Seawater turbidity due to suspended particulate material (SPM) is an important property of a marine ecosystem, determining the underwater light environment and many aspects of biological production and ecology. SPM concentrations are largely determined by patterns of sediment resuspension from the seabed due to shear stress caused by waves and currents. Hence planning for the construction of large scale offshore structures which will alter regional hydrodynamics needs to consider the consequences for SPM concentrations. Here we develop a one-dimensional (vertical) model of SPM dynamics which can be used to scope the effects of changes in wave and tidal current properties at a site. We implement the model for a number of sites off the east coast of Scotland where we have extensive data sets to enable numerical parameter optimisation. The model performs well at simulating fluctuations in turbidity varying from flood-ebb tidal cycles, spring-neap cycles, storm wave events, and an annual cycle of SPM concentration which is attributed to seasonal consolidation of seabed sediments. Sensitivity analysis shows that, for the range of seabed sediment types in the study (water depth 16–50 m; mud content 0.006–0.380 proportion by weight), relatively large (50%) attenuations of tidal current speed are required to produce changes in water column turbidity which would be detectable by observations given the variability in measurements. The model has potential for application to map the large scale sensitivity of turbidity distributions to the installation of wave and tidal energy extraction arrays

Regulatory requirements for sub-sea oil and gas operators mandates the frequent inspection of pipeline assets to ensure that their degradation and damage are maintained at acceptable levels. The inspection process is usually sub-contracted to surveyors who utilize sub-sea Remotely Operated Vehicles (ROVs), launched from a surface vessel and piloted over the pipeline. ROVs capture data from various sensors/instruments which are subsequently reviewed and interpreted by human operators, creating a log of event annotations; a slow, labor-intensive and costly process. The paper presents an automatic image annotation framework that identifies/classifies key events of interest in the video footage viz. exposure, burial, field joints, anodes, and free spans. The reported methodology utilizes transfer learning with a Deep Convolutional Neural Network (ResNet-50), fine-tuned on real-life, representative data from challenging sub-sea environments with low lighting conditions, sand agitation, sea-life and vegetation. The network outputs are configured to perform multi-label image classifications for critical events. The annotation performance varies between 95.1% and 99.7% in terms of accuracy and 90.4% and 99.4% in terms of F1-Score depending on event type. The performance results are on a per-frame basis and corroborate the potential of the algorithm to be the foundation for an intelligent decision support framework that automates the annotation process. The solution can execute annotations in real-time and is significantly more cost-effective than human-only approaches.