Based on the National Oceanic and Atmospheric Administration, aquaculture in the US represents a $1.5 billion industry annually. Like land-based farming, shellfish aquaculture requires healthy seed production with a view to maintain a sustainable industry. Aquaculture hatchery production of shellfish larvae — seeds — requires close monitoring to trace mortality rates and assess health from the earliest stages of life.
Careful commentary is essential to tell production scheduling, determine effects of naturally occurring harmful bacteria, and ensure sustainable seed production. That is an important step for shellfish hatcheries but is currently a time-consuming manual process liable to human error.
With funding from MIT’s Abdul Latif Jameel Water and Food Systems Lab (J-WAFS), MIT Sea Grant is working with Associate Professor Otto Cordero of the MIT Department of Civil and Environmental Engineering, Professor Taskin Padir and Research Scientist Mark Zolotas on the Northeastern University Institute for Experiential Robotics, and others on the Aquaculture Research Corporation (A.R.C.), and the Cape Cod Business Fishermen’s Alliance, to advance technology for the aquaculture industry. Positioned on Cape Cod, A.R.C. is a number one shellfish hatchery, farm, and wholesaler that plays a significant role in providing high-quality shellfish seed to local and regional growers.
Two MIT students have joined the trouble 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 sophomore Santiago Borrego are using microscopy images of shellfish seed from A.R.C. to coach machine learning algorithms that may help automate the identification and counting process. The resulting user-friendly image recognition tool goals to help aquaculturists in differentiating and counting healthy, unhealthy, and dead shellfish larvae, improving accuracy and reducing effort and time.
Vincent explains that AI is a robust tool for environmental science that allows researchers, industry, and resource managers to deal with challenges which have long been pinch points for accurate data collection, evaluation, predictions, and streamlining processes. “Funding support from programs like J-WAFS enable us to tackle these problems head-on,” he says.
ARC faces challenges with manually quantifying larvae classes, a very important step of their seed production process. “When larvae are of their growing stages they’re always being sized and counted,” explains Cheryl James, A.R.C. larval/juvenile production manager. “This process is critical to encourage optimal growth and strengthen the population.”
Developing an automatic identification and counting system will help to enhance this step within the production process with time and price advantages. “This isn’t a straightforward task,” says Vincent, “but with the guidance of Dr. Zolotas on the Northeastern University Institute for Experiential Robotics and the work of the UROP students, we’ve got made solid progress.”
The UROP program advantages each researchers and students. Involving MIT UROP students in developing a lot of these systems provides insights into AI applications that they may not have considered, providing opportunities to explore, learn, and apply themselves while contributing to solving real challenges.
Borrego saw this project as a chance to use what he’d learned in school 6.390 (Introduction to Machine Learning) to a real-world issue. “I used to be beginning to form an idea of how computers can see images and extract information from them,” he says. “I desired to keep exploring that.”
Usua decided to pursue the project due to direct industry impacts it could have. “I’m pretty interested by seeing how we will utilize machine learning to make people’s lives easier. We’re using AI to assist biologists make this counting and identification process easier.” While Usua wasn’t accustomed to aquaculture before starting this project, she explains, “Just hearing in regards to the hatcheries that Dr. Vincent was telling us about, it was unlucky that not a variety of people know what’s happening and the issues that they’re facing.”
On Cape Cod alone, aquaculture is an $18 million per 12 months industry. However the Massachusetts Division of Marine Fisheries estimates that hatcheries are only in a position to meet 70–80 percent of seed demand annually, which impacts local growers and economies. Through this project, the partners aim to develop technology that may increase seed production, advance industry capabilities, and help understand and improve the hatchery microbiome.
Borrego explains the initial challenge of getting limited data to work with. “Starting out, we needed to undergo and label all of the information, but going through that process helped me learn loads.” In true MIT fashion, he shares his takeaway from the project: “Attempt to get the perfect out of what you’re given with the information you’ve got to work with. You’re going to should adapt and alter your strategies depending on what you’ve got.”
Usua describes her experience going through the research process, communicating in a team, and deciding what approaches to take. “Research is a difficult and long process, but there may be loads to realize from it since it teaches you to search for things on your personal and find your personal solutions to problems.”
Along with increasing seed production and reducing the human labor required within the hatchery process, the collaborators expect this project to contribute to cost savings and technology integration to support some of the underserved industries in the US.
Borrego and Usua each plan to proceed their work for a second semester with MIT Sea Grant. Borrego is interested by learning more about how technology will be used to guard the environment and wildlife. Usua says she hopes to explore more projects related to aquaculture. “It looks as if there’s an infinite amount of how to tackle these issues.”
