According to the National Oceanic and Atmospheric Administration, aquaculture in the United States represents a $1.5 billion annual industry. Like land-based aquaculture, shellfish farming requires healthy seed production to maintain a sustainable industry. Production of shellfish larvae (seeds) in aquaculture hatcheries requires close monitoring to track mortality and assess health status from early stages of life.
Careful observation is required to determine production schedules, determine the impact of naturally occurring harmful bacteria, and ensure sustainable seed production. Although this is an essential step for shellfish hatcheries, it is currently a time-consuming manual process and prone to human error.
With funding from MIT's Abdul Latif Jameel Water and Food Systems Laboratory (J-WAFS), MIT Sea Grant is partnering with Associate Professor Otto Cordero of the Massachusetts Institute of Technology's School of Civil and Environmental Engineering and Northeastern University's The researchers are collaborating with Professor Taskin Padir and research scientist Mark Zolotas. The Experiential Robotics Institute, other members of the Aquaculture Research Corporation (ARC), and the Cape Cod Commercial Fishermen's Alliance are committed to advancing technology in the aquaculture industry. Located on Cape Cod, ARC is a leading shellfish hatchery, farm and wholesaler, playing an important role in providing high quality shellfish seed to local and regional producers.
Two MIT students joined the effort this semester, working with Robert Vincent, MIT Sea Grant's assistant director of advisory services, through the Undergraduate Research Opportunities Program (UROP).
First-year student Unyime Usua and second-year student Santiago Borrego are using microscopic images of shellfish species obtained from ARC to train machine learning algorithms that help automate the identification and counting process. The resulting user-friendly image recognition tool helps aquaculture farmers differentiate and count healthy, unhealthy, and dead shellfish larvae, improving accuracy and reducing time and effort. The purpose is
Vincent said AI is a powerful tool for environmental science that can help researchers, industry, and resource managers address long-standing pinch points in accurate data collection, analysis, prediction, and streamlining processes. I'll explain how it goes. “Funding support from programs like J-WAFS allows us to tackle these issues head-on,” he says.
ARC faces the challenge of manually quantifying larval classes, a critical step in the seed production process. “The size and number of larvae are constantly measured when they are in the growth stage. This process is important to promote optimal growth and strengthen the population,” said ARC's Larva/Nymph Production Manager. Cheryl James explains.
Developing an automatic identification and counting system can improve this step of the production process and reap time and cost benefits. “This is not an easy job,” says Vincent. “However, thanks to the guidance of Dr. Zolotas from Northeastern University's Experiential Robotics Institute and the hard work of our UROP students, we have definitely made progress.”
The UROP program benefits both researchers and students. Participating MIT UROP students in the development of these types of systems provides insight into AI applications that they have never thought of, and allows them to explore, learn, and explore themselves while contributing to solving real-world problems. You will have the opportunity to apply it.
Borrego saw this project as an opportunity to apply what he learned in class 6.390 (Introduction to Machine Learning) to real-world problems. “I was starting to have ideas about how computers could recognize images and extract information from them,” he says. “I wanted to keep exploring that.”
Usua decided to pursue this project because of its potential to have a direct impact on the industry. “I'm really interested in how machine learning can be used to make people's lives easier. We're using AI to make this counting and identification process easier for biologists. Usua didn't know much about aquaculture before starting this project, but said, “I just heard about the hatchery that Dr. Vincent was talking about and I was wondering what was going on.'' It was unfortunate that not many people knew what the problem was.” Face it again. ”
On Cape Cod alone, aquaculture is an $18 million-a-year industry. However, the Massachusetts Department of Marine and Fisheries estimates that hatcheries can only meet 70 to 80 percent of annual seed demand, impacting local producers and the economy. Through this project, the partners aim to increase seed production, improve industry capacity, and develop technologies that will help understand and improve the hatchery microbiome.
Borrego describes the first challenge: having limited data to work with. “Initially I had to go through all the data and label it, but I learned a lot through that process.” In true MIT fashion, he says he learned a lot from this project. He shares his lessons learned: You need to adapt and change your strategy according to what you have. ”
Usua describes his experience going through the research process, communicating within his team, and deciding what approach to take. “Research is a difficult and long process, but you get a lot out of it because it teaches you to look for things on your own and find solutions to problems on your own.”
In addition to increasing seed production and reducing the human labor required for the hatching process, the collaborators believe the project will contribute to cost savings and technology integration to support one of the most disadvantaged industries in the United States. I hope that you will.
Both Borrego and Usua will continue their research at MIT Sea Grant for a second semester. Borrego is interested in learning more about how technology can be used to protect the environment and wildlife. Usua said she would like to explore more projects related to aquaculture. “There seem to be an infinite number of ways to approach these problems.”
