Assessing the Image Concept Drift at the OBSEA Coastal Underwater Cabled Observatory

13 pages, 9 figures, 2 tables.-- Data Availability Statement: The time series of specimen counts per species, obtained through the visual inspection of the image dataset, is provided as a supplementary material (only the images containing at least one specimen are reported). The image datasets analysed for this study can be accessed by contacting the OBSEA observatory [https://www.obsea.es/] on reasonable requestThe marine science community is engaged in the exploration and monitoring of biodiversity dynamics, with a special interest for understanding the ecosystem functioning and for tracking the growing anthropogenic impacts. The accurate monitoring of marine ecosystems requires the development of innovative and effective technological solutions to allow a remote and continuous collection of data. Cabled fixed observatories, equipped with camera systems and multiparametric sensors, allow for a non-invasive acquisition of valuable datasets, at a high-frequency rate and for periods extended in time. When large collections of visual data are acquired, the implementation of automated intelligent services is mandatory to automatically extract the relevant biological information from the gathered data. Nevertheless, the automated detection and classification of streamed visual data suffer from the “concept drift” phenomenon, consisting of a drop of performance over the time, mainly caused by the dynamic variation of the acquisition conditions. This work quantifies the degradation of the fish detection and classification performance on an image dataset acquired at the OBSEA cabled video-observatory over a one-year period and finally discusses the methodological solutions needed to implement an effective automated classification service operating in real timeThis research activity was partially funded by the “ENDURUNS - Development and demonstration of a long-endurance sea surveying autonomous unmanned vehicle with gliding capability powered by hydrogen fuel cell project”, Horizon 2020, Grant Agreement H2020-MG-2018-2019-2020 n.824348 and by the “Joint European Research Infrastructure of Coastal Observatories: Science, Service, Sustainability - JERICO-S3’’ project, Horizon 2020, Grant Agreement no. 871153. This research was also funded within the framework of the following project activities: ARIM (Autonomous Robotic sea-floor Infrastructure for benthopelagic Monitoring; MarTERA ERA-Net Cofound); RESBIO (TEC2017-87861-R; Ministerio de Ciencia, Innovación y Universidades). We also profited from the funding from the Spanish Government through the ‘Severo Ochoa Centre of Excellence’ accreditation (CEX2019-000928-S