{"title":"Maritime accident risk prediction integrating weather data using machine learning","authors":"","doi":"10.1016/j.trd.2024.104388","DOIUrl":null,"url":null,"abstract":"<div><p>The study explores the capability of various machine learning (ML) models in maritime accident risk prediction. Data from 1981 to 2021 from the Norwegian Maritime Authorities (NMA) was analysed together with the data of 51 different weather-related variables, which were collected from Visual Crossing for each accident recorded in the NMA dataset. The findings reveal an increased predictive ability of ML models when relevant weather data is introduced. The results show that the <em>Light Gradient Boosted Trees with Early Stopping</em> perform the best, with a five-fold cross validation accuracy of 70.23% when weather data was included, compared to 64.86% without. Furthermore, the study revealed that the leading weather variables for accident prediction are <em>wind</em>, <em>sea level pressure</em>, <em>visibility</em>, and <em>moon phase</em>. The most effective multi-classification ML algorithm can be deployed for improving maritime safety resilience through vulnerability assessment and preparedness.</p></div>","PeriodicalId":23277,"journal":{"name":"Transportation Research Part D-transport and Environment","volume":null,"pages":null},"PeriodicalIF":7.3000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1361920924003456/pdfft?md5=5d53a869a9f967d61742260db77f1d99&pid=1-s2.0-S1361920924003456-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transportation Research Part D-transport and Environment","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1361920924003456","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL STUDIES","Score":null,"Total":0}
引用次数: 0
Abstract
The study explores the capability of various machine learning (ML) models in maritime accident risk prediction. Data from 1981 to 2021 from the Norwegian Maritime Authorities (NMA) was analysed together with the data of 51 different weather-related variables, which were collected from Visual Crossing for each accident recorded in the NMA dataset. The findings reveal an increased predictive ability of ML models when relevant weather data is introduced. The results show that the Light Gradient Boosted Trees with Early Stopping perform the best, with a five-fold cross validation accuracy of 70.23% when weather data was included, compared to 64.86% without. Furthermore, the study revealed that the leading weather variables for accident prediction are wind, sea level pressure, visibility, and moon phase. The most effective multi-classification ML algorithm can be deployed for improving maritime safety resilience through vulnerability assessment and preparedness.
期刊介绍:
Transportation Research Part D: Transport and Environment focuses on original research exploring the environmental impacts of transportation, policy responses to these impacts, and their implications for transportation system design, planning, and management. The journal comprehensively covers the interaction between transportation and the environment, ranging from local effects on specific geographical areas to global implications such as natural resource depletion and atmospheric pollution.
We welcome research papers across all transportation modes, including maritime, air, and land transportation, assessing their environmental impacts broadly. Papers addressing both mobile aspects and transportation infrastructure are considered. The journal prioritizes empirical findings and policy responses of regulatory, planning, technical, or fiscal nature. Articles are policy-driven, accessible, and applicable to readers from diverse disciplines, emphasizing relevance and practicality. We encourage interdisciplinary submissions and welcome contributions from economically developing and advanced countries alike, reflecting our international orientation.