Generation of Synthetic CPTs with Access to Limited Geotechnical Data for Offshore Sites
Gohar Shoukat,
Guillaume Michel,
Mark Coughlan,
Abdollah Malekjafarian,
Indrasenan Thusyanthan,
Cian Desmond,
Vikram Pakrashi
Affiliations
Gohar Shoukat
UCD Centre for Mechanics, Dynamical Systems and Risk Laboratory, School of Mechanical and Materials Engineering, University College Dublin, D04 V1W8 Dublin, Ireland
UCD Centre for Mechanics, Dynamical Systems and Risk Laboratory, School of Mechanical and Materials Engineering, University College Dublin, D04 V1W8 Dublin, Ireland
The initial design phase for offshore wind farms does not require complete geotechnical mapping and individual cone penetration testing (CPT) for each expected turbine location. Instead, background information from open source studies and previous historic records for geology and seismic data are typically used at this early stage to develop a preliminary ground model. This study focuses specifically on the interpolation and extrapolation of cone penetration test (CPT) data. A detailed methodology is presented for the process of using a limited number of CPTs to characterise the geotechnical behavior of an offshore site using artificial neural networks. In the presented study, the optimised neural network achieved a predictive error of 0.067. Accuracy is greatest at depths of less than 10 m. The pitfalls of using machine learning for geospatial interpolation are explained and discussed.
