Posted in | News | Machine-Vision

Researchers Create New AI Technique to Analyze Eelgrass Wasting Disease

An interdisciplinary study group used ecological field methods combined with cutting-edge artificial intelligence to discover eelgrass-wasting disease at almost three dozen sites throughout a 1,700-mile length of the West Coast, from San Diego to southern Alaska.

New AI Technique to Analyze Eelgrass Wasting Disease.
An eelgrass meadow is pictured at low tide at False Bay Biological Preserve, Washington. Eelgrass is a vital coastal species of seagrass for fish habitat, biodiversity, shoreline protection and carbon sequestration. Image Credit: Olivia Graham/Provided.

The important finding: Seagrass wasting, which is induced by the organism Labyrinthula zosterae and may be detected by lesions on grass blades that can be validated by molecular diagnostics, is linked to warmer-than-normal water temperatures, especially in early summer, regardless of location. Eelgrass is an important seagrass species for fish habitat, biodiversity, coastline protection, and carbon sequestration along the coast.

Carla Gomes, the Ronald C. and Antonia V. Nielsen Professor of Computing and Information Science at the Cornell Ann S. Bowers College of Computing and Information Science, as well as Drew Harvell, professor emeritus in the Department of Ecology and Evolutionary Biology (College of Agriculture and Life Sciences; College of Arts and Sciences), led the Cornell research team, which published their findings in Limnology and Oceanography on May 27th, 2022.

Brendan Rappazzo, M.Eng. ‘18, a computer science doctoral student, and Lillian Aoki ‘12, a former postdoctoral researcher in Harvell’s lab who is currently a research scientist at the University of Oregon, are co-lead authors. Olivia Graham and Morgan Eisenlord, both doctoral students in ecology and evolutionary biology, also contributed.

J. Emmett Duffy of the Smithsonian Institution was the principal investigator on a three-year, $1.3 million National Science Foundation (NSF) project that resulted in this study. The NSF Expeditions in Computing grant for computational sustainability financed the AI research and development; the first relationship between Harvell and the Smithsonian was formed as a Cornell Atkinson Center for Sustainability effort.

Gomes, who is also the director of the Institute for Computational Sustainability, collaborated with Rappazzo to create the Eelgrass Lesion Image Segmentation Application (EeLISA, pronounced eel-EYE-zah), an AI method that can quickly analyze thousands of images of seagrass leaves and distinguish diseased from healthy tissue when properly trained.

EeLISA operates 5,000 times quicker than human specialists and with equivalent accuracy, according to the researchers. As more data is given into the program, it becomes “smarter” and gives more consistent results.

That’s really a key component, if you give the same eelgrass scan to four different people to label, they’ll all give variable measurements of disease. You have all this variation, but with EeLISA, it’s not only faster but it’s consistently labeled.

Brendan Rappazzo, Study Co-Lead Author and Doctoral Student, Department of Computer Science, Cornell University

Rappazzo earned the AAAI Conference on Artificial Intelligence’s Innovative Application Award in 2021 for his work on EeLISA.

In traditional machine learning, you need large amounts of labeled data up front. But with EeLISA, we’re getting feedback from the scientists providing the images, and the system improves very rapidly. So in the end, it doesn’t require that many labeled examples.

Carla Gomes, Professor, Computing and Information Science, Cornell University

This study featured a network of 32 field locations spanning 23° of latitude along the Pacific coast. The research of seagrass wasting disease in various temperatures and habitats was made possible by the diversity of regions.

Thousands of images from across the network are supplied into the EeLISA system, which evaluates each image pixel by pixel to see if it contains healthy tissue, sick tissue, or background. Human annotators rate EeLISA’s first results, and adjustments are supplied to the program so that it can learn from its mistakes.

The researchers get their output, send their corrections back to the algorithm, and it updates the next iteration. The original scans for EeLISA to label, when it’s completely random, might take half an hour per scan. By the next iteration, it might be down to 10 minutes, then to two minutes, then one minute. And we reached the point where it was at human-level accuracy, and needed to be checked only sporadically.

Brendan Rappazzo, Study Co-Lead Author and Doctoral Student, Department of Computer Science, Cornell University

Warm-water anomalies, independent of what usual temperatures were for a given place, were shown to be the primary cause of eelgrass wasting disease, according to an AI-assisted study. This indicated to the researchers that examining the link between disease and climate change is important in all conditions, not only in warm-climate seagrass meadows.

Harvell added, “We have invested a decade developing the disease recognition tools to monitor these outbreaks at a large spatial scale, because our early studies suggested eelgrass could be sensitive to warming-induced outbreaks. Eelgrass is an essential marine habitat, and a critical link in the chain of survival for fishes such as salmon and herring.”

The objective, according to Gomes, is to scale EeLISA such that it may be utilized for “citizen science” all over the world. That, according to Aoki, is one of the most intriguing features of this project.

We could ask people to identify seagrass disease in this much broader way, leveraging a lot more public involvement. We’re certainly several steps away from that, but I think that is an incredibly exciting frontier,” Aoki concluded.

University of California, Davis; University of Alaska, Fairbanks; University of Central Florida; Hakai Institute, British Columbia; Oregon State University; San Diego State University; and Mediterranean Institute for Advanced Studies, Esporles, Spain are among the other co-authors.

The National Science Foundation provided funding for this study.

Journal Reference:

Aoki, L. R., et al. (2022) Disease surveillance by artificial intelligence links eelgrass wasting disease to ocean warming across latitudes. Limnology and Oceanography.


Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Azthena logo powered by Azthena AI

Your AI Assistant finding answers from trusted AZoM content

Azthena logo with the word Azthena

Your AI Powered Scientific Assistant

Hi, I'm Azthena, you can trust me to find commercial scientific answers from

A few things you need to know before we start. Please read and accept to continue.

  • Use of “Azthena” is subject to the terms and conditions of use as set out by OpenAI.
  • Content provided on any AZoNetwork sites are subject to the site Terms & Conditions and Privacy Policy.
  • Large Language Models can make mistakes. Consider checking important information.

Great. Ask your question.

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.