Unveiling the Operational Patterns of Global LNG Terminal Points: A Multi-algorithmic Clustering Approach

DOI

10.2991/978-94-6463-300-9_28How to use a DOI?

Keywords

Machine Learning; Clustering Algorithm; LNG Terminal Points

Abstract

This study embarked on a mission to solve a complex issue in the field of maritime logistics - understanding and classifying the operational patterns of Liquified Natural Gas (LNG) terminal points across the globe. Given the significant role of LNG shipping in global energy transport, identifying these patterns holds substantial value for optimizing shipping operations and improving safety. The adopted methodology was a novel multi-algorithmic approach using machine learning, specifically leveraging the BIRCH, KMeans, and DBSCAN clustering algorithms. These tools enabled this study to scrutinize a comprehensive dataset, capturing the operational dynamics of LNG terminal points based on draft depth alterations. This approach facilitated a more nuanced and sophisticated understanding of the terminal points, unlike conventional methodologies. The research findings delineated a detailed and holistic geospatial distribution of LNG terminal points. The results were testament to the effectiveness of the proposed approach as the generated cluster graphs closely mirrored actual site maps, illustrating a high degree of precision and robustness. It was demonstrated that the operational patterns derived from this methodology can provide superior insights for logistics planning, potentially allowing for more efficient and safer maritime operations. However, it is important to acknowledge that the choice of clustering algorithm can influence the resolution and accuracy of the clustering results, indicating the possibility for further refinement. Moving forward, this work establishes a promising foundation for optimizing LNG logistics and developing predictive traffic models, with potential applications extending to other domains within maritime data analysis.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Haoda Wen
PY  - 2023
DA  - 2023/11/27
TI  - Unveiling the Operational Patterns of Global LNG Terminal Points: A Multi-algorithmic Clustering Approach
BT  - Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
PB  - Atlantis Press
SP  - 280
EP  - 292
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-300-9_28
DO  - 10.2991/978-94-6463-300-9_28
ID  - Wen2023
ER  -