Throughout March and April, we are featuring articles shortlisted for the 2024 Robert May Prize. The Robert May Prize is awarded by the British Ecological Society each year for the best paper in Methods in Ecology and Evolution written by an early career author. Jonathan Sauder’s article ‘Scalable semantic 3D mapping of coral reefs with deep learning‘ is one of those shortlisted for the award.

The paper

What is your shortlisted paper about, and what are you seeking to answer with your research?  

Coral reefs are at a decline worldwide, but due to the limited scalability of reef monitoring methods, our understanding of how reefs are impacted by stressors remains incomplete. We capitalise on the synergy between 3D mapping based on deep learning, and neural networks for semantic segmentation, to devise a method for automatically processing coral reef video transects within a few minutes. 

Were you surprised by anything when working on it?  Did you have any challenges to overcome? 

The main challenge was bridging the interdisciplinary gap – finding a common language to describe methods that are both technologically feasible and find real ecological applications. 

What is the next step in this field going to be?  

The next step in this field is to facilitate the deployment of AI-based methods in new biogeographic regions, and to further increase the resolution and robustness. 

What are the broader impacts or implications of your research for policy or practice?   

The broader impact of designing such a scalable and affordable monitoring method is that coral reef monitoring becomes feasible even in regions with heavily restricted research resources, democratising participation in coral reef science. Furthermore, the general methodology can be applied to a wide range of other underwater ecosystems that are currently costly to monitor. 

The author

How did you get involved in ecology?  

My pivot from pure computer science to applied work in ecology happened by chance – even though I was always concerned with environmental and ecological issues. When faced with the opportunity of this interdisciplinary PhD position, I was eager to use my computational background in ecological applications. 

What is your current position? 

Currently, I am a PhD student at the École Polytechnique Fédérale de Lausannne (EPFL), co-hosted by the Environmental Computational Science and Earth Observation (ECEO) Laboratory and the Laboratory for Biological Geochemistry. 

Have you continued the research your paper is about? 

Yes, we continue to work on improving the methodology and extending its scope to more regions. 

What one piece of advice would you give to someone in your field?  

When working on technology for ecology or conservation, it’s easy to get carried away by technological gimmicks. I try to make an effort to think of the underlying ecological questions and how we can enhance ecologists in their work, instead of trying to compete.