An pipeline for generating additional AIS features to existing AIS message streams
Open Data Sources of AIS messages used in pipeline:
Sören Dethlefsen
Supervised by Mirjam Bayer
- Data imported into SQL database
- Deltas of time passed and distance travelled between consequetive AIS massege per vessel
- Average time computed based on previously computed values
- Unrealistic values removed based on location and speed. (Thresholds can optionally be adapted when running pipeline)
- Water depth added to every AIS message
- Distance to shore appended if not entailed using GFW dataset or tif-file
- Anchorage detection performed based on distance to shore, stationarity and speed. (Thresholds can optionally be adapted when running pipeline)
- Full trajectoriesof individual vessels split into trips
- Data exported as csv containing all additional features
This pipeline was presented at the eScience Conference in Limassol, Cyprus in October 9-13, 2023. The collateral poster paper contains more details on the features computed in this pipeline.
Bayer, M., Dethlefsen, S., Fry, T., & Kröger, P. (2023, October). Enhancing AIS Vessel Trajectories via Trip Detection. In 2023 IEEE 19th International Conference on e-Science (e-Science) (pp. 1-2). IEEE.