Abstract

Ports are essential to global trade and logistics, but they face substantial challenges in aligning with sustainability goals, particularly in reducing greenhouse gas emissions and improving energy efficiency. Machine-Learning (ML) has emerged as a tool to address these challenges by enabling more accurate predictions of energy demand and optimization of port operations. This paper provides a rapid review of ML applications within port operations, focusing specifically on energy efficiency. The review examines three key areas, namely, ship energy consumption, the energy demands of cruise ships, and the implementation of shore-side electricity. Therefore, this work analyzes the current state of ML applications in these areas to identify challenges and opportunities, including the lack of publicly available data and the absence of established performance benchmarks, which hinder the widespread adoption of ML-driven solutions for enhancing sustainability in port operations.