Automated Image Analysis of Offshore Infrastructure Marine Biofouling

Abstract

Abstract:In the UK, some of the oldest oil and gas installations have been in the water for over 40 years and have considerable colonisation by marine organisms, which may lead to both industry challenges and/or potential biodiversity benefits (e.g., artificial reefs). The project objective was to test the use of an automated image analysis software (CoralNet) on images of marine biofouling from offshore platforms on the UK continental shelf, with the aim of (i) training the software to identify the main marine biofouling organisms on UK platforms; (ii) testing the software performance on 3 platforms under 3 different analysis criteria (methods A-C); (iii) calculating the percentage cover of marine biofouling organisms and (iv) providing recommendations to industry. Following software training with 857 images, and testing of three platforms, results showed that diversity of the three platforms ranged from low (in the central North Sea) to moderate (in the northern North Sea). The two central North Sea platforms were dominated by the plumose anemone Metridium dianthus; and the northern North Sea platform showed less obvious species domination. Three different analysis criteria were created, where the method of selection of points, number of points assessed and confidence level thresholds (CT) varied: (method A) random selection of 20 points with CT 80%, (method B) stratified random of 50 points with CT of 90% and (method C) a grid approach of 100 points with CT of 90%. Performed across the three platforms, the results showed that there were no significant differences across the majority of species and comparison pairs. No significant difference (across all species) was noted between confirmed annotations methods (A, B and C). It was considered that the software performed well for the classification of the main fouling species in the North Sea. Overall, the study showed that the use of automated image analysis software may enable a more efficient and consistent approach to marine biofouling analysis on offshore structures; enabling the collection of environmental data for decommissioning and other operational industries.

Ecological Role of an Offshore Industry Artificial Structure

“…Oil and gas industry structures are rapidly colonised (Bell and Smith, 1999) and typically develop a highly productive ecosystem, e.g., ∼2700 tons of marine life have been estimated to live on the Shell Brent Alpha platform in the North Sea (Shell UK Ltd., 2017), including conservation priority species such as the reef-forming cold-water coral Desmophyllum pertusum (Linnaeus, 1758) (formerly Lophelia pertusa) (Bell and Smith, 1999). However, research on successional dynamics of organisms living on offshore infrastructure and the impacts to the surrounding benthos is surprisingly rare and generally limited to inaccessible consultancy reports (Gormley et al, 2018).…”

Automating the assessment of biofouling in images using expert agreement as a gold standard

“…However, this issue is somewhat mitigated by our focus on classifying the overall coverage of biofouling in an image, rather than just the species present. This also allows us to side-step the challenge of identifying species or species groups, which would have likely required a larger set of images to obtain similar results 32 . Our approach of simply looking at the overall level of fouling is more robust for the purpose of identifying biosecurity risk, as even if a particular type of organism occurs infrequently or not at all in the training data, our models may generalise information gained from other types of biofouling to detect that the hull is still fouled.…”

“…Since videos are constructed using a stream of images, our model should be readily adaptable to videos as well. However, further work is needed to address issues such as identifying the frames in which the camera is directed towards a vessel hull as opposed to open water or where image quality is poor, which is a common issue when analysing stills obtained from ROV footage 32 . The video format would also offer the opportunity to incorporate information from future and previous frames to improve and smooth fouling estimates, and ideas from current action recognition methods could potentially be applied 67 .…”

Benthic Conservation Features and Species Associated With Subsea Pipelines: Considerations for Decommissioning

“…Remotely operated vehicles video footage was successfully used in this study to quantify FOCI and record the presence of other marine fauna associated with pipelines. The repurposing of video footage, originally obtained for integrity assessments, for ecological analysis presented a number of challenges as have been documented previously by Gormley et al (2018) and Macreadie et al (2018). The lack of a suitable scale in the footage meant that the area within the field of view could not be calculated and faunal counts could not be scaled by area.…”

“…Subsea pipelines are an integral part of offshore oil and gas extraction and have been installed in all major hydrocarbon basins (Guo et al, 2005). Pipelines are generally constructed from steel, with polymer or concrete coatings, and can be installed directly on the seabed ("surface laid") or within a trench, which can be back filled naturally or artificially (Oil and Gas Uk, 2013a).…”