3. Can support a shared planning of freight transport with business operators in order to reduce the impact on hinterland and environment.
1. Improves the capacity of planning of port operators, business operators and policy makers to reach economic growth and to reduce the environmental impact.
2. Utilizes sophisticated algorithms to forecast ETA/ETD, helping to plan arrival/departure times to minimize congestion at the port, optimising costs/gains.
3. Reduce the congestion events in the Port area and of the hinterland, by an interoperability with other Regional node.
Keywords: intermodal transport, traffic optimization, multimodality, queue conjestion prevention, predictive algorithms, data insights, machine learning, ETA, ETD, AIS.