Full text loading...
-
Addressing the Challenge of Efficiency and Scale within Near-Surface Characterization Workflows Using Machine Learning
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 6th Asia Pacific Meeting on Near Surface Geoscience and Engineering, May 2024, Volume 2024, p.1 - 5
Abstract
Summary
The increase in the size and number of offshore windfarm license block areas requires a review of the effiency of near-surface characterisation workflows. The size of area requiring near-surface characterisation in support of the development of offshore windfarms has increased by several orders of magnitude in recent years, and whilst the geotechnical site investigation workflows for this are established, mature and efficient, this rapid increase in scale requires us to review how new technologies can further accelerate the site investigation process. The use of machine learning (ML) shows significant promise in a number of core tasks such as site screening, structural interpreation, boulder detection and soil property estimation. When combined with similar advances in data management, visualistion and communication, we are well placed to support the increase in scale required to meet our societal goal of reducing carbon emissions through the generation of clean energy. The continued development and ultimate adoption of ML and artificial intelligence is relevant as it has the potential to significantly impact our ability to reach our goals within the time scales identified.
© EAGE Publications BV