Exploring 3D Wave-Induced Scouring Patterns around Subsea Pipelines with Artificial Intelligence Techniques

Subsea pipelines carry oil or natural gas over long distances of the seabed, but fluid leakage due to a failure pipeline can culminate in huge environmental disasters. Scouring process may take place beneath current and/or wave action, causing suspension and leading risk failure. The resulting morphological variations seabed propagate not only below normally also along itself. Therefore, 3D scouring patterns need be considered. Mainly based on experimental works at laboratory scale by Cheng coworkers, this study, Artificial Intelligent (AI) techniques are employed present new equations for predicting three dimensional current- wave-induced scour rates around subsea pipelines. These given terms key dimensionless parameters, among which Shields’ parameter, Keulegan–Carpenter number, relative embedment depth, wave/current angle attach. Using various statistical benchmarks, efficiency AI-models-based regression is assessed. proposed predictive models perform much better than existing empirical from literature. Even more interestingly, they exhibit clear physical consistence allow highlighting importance variables governing patterns.