Speaker
Description
Geophysical, geological and geotechnical data play a vital role in deepwater/ultra-deepwater site characterizations for subsea structures sitting on/below the seabed. From the engineering perspective, considering the risk of subsea development and the capital investment, the integration of the above three sets of data are paramount, especially during the planning phase of the project for offshore site investigations, not only to define the scope to be performed at the target site most effectively, but also to aid interpretation once engineering data are acquired for subsea structure design. Although geophysical data are advantageous in imaging the subsurface conditions over large offshore areas revealing important information about seabed features, and geological data can identify the sediment depositional history, the information obtained is usually qualitative from an engineering design perspective. Thus, this talk will present a quantitative framework to digitally integrate these three sets of data using machine learning. Examples from different regions with different data are presented, with a hope to promote this technique for deepwater site characterizations to reduce both the risk and the cost.
