L2M – Deep Learning-Based Detection and Classification of Biofouling on Marine Surfaces

The maritime industry faces significant challenges from biofouling—the buildup of marine organisms on vessel hulls—which leads to higher fuel costs, increased carbon emissions, and frequent maintenance. Traditionally, biofouling inspections are manual, costly, and time-consuming, offering limited real-time insights. Our project seeks to address these inefficiencies by developing an AI-powered model to automate the detection and classification of biofouling on vessel surfaces. This technology will provide accurate, timely data to optimize maintenance and improve vessel efficiency.
Over a four-month internship, our team will focus on three main objectives to advance and commercialize this technology. First, we will validate the performance of our AI model in real-world marine environments by capturing and analyzing biofouling data using high-resolution underwater cameras. Second, we aim to refine our business model by conducting market research and engaging directly with shipping companies and regulatory bodies to develop a value proposition that addresses their specific needs. Lastly, we will establish strategic partnerships with marine technology companies specializing in drones and remotely operated vehicles (ROVs) to facilitate broader integration and market reach.
This project not only aims to improve operational efficiency in the maritime industry but also to support sustainability by reducing fuel consumption and emissions. Our expertise in AI, machine learning, and marine systems engineering, combined with a focus on commercialization strategies, will help bring this innovative solution to the market, addressing a critical need for the maritime sector.

Faculty Supervisor:

Lihong Zhang

Student:

Partner:

Springboard Atlantic Inc.

Discipline:

Engineering

Sector:

Artificial Intelligence; Transportation (excluding aerospace); Ocean Tech

University:

Memorial University of Newfoundland

Program: