Búgvi Benjamin Magnussen Búgvi Benjamin Magnussen

Búgvi Benjamin Magnussen

Maritime data scientist, researcher, and trained musician.

Specialist in maritime data science. Industrial PhD on vessel behaviour, published research, and the rest of the time a musician.

See my research Get in touch

About

I'm a data scientist working in the maritime domain. My industrial PhD, in collaboration with TORM, a Danish product tanker shipping company, is about vessel behaviour: where ships are heading, how to reconstruct their movement from sparse position reports, when they'll arrive, and general supply and demand trends in the tramp market.

I have a background in computer science and worked as a software engineer before becoming a data scientist. Before that I studied music at the University of Melbourne. I still play. I'm from the Faroe Islands, based in Copenhagen, and I also do consulting work on the side.

Experience

  1. 2021 — Present

    Data Scientist & Industrial PhD Fellow

    TORM

    Work spans both operational and commercial projects, such as route optimisation and strategic planning, covering the full pipeline from managing projects and stakeholders through to analysis and implementation.

  2. 2019 — Present

    Data Scientist Consultant

    FaroeSeaV

    Consulting work in the salmon aquaculture industry, covering data analysis, machine learning, and computer vision algorithms.

  3. 2018 — 2022

    Teaching Assistant

    IT University of Copenhagen

    Taught various courses, including Introduction to Database Design, Functional Programming, and Advanced Programming.

  4. 2021

    Analyst

    Netlight

    Focused on data migration and data verification.

  5. 2019 — 2021

    Software Engineer

    Cimco

    Worked on tooling software for CNC machines, leading a small team responsible for a tool manager application.

  6. 2018 — 2019

    Student Software Engineer

    Siteimprove

    Worked on Alfa, Siteimprove's accessibility engine.

Education

Research & Publications

Modelling Tramp Shipping Tonne-Miles in an Ever-Changing Market

16th Joint International Conference on Computational Logistics and EURO Mini Conference on Maritime Optimization and Logistics (ICCL 2025), Rotterdam, Netherlands, 8–10 Sept 2025 · Accepted / in press

The tonne-mile metric serves as a measure to proxy demand for commodity transport in tramp shipping, yet predicting it is challenging due to complex trade route interdependencies and a dynamic geopolitical landscape. This study proposes a methodology for predicting tonne-miles based on trade flow modelling. Leveraging country-level export and import data, we frame tonne-mile estimation as a variant of the Minimum-Cost Flow Problem (MCFP) tailored towards tramp shipping and construct a time-expanded flow network that integrates multiple datasets to capture trade relationships. To evaluate the methodology, we perform a series of experiments across four key Clean Petroleum Product (CPP) commodities, demonstrating the ability of the model to reconstruct tonne-miles over a four-year historical period with a 2.1% Mean Absolute Percentage Error (MAPE). Finally, we showcase our method's utility as a decision-support tool by estimating future tonne-miles under several market scenarios utilising projected country-level export and import data. The framework can be used to estimate tonne-miles per commodity segment both regularly and during disruptions, such as geopolitical tensions.

MATNEC: AIS data-driven environment-adaptive maritime traffic network construction for realistic route generation

Transportation Research Part C: Emerging Technologies, vol. 169, art. 104853 · 2024

In the context of the global maritime industry, which plays a vital role in international trade, navigating vessels safely and efficiently remains a complex challenge, especially due to the absence of structured road-like networks on the open seas. This paper proposes MATNEC, a framework for constructing a data-driven Maritime Traffic Network (MTN), represented as a graph that facilitates realistic route generation. Our approach, leveraging Automatic Identification System (AIS) data along with portcall and global coastline datasets, aims to address key challenges in MTN construction from AIS data observed in the literature, particularly the imprecise placement of network nodes and sub-optimal definition of network edges. At the core of MATNEC is a novel incremental clustering algorithm that is capable of intelligently determining the placement and distribution of the graph nodes in a diverse set of environments, based on several environmental factors. To ensure that the resulting MTN generates maritime routes as realistic as possible, we design a novel edge mapping algorithm that defines the edges of the network by treating the mapping of AIS trajectories to network nodes as an optimisation problem. Finally, due to the absence of a unified approach in the literature for measuring the efficacy of an MTN's ability to generate realistic routes, we propose a novel methodology to address this gap. Utilising our proposed evaluation methodology, we compare MATNEC with existing methods from literature. The outcome of these experiments affirm the enhanced performance of MATNEC compared to previous approaches.

DAISTIN: A Data-Driven AIS Trajectory Interpolation Method

Proceedings of the 18th International Symposium on Spatial and Temporal Data (SSTD '23), Calgary, AB, Canada, pp. 75–84 · 2023

The Automatic Identification System (AIS) provides global vessel positioning data used in a variety of maritime applications. However, AIS suffers from transmission signal gaps, which causes vessels to disappear from AIS records for prolonged periods and poses a major challenge for the use of AIS data. In this paper, we propose a novel Data-driven AIS Trajectory INterpolation method (DAISTIN) to address AIS signal gaps. DAISTIN first makes use of massive raw AIS data to delicately construct a graph that well represents vessel movements. Next, given a gap between two locations A and B in an AIS trajectory, DAISTIN searches the graph for the shortest path from A to B and uses the path to interpolate the vessel's whereabouts in between. To cope with large amounts of AIS data, we design a geometric sampling method for DAISTIN to select representative AIS data points for the graph construction. Finally, we design a postprocessing step for DAISTIN to fine-tune the quality of interpolated results. We conduct extensive experiments to compare DAISTIN with selected existing methods. The results verify the superiority of DAISTIN in terms of multiple performance metrics.

Destination Prediction of Oil Tankers Using Graph Abstractions and Recurrent Neural Networks

Computational Logistics (ICCL 2021), Lecture Notes in Computer Science vol. 13004, pp. 51–65 · 2021

Predicting the destination of vessels in the maritime industry is a problem that has seen sustained research over the last few years fuelled by an increase in the availability of Automatic Identification System (AIS) data. The problem is inherently difficult due to the nature of the maritime domain. In this paper, we focus on a subset of the maritime industry - the oil transportation business - which complicates the problem of destination prediction further, as the oil transportation market is highly dynamic. We propose a novel model, inspired by research on destination prediction and anomaly detection, for predicting the destination port- and region of oil tankers. In particular, our approach utilises a graph abstraction for aggregation of global oil tanker traffic and feature engineering, and Recurrent Neural Network models for the final port- or region destination prediction. Our experiments show promising results with the final model obtaining an accuracy score of 41% and 87.1% on a destination port- and region basis respectively. While some related works obtain higher accuracy results - notably 97% port destination prediction accuracy - the results are not directly comparable, as no related literature found deals with the problem of predicting oil tanker destination on a global scale specifically.

Music

Búgvi playing electric guitar outdoors

I've played music since I was a kid and went on to study contemporary music performance in Melbourne. I take bookings for weddings, receptions, parties and birthdays, in two formats: a full band, where I play drums, or a duo where I play guitar with a singer. Get in touch if you're looking for either.

Booking enquiries

Contact

Copenhagen, Denmark

Email LinkedIn Google Scholar