Open Data Science Europe Workshop 2021

A fleet of more than 50.000 cargo ships worldwide has an enormous demand for energy resulting in considerable emissions. According to the 4th International Maritime Organization (IMO) global greenhouse gas (GHG) study, maritime transport emitted around 1,056 million tonnes of CO2 in 2018 and was responsible for about 2.9% of the global anthropogenic CO2 emissions. While the emissions per tonne and nautical mile have been reduced by almost 30% in the last decade, the overall emissions of cargo ships increased by more than 10% (up to 30% in some models) due to the growing demand. The IMO has committed itself to reducing the amount of global pollutant emissions by 50% in 2050 compared to 2008.

An utmost important factor of the energy demand of a cargo ship is the state of environment it has to traverse to get from its origin to its destination. Among wind, waves and currents, salinity and temperature also influence a ship’s resistance which naturally also depends on the dimensions and hydrodynamics of the ship itself. In the national research project MariData, an energy optimised routing will be developed which takes the environmental conditions into account to considerably contribute to the energy efficiency of global cargo ships.

This multicriterial optimisation challenge can only be tackled with the help of a tailored Geo Data Cube (GDC) and recent developments in efficient machine learning (ML) algorithms. Relevant data and forecasts on a global scale are available through e.g. the Copernicus Marine Environmental Monitoring Service (CMEMS) or the Global Forecasting System (GFS) of the National Centers for Environmental Prediction (NCEP). Additional constraints like impassable areas, bathymetry and alike are also provided through a set of different services. While the data sets are mostly made available through open standardized interfaces (e.g. Web Map or Coverage Services), this is not sufficient for a tight integration with a challenging ML approach.

Our presentation will illustrate the maritime transport use-case and its requirements on a spatial information infrastructure. We will present the design of our open source Geoplatform including a GDC harmonising all the necessary gridded data, its API to dynamically provide relevant data per ship and how we integrate the Python based routing approach.