A United Nations investigation into data collected from vessels' AIS has found many potential uses including ways to estimate carbon emissions and manage risks to ships, cargo and crews.

The AIS Big Data Hackathon was designed to highlight the capabilities of the UN’s Global AIS Platform which contains 3.6 terabytes of real-time and historical data on ship location, speed, and type from December 2018 onwards.

International effort

Run by the United Nations Statistics Division, along with UNCTAD, UN Global Pulse, Marine Traffic, and CCRi, involved 17 teams selected from 43 applicants from around the world.

Three commercial and three student teams were judged to have come up with top solutions. The overall top-ranked participant, Blue Carbon, has been invited to send a team member to the UN World Data Forum in Bern, Switzerland, in 2021.

Team Blue Carbon, a cross-disciplinary group of Wartsila employees from four countries, came first with a global map of estimated shipping emissions, visualised in an easy-to-use dashboard.

Using the European Union's Monitoring, Reporting, and Verification of CO2 emissions (MRV) dataset, Blue Carbon estimated the geographic distribution of emissions according to vessel locations and activity. Using a machine learning model, they created an interactive map that provides granular information on areas with high emissions, such as shipping lanes and busy ports.

The map displays aggregated emission concentrations at various zoom levels, enabling global and country-specific visualisations of shipping emissions for different time periods. It also makes possible the removal of shipping-related “noise” from external estimates of regional emissions.

Second overall was Team Data Caliber Group, which generated AIS-based transit indicators for the Panama and Suez canals that can signal the health of international trade by using a reduced sample of shipping data.

Team Data Caliber’s members from academia, industry, and government from Panama, Egypt and Norway also established a framework for just-in-time arrival and efficiency enhancement policies to reduce vessel emissions and waiting and transit times through the canals.

Team Barents Sea, which came third, redefined key port performance indicators that are usually heterogeneous, delayed, and not easily accessible.

It estimated real-time throughput of ports and proposed a congestion indicator for monitoring actual congestion levels. They also built a connectivity index at the port level, using traffic characteristics and network factors that proved 95% accurate when validated against real data.

Coronavirus forces

First among the students, Team DogCat used AIS data to analyse the impact of Covid-19 on economic and social factors, including offshore stockpiling, container and bulk shipping.

The dry bulk research, focused on capesizes and VLOCs, found no significant changes in iron ore trade patterns between the largest export and import countries, Australia and China, during the pandemic. But coal was more susceptible to the influence of Covid-19 with the largest decrease seen in the trade between Indonesia and India.

Second-placed Team Fraunhofer CML investigated predicted correlations between reduced vessel movements in the North and Baltic seas and stock-market values of companies in Northern Germany during the pandemic.

The team reported that it did not find a correlation between more vessels being anchored in 2020 than 2019 with a resultant lower flow of goods and an expected reduction in stock values of German companies. Further investigation was needed, it concluded.

Third among the students was Team Deep Water, which designed an AIS and external data monitoring tool to analyse and manage risks affecting ships, crew, cargo and health. These included probabilities a ship will generate pollution, be associated with poor mental health among passengers or crew, experience weather-related cargo damage or incubate disease.