My research career began in benthic ecology, investigating the environmental drivers for species distributions, but I have become increasingly interested in applied informatics research, specifically how technological advancements to seabed monitoring can better aid our understanding and protection of benthic communities, such as deep sea corals and sponges. In particular, i seek innovative solutions that promote accessibility, standardization and real-world impact. 

I have undertaken degrees and research positions in marine ecology, on topics related to biodiversity, imaging and machine learning. I also have a PhD in computer science, which focused on improving the extraction and processing of ecological data from images of deep benthic habitats in the Norwegian Sea. This involved the development of ML (including deep learning) solutions and a novel underwater image enhancement algorithm, specifically aimed at improving the accessibility of these analysis methods to ecologists without training in this field. 

Game, C.A., Thompson, M.B. and Finlayson, G.D., 2024. Machine learning for non-experts: A more accessible and simpler approach to automatic benthic habitat classification. Ecological Informatics, 81, p.102619. https://www.sciencedirect.com/science/article/pii/S1574954124001614?via%3Dihub

Borremans, C., et al (inc. Game, C. A.). 2024. Report on the Marine Imaging Workshop 2022. Research Ideas and Outcomes 10: e119782. https://doi.org/10.3897/rio.10.e119782

Game, C.A., Thompson, M.B. and Finlayson, G.D. 2023. Weibull Tone Mapping (WTM) for the enhancement of underwater imagery. Sensors, 23(7), p.3533. https://www.mdpi.com/1424-8220/23/7/3533 

Game, C. A. 2022. Domain-inspired image processing and computer vision to support deep-sea benthic ecology (Doctoral dissertation, University of East Anglia). https://ueaeprints.uea.ac.uk/id/eprint/93971/

Game, C.A., Thompson, M.B. and Finlayson, G.D. 2021. Chromatic Weibull Tone Mapping for Underwater Image Enhancement. Proceedings of the International Colour Association Congress 2021, pp. 239–244. https://ueaeprints.uea.ac.uk/id/eprint/81310/

Game, C.A., Thompson, M.B. and Finlayson, G.D. 2020. Weibull Tone Mapping for Underwater Imagery. Color and Imaging Conference 2020, 379, pp. 156–161. https://library.imaging.org/admin/apis/public/api/ist/website/downloadArticle/cic/28/1/art00025

Howell et al (inc. Game, C. A). 2019. A framework for the development of a global standardised marine taxon reference image database (SMarTaR-ID) to support image-based analyses. PLOS ONE, 14 (12):e0218904. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0218904.

Sheehan, E.V., Hosegood, P., Game, C. A, Attrill, M.J., Tickler, D., Wootton, M., Johns, D.G., Meeuwig, J.J. 2019. The effect of deep oceanic flushing on water properties and ecosystem functioning within atolls in the British Indian Ocean Territory. Frontiers in Marine Science, 6, p.512. https://www.frontiersin.org/articles/10.3389/fmars.2019.00512/full?field=&id=469047&journalName=Frontiers_in_Marine_Science

Sheehan, E.V., Cartwright, A.Y., Game, C.A, Cousens, S.L., Bridger, D.R., Nancollas, S.J., Rees, A.G., Gall, S.C., Attrill, M.J. 2017. Lyme Bay- a case-study: Response of the benthos to the zoned exclusion of towed demersal fishing gear in Lyme Bay; 8 years after the closure. March 2017. Report to Natural England from Plymouth University Marine Institute. 88 pages. 

Developing automated multi-modal monitoring strategies of vulnerable marine ecosystems (VMEs) (2024-2027)

Part of the SEAS programme (Shaping European Research Leader for Marine Sustainability), funded by Marie Skłodowska-Curie grant agreement No. 101034309

Anthropogenic impacts on the marine environment are increasing as growing resource demands must be met. Recently (2024), the Norwegian government voted to undertake seabed mining, which could put the deep-sea bed, which harbors a rich diversity of ecologically and economically valuable, yet vulnerable, ecosystems, under serious threat. It is critical that extensive accurate maps of the seafloor are created to establish baselines and support monitoring of impacts and recovery. Given the region’s vastness and isolation, such monitoring is logistically challenging and too slow to meet the requirements. It must therefore be conducted with photography and machine learning (ML) used to automatically identify and quantify seafloor organisms; avoiding labor-intensive manual analysis. 

This project aims to increase performance (accuracy, consistency & efficiency) of benthic monitoring. To this end, we aim to develop an ML approach that combines both seabed images and associated environmental data (from other sensors such as local topography and water temperature) to increase accuracy of automated analysis and refine the level of biological details used to make predictions, which is currently not possible for ML with images alone. Importantly, we will consider explainability of model decisions, opening up the ‘black-box’, and seek to generalize the approach across target seabed communities and datasets. Through collaboration with the Mareano project (Institute of Marine Research) and the Centre for Deep Sea Research (UIB), this research will be explored on the Norwegian Continental shelf and the Arctic Mid-Ocean Ridge.