• Systematic review of digital disaster prevention in ocean engineering. • Digital transition shifts ocean engineering to proactive disaster resilience. • Interpretable hybrid and causal models enable reconstruction of disaster mechanisms. • Overcoming data scarcity underpins real-time digital twins and fidelity simulations. • A four-layer digital framework is proposed for closed-loop disaster prevention. The increasing frequency of typhoons and other extreme climate events has intensified the risks of natural hazard-triggered technological accidents (Natech), posing significant challenges to ocean engineering infrastructures. Traditional disaster-prevention approaches, largely dependent on empirical judgments and static analyses, are no longer sufficient for real-time risk identification or proactive mitigation in complex ocean environments. Advances in digital technologies offer new pathways for disaster reduction and have become the critical frontier for ocean engineering safety. This review synthesizes recent progress in digital disaster prevention for ocean engineering under climate extremes. We examine three core areas: disaster-inducing factor identification, disaster mechanism modeling, and structural safety assessment. Within this framework, we summarize the integration of physics-based numerical modeling, data-driven simulation, and system dynamics for understanding hazard triggers, causal chains, and cascading failures. We further review applications of digital twins, machine learning, and deep learning in scenario-based risk analysis, safety evaluation, and early-warning systems, emphasizing offshore wind farms. Key challenges and future directions are discussed, proposing a forward-looking digital technology system that integrates environmental sensing, interpretable modelling, intelligent prediction and warning, and resilience-oriented decision support. Overall, digital disaster prevention provides a significant pathway toward more adaptive, predictive, and resilient safety management in ocean engineering.
Hu et al. (Wed,) studied this question.