EUVIMEDEUVIMED entdecken
Crossref

Real-time integration framework of AI-powered and traditional maritime forecasting for safer and more efficient offshore operations

Ellen Xiao, Qi Chu, Ian Milne, Michael Garvey, Mohamed Ibrahim, Jan Flynn

Australian Energy Producers Journal · 14.05.2026 · 66 (S1)

DOI: 10.1071/ep25231 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Australian Energy Producers Journal, online erschienen am 14.05.2026. Verfasst von Ellen Xiao und 5 weiteren Autor:innen. Die Arbeit nennt 4 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Woodside Energy leverages a diverse range of maritime forecasting products to guide weather sensitive offshore operations across development, production, and decommissioning. Significant increases in the volume and diversity of forecast data, and the opportunity for real-time acquisition have impelled the need for an integrated framework to support operational decision-making and risk management. Here, we present a framework enabling a range of forecasting services, including vessel motion, wave conditions, and ocean currents; some of which are data-driven predictions while others use physics-based numerical models. Each forecasting product poses distinct challenges in data acquisition and cybersecurity vetting, as well as in format heterogeneity, data volume, and forecast cadence. To address these challenges, a cloud-based archiving and scheduling system has been implemented, allowing coherent integration of varied forecasting products and robust data management. This framework also includes a statistical analytics workflow for continuous performance validation and real-time uncertainty quantification. Depending on operational requirements, output deliverables are tailored to the needs of internal and external users, either through interactive dashboards for real-time monitoring or via scheduled email notifications to support planning and response. Built on a cloud-native architecture designed to scale with rapid AI-driven advances in forecasting, this framework streamlines data management, enables real-time validation, and delivers tailored outputs. This improves forecast accessibility and utility, and enhances decision-making for safer, more efficient operations.

Zitieren

APA

Xiao, E., Chu, Q., Milne, I., Garvey, M., Ibrahim, M., & Flynn, J. (2026). Real-time integration framework of AI-powered and traditional maritime forecasting for safer and more efficient offshore operations. Australian Energy Producers Journal, 66(S1). https://doi.org/10.1071/ep25231

Vancouver

Xiao E, Chu Q, Milne I, Garvey M, Ibrahim M, Flynn J. Real-time integration framework of AI-powered and traditional maritime forecasting for safer and more efficient offshore operations. Australian Energy Producers Journal. 2026;66(S1). doi:10.1071/ep25231

BibTeX
@article{Xiao2026,
  author = {Xiao, Ellen and Chu, Qi and Milne, Ian and Garvey, Michael and Ibrahim, Mohamed and Flynn, Jan},
  title = {Real-time integration framework of AI-powered and traditional maritime forecasting for safer and more efficient offshore operations},
  journal = {Australian Energy Producers Journal},
  year = {2026},
  volume = {66},
  number = {S1},
  doi = {10.1071/ep25231}
}
Kostenlos starten →