Report for "Machine learning-driven, near-surface velocity modelling in the North Sea: Using onshore data to predict offshore conditions"

Shear-wave velocity (Vs) is an essential parameter in evaluating geotechnical hazards and in foundation design. Conventional techniques to measure Vs are time-intensive, costly, and infeasible to perform at high resolution across large sites such as offshore wind farms. However, predicting Vs, particularly the time-averaged Vs in the uppermost 30 m (Vs30), using readily available geospatial proxies has significant technical and economic benefits. This study employs geospatial data and machine learning techniques to advance Vs30 mapping in the North Sea, leveraging onshore geotechnical data from the United Kingdom, Norway, and the Netherlands. To encourage reliable extrapolation from onshore to offshore environments, the workflow prioritises domain-limited predictions and independent verification against offshore datasets. The outcomes of this modelling effort include a proof-of-concept simplified site classification map in the North Sea (presented in this dataset) and a scalable methodologic framework adaptable to other offshore regions and geotechnical parameters. Importantly, this study identifies critical data gaps that constrain current model performance and that should be prioritised to advance offshore Vs mapping for hazard assessment, siting, and infrastructure design.

Additional model development and performance details are provided in the following manuscript:
Sanger, M.D., Carlton, B., Liu, Z., Vanneste, M., Griffiths, L., & Maurer, B.W. (In Review). Machine learning-driven, near-surface velocity modelling in the North Sea: Using onshore data to predict offshore conditions. GeoRisk. (Journal Paper)