Analysis of Automatic Identification System (AIS) data to understand shipping and ports

The off-course project explores the operation, use and relationships between ports in the UK at a macro level and the behaviour and operational characteristics of ships at a micro level. Specifically, we explored ship travelling behaviours, traffic at ports and related factors, port capacity utilisation, national and international port relationships and inbound ship delays.

Team members

  • Christopher Bonham
  • Alex Noyvirt
  • Jacob Thomas
  • Ioannis Tsalamanis
  • Sonia Williams

The need

The maritime freight industry is of critical importance to the economic output of the UK, with almost half a billion tonnes of freight being handled by UK ports in 2016. The Freight Transportation Association estimate that delays on both side of the Channel cost the UK logistics industry £750,000 a day. As the demands upon shipping freight are likely to increase in the future, a more in-depth understanding of the UK maritime shipping industry becomes increasingly more important.

This project explores the operation, use and relationships between ports in the UK at a macro level and the behaviour and operational characteristics of ships at a micro level, specifically:

  • national and international relationships
  • traffic at ports and related factors
  • inbound delays
  • capacity utilisation

Two sources of data are utilized:

Impact

The main outputs of this project are: • processing pipeline of big data containing location of ships and reports containing itinerary information • port statistics based on several criteria • port relationships between UK and international ports • classification of ship travelling behaviour • prediction models for delayed arrivals of freight ships

Data science

• Development of Scala functions to decode, sort, filter and extract AIS messages. • Visualisations of port statistics and network analysis. • Unsupervised machine learning algorithms to classify the ships’ moving behaviour. • Supervised machine learning algorithms to predict if a freight ship is going to arrive delayed.

Stakeholders

  • Maritime and Coastguard Agency (MCA)
  • Department for International Trade (DIT)

Code and outputs

Report on main website • GitHub public repository

Delivery

  • September 2017 Project started
  • June 2018 Project finished

Further information

Please contact datasciencecampus@ons.gov.uk for more information.

Updates

  • No updates yet.

Notes

This page has been automatically generated. Click here to download this project description as a pdf or click here to download as a word document.


Updated