Please login first
Advancing Antarctic Benthic Ecosystem Monitoring through Photogrammetry and Automated Recognition Technologies
* 1, 2, 3 , 4 , 5 , 6 , 5 , 7 , 7 , 2, 3, 7
1  Department of Earth, Environmental and Life Sciences (DISTAV), University of Genoa
2  Italian National Antarctic Museum (MNA, section of Genoa), Viale Benedetto XV No. 5, 16132 Genoa, Italy
3  National Biodiversity Future Center (NBFC), Piazza Marina 61, 90100 Palermo, Italy
4  Visual Computing Lab ISTI-CNR, 56124 Pisa, Italy
5  3D Optical Metrology (3DOM) Unit, Bruno Kessler Foundation (FBK), Trento, Italy
6  Department of Humanities and Social Sciences, University of Sassari, 07100 Sassari, Italy
7  Department of Earth, Environmental and Life Sciences (DISTAV) - University of Genoa, Corso Europa 26, 16132 Genoa, Italy
Academic Editor: Kevin Cianfaglione

Abstract:

Antarctic benthic ecosystems are home to a unique and diverse fauna, with high levels of endemism. Despite their ecological importance, these communities are understudied, particularly in terms of their spatial variability. The remoteness and harsh environmental conditions of Antarctica complicate efforts to understand these ecosystems. The lack of time-series data limits our comprehension of temporal variations, highlighting the need for baseline data to detect natural or anthropogenic changes. To address these challenges, recent technological advancements have introduced non-destructive methods for studying benthic dynamics and spatial patterns. This study employs improved underwater optical recording systems, optimized image sampling, and 3D mapping techniques, along with advanced software for benthic imagery analysis. Photographic and video sampling techniques are utilized to create permanent records, facilitating detailed image analyses and reducing the underwater time and expertise required for species identification. The primary goal of this research is to create a comprehensive library of Antarctic benthic organisms using AI software. This approach streamlines the identification process and reduces the need for manual classification. By integrating photogrammetry with automated organism recognition, this study aims to develop a sustainable, long-term monitoring system for Antarctic benthic ecosystems. This innovative methodology promises to enhance our understanding of temporal and spatial changes in Antarctic benthic ecosystems. The implementation of this long-term monitoring system will provide critical data to support informed conservation and management strategies in response to environmental challenges. The study's findings underscore the potential for advanced technologies to facilitate ecological research in remote and extreme environments.

Keywords: Benthos; diver-operated underwater photogrammetry; video samplings; long-term monitoring
Comments on this paper
Daria Balycheva
Dear Alice,

Thank you for the interesting presentation.
I would like to clarify, did you control the accuracy of species identification using classical methods?
Alice Guzzi
Dear Daria,

Thank you for your kind words—I'm glad to hear you found my presentation interesting.

To address your question, unfortunately, we are unable to perform detailed morphological analyses of the organisms at this time. Achieving the lowest taxonomic resolution often requires specific analyses (e.g., slide preparation, SEM imaging) that depend on physical samples, which we do not currently have.

However, we are fortunate to have extensive reference literature from the area listing present species, as the site is close to the Italian Mario Zucchelli Station. Additionally, the Italian National Antarctic Museum (MNA) - section of Genoa houses biological collections from the region, allowing us to familiarize ourselves with the species prior to identification.

That said, we exercise caution when assigning definitive identifications to organisms we are uncertain about. Whenever possible, we’ve consulted experts in various taxonomic groups, but many organisms remain identified only to the genus level, or higher. For certain organisms, such as some sponges lacking clear macroscopic diagnostic traits, we use descriptive labels (e.g., "massive orange morphotype") for now.

Looking ahead, since the site is georeferenced, we could plan to collect tissue samples from sessile organisms (e.g., sponges) during future monitoring efforts to ensure more accurate identification with ground truth.

Thank you again for your question and please don’t hesitate to reach out if you have any more.

Best regards,

Alice

Daria Balycheva
Dear Alice,
Thank you so much for your prompt reply and clarification.
You have presented a very promising research method.



Dr. Daria Balycheva



 
 
Top