Data Science for Maritime Transportation
Buch in deiner Nähe kaufen
Beschreibung
Dr. Liang Zhao received the Ph.D. degree in Civil Engineering at Zhejiang University and the Bachelor degree at Central South University. He was a visiting researcher in Maritime Studies at Nanyang Technological University from 2023 to 2024. Currently, he is an affiliated data scientist and research fellow at Zhejiang University. Dr. Zhao has over eight years of research experience in intelligent marine vehicles and maritime shipping systems. He has been the leading researcher for 12 industrial and government projects related to green shipping corridors, maritime decarbonization, autonomous ships, and vessel manoeuvring. Dr. Liang Zhao has co-authored over 30 research articles in top-tier engineering journals including Communications Engineering (Nature Portfolio), IEEE Transactions on Intelligent Vehicles, IEEE Transactions on Vehicular Technology, Knowledge-Based Systems, and Ocean Engineering. Dr. Liang Zhao also serves as an Associate Editor of Ships and Offshore Structures, and a Guest Editor for Journal of Marine Science and Engineering. His current research focuses on artificial intelligence, marine robotics, spatio-temporal data analytics, and green & intelligent shipping.
This book provides a comprehensive and application-oriented introduction to data science, machine learning, and deep learning methods for maritime transportation. It is written to help readers understand how maritime data can be processed, analyzed, modeled, and used to support digitalization for shipping industry. The book is organized into two parts. Part I, Fundamentals and Concepts, introduces the theoretical and methodological foundations required for maritime data science. It begins with maritime transportation data sources, structures, and characteristics, followed by essential data preprocessing techniques. It then presents methods for vessel trajectory representation, transformation, and analysis. The part also introduces the fundamental concepts of machine learning and deep learning, with a focus on their relevance to maritime applications. The final chapter of this part provides background knowledge on vessel maneuvering behavior and motion dynamics, establishing a bridge between physical understanding and data-driven modeling. Part II, Practical Applications and Case Studies, focuses on representative real-world problems in maritime data science and intelligent shipping. It covers trajectory clustering and pattern mining, deep learning-based vessel trajectory forecasting, anomaly detection using reconstruction methods, data-driven and physics-informed modeling of vessel propulsion power, regional ocean wave prediction, maritime traffic flow forecasting using graph neural networks, and vessel estimated time of arrival (ETA) prediction using machine learning. Each application chapter is designed as a self-contained case study that combines problem formulation, modeling methodology, implementation details, and practical interpretation. The book is suitable for graduate students, researchers, and practitioners in academia and industry. It can be used both as a structured textbook and as a practical reference for self-study. With hands-on Python examples and source code provided through the author’s GitHub repository, the book enables readers to reproduce key methods, understand maritime data characteristics, select appropriate modeling approaches, and develop data-driven solutions for real operational scenarios in maritime transportation.
Introduces core concepts in structured way Provides hands-on Python examples Covers frontier topics of maritime studies
Autor*in
Liang Zhao
Themen in »Data Science for Maritime Transportation«
Logistics Maritime Transportation Deep learning Port management Data science Artificial Intelligence Maritime shipping