Answers are grounded in this paper and cite their sources.
This study introduces a novel probabilistic framework for the assessment and prediction of scour around submerged pipelines under wave-induced loading and parameter uncertainties. A surrogate model based on Gaussian process regression (GPR) is proposed to provide accurate scour estimations in situations with limited laboratory and field data. The performance of the proposed surrogate model is first validated through comparison with seven machine learning models. Subsequently, a probabilistic sensitivity analysis is developed to evaluate the relative influence of hydrodynamic, geomorphological, and structural factors on submerged pipeline failure under scour conditions, employing Monte Carlo simulation and GPR. Statistical evaluations demonstrate the superior performance of the GPR model in identifying key parameters affecting the failure of submerged pipelines compared to other machine learning approaches. Further, an explicit relationship is established to link reliability index with the design safety factor of offshore pipelines. The proposed framework offers a robust predictive tool and reliable uncertainty quantification for evaluating the performance of submerged pipelines under uncertain scenarios.
No takes yet. Share an insight, caveat, or question.
Vatani et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: