| 23 Apr 2026
Machine Learning Framework for Scour Detection Across Multiple Offshore Wind Farms
Abstract. This paper proposes a global scour detection framework for monopile foundations across offshore wind farms, based on data from a single accelerometer installed on the turbine tower. The framework is designed to address the real-world complexity and heterogeneity of offshore wind systems installed across multiple offshore sites. To achieve this, numerically generated acceleration data are obtained for various offshore wind turbines (OWTs) across multiple wind farms using a coupled OpenFAST and bespoke soil-structure interaction (SSI) model. The simulation accounts for a wide array of offshore conditions, from sea states and soil properties to structural characteristics and site-specific scour. For each OWT, acceleration data are generated using foundation stiffness derived from the SSI model, reflecting the site conditions and turbine characteristics. A multi-source domain generalisation (DG) strategy is then employed, in which a model trained on a combined dataset containing one turbine per farm (referred to as source turbines) is used to detect scour around the remaining, previously unseen turbines (referred to as target turbines) across geographically-disparate wind farms. The results demonstrate that the proposed method can identify the scour state for multiple target turbines across multiple wind farms with acceptable accuracy. In addition, the choice of source turbine significantly impacts model performance, with shallow water, low-stiffness turbine foundations providing the most reliable training base. Furthermore, obtaining sensor data from the tower base significantly improves scour detection, while increasing the number of source turbines in the training dataset enhances prediction accuracy, specifically at lower scour states.
The paper “Machine Learning Framework for Scour Detection Across Multiple Offshore Wind Farms” proposes a domain generalisation framework – specifically a domain-adversarial neural network using acceleration spectral content as input – for scour detection across multiple offshore wind farms. To this end, a coupled OpenFAST-SSI model was used to simulate responses of turbines in three hypothetical wind farms sharing the same turbine type and with varying soil and structural characteristics, subject to different environmental conditions. The main novelty of the contribution lies with the extending scour detection into fleets. Apart from minor typos, the paper is generally well-written.
However, I believe some further results are required to strengthen the paper and its assertions.
Firstly, appropriate baselines are missing. Without these, some of the conclusions of the contribution can be called into question. Namely:
Therefore, the conclusion that model training is best performed for the shallowest farms/turbines with lowest stiffness foundation could be called into question (if, i.e., the model is just triggering in different dynamics and not on actual scour). Given this assertion, it could also be considered as an additional baseline into the ‘population-based’ approach to train in a single turbine (e.g. T1.1., the shallowest and with lowest soil stiffness). A further suggestion related to this conclusion would be to fully flesh it out in terms of the what it means for the structures’ eigenfrequency (lower soil density, lower stiffness, lower eigenfrequency, but conversely, shallower water depth, higher eigenfrequency).
The setup of the experiment could also be strengthen in the introduction: in a landscape where there are few labelled scour data (and therefore an incentive for self-supervised learning) and OWT fleets more often than not consist of different wind turbine types, how would you set up the current experiment. These aspects could also be reflected in the conclusions/future work.
Regarding the modelling in OpenFAST in sections 2.3. and 3., more details could be provided:
Some further clarifications could also be provided:
Finally, some suggestions: