Can AIS data be used to predict fish processing at Grieg Seafood Stjernelaks?
Abstract
This study investigates the potential of using Automatic Identification System(AIS) data to predict fish processing at Grieg Seafood Stjernelaks. The re-search involved creating and analyzing two processed datasets: Labeled Daysand Labeled Time Series. The Labeled Days dataset uses the Active label,indicating the days when fish processing occurred, while the Labeled Time Se-ries dataset uses the Direct label, indicating the specific times when fish wasdirectly delivered by relevant vessels. Machine learning techniques, includingfeature engineering, decision trees, random forests, and dynamic time warping,were used to analyze the AIS data.
The results of this study highlight that the Labeled Days baseline utilizingtemporal patterns to predict the activity status for Stjernelaks perform excellentin terms of Area Under the ROC Curve (AUC-ROC ) score. However, the bestmachine learning model, ’Rand RFE RF,’ outperforms the baseline by utilizingAIS data with an AUC-ROC score of 0.933. No model outperformed thebaseline for the Labeled Time Series dataset.
The study concludes that while AIS data shows promise in predicting if Stjer-nelaks is processing fish on any given day, it does not conclusively prove thatAIS can be used to predict fish processing at Grieg Seafood Stjernelaks. Theresearch faced limitations due to issues encountered with Kystdatahuset’s APIendpoint for fetching AIS data, and the scarcity of label data. These limitationsmay have affected the ability to fully answer the research question and shouldbe addressed in future research.ii