Bryton Shang ’12 Applies Machine Learning to Fish Farming in Norway

Placeholder author icon
By Francesca Billington ’19

Published Oct. 3, 2018

2 min read

Image

Bryton Shang ’12

Courtesy Bryton Shang

Bryton Shang ’12 wasn’t the traditional college entrepreneur. As an operations research and financial engineering (ORFE) major who graduated early with advance standing, he ignored the advice of professors who urged him to apply for grad school, choosing instead to work at a hedge fund in New York. When the firm shut down, he started his own trading fund with his former managing director and later co-founded and incubated two startups — iQ License, a brand licensing platform, and Nikao Investments, a proprietary trading firm.

In 2017, Shang moved on to his next project: applying machine learning and data science to fish farming, the fastest growing sector of food production and the most efficient way to grow protein. New Enterprise Associates and Princeton’s Alumni Entrepreneurs Fund became the first two investors in his company, Aquabyte.

Shang spent months visiting farms in Washington, Maine, and Canada until he landed in Norway, home to a massive fish farming industry unknown to most people in the U.S. Farmers there told him that over half the cost of operating the farm comes from feed. With his background in data analysis and machine learning, Shang wanted to determine how to optimally feed the fish given how hungry they are, their metabolic requirements, and the environmental conditions in which they live. This would both drive down costs for farmers and create an environmentally sustainable process. “At the core of it, this turned into a very ORFE-like problem,” Shang said.

Aquabyte works with manufacturers to create camera systems that are installed in the fish pens. Photos are then transferred and run through software that uses computer vision algorithms to build a model approach for each farmer based on the data. For instance, the software looks for the presence of sea lice attached to the fish — parasites that usually kill wild salmon. Once the camera is installed, the customers have access to a website with analytics to help them more effectively run their farms. Other companies in Norway build expensive cameras for similar purposes, but Aquabyte aims to differentiate itself with cheaper equipment and more sophisticated software.

Shang now has five employees on the ground in Norway and 10 others working out of Aquabyte’s San Francisco office. Of his employees — some engineers and researchers, some former fish farmers, biologists, or oceanography experts — four are Princeton alumni. The company has started trials with a couple farms in Norway and later this year, it will commercialize its first product. After the company grows and gains customers, Shang wants to expand to new geographies where salmon are farmed, and expand his method for farmers growing different species of fish.

“In finance, at every given time period you have to figure out what your asset allocation is and your portfolio stocks to buy and sell them,” Shang said. “In fish farming, it’s almost analogous. At any given instant you’re amalgamating information on the temperature, oxygen, activity, and making a decision on feeding. We’re using a lot of the same tools and techniques [that I learned in ORFE].”

0 Responses

Join the conversation

Plain text

Full name and Princeton affiliation (if applicable) are required for all published comments. For more information, view our commenting policy. Responses are limited to 500 words for online and 250 words for print consideration.

Related News

Newsletters.
Get More From PAW In Your Inbox.

Learn More

Title complimentary graphics