2. Project summary oysters are economically important, but their natural populations have drastically declined, and oyster aquaculture is necessary to meet market demand

The National Oceanic and Atmospheric Administration (NOAA) awarded a $738,406 Cooperative Agreement under the Sea Grant Support program (CFDA 11.417) to the Marine Environmental Sciences Consortium (MESC), doing business as the Dauphin Island Sea Lab, for a project period from September 1, 2024 to August 31, 2027.

The purpose of this Cooperative Agreement is to develop a machine learning tool that can predict optimal locations for off-bottom oyster farming along the Alabama coast. To achieve this, the project will collect data on oyster growth, survival, feeding efficiency, water quality, and other environmental parameters through a combination of in-situ research and citizen science efforts. This data will be used to train the machine learning model, which will then be made available as an online tool to help industry partners, state agencies, and non-profit organizations identify suitable sites for oyster aquaculture development and oyster population restoration.

Off-bottom oyster farming, where oysters are grown suspended above the sediment, is on the rise in alabama because IT reduces losses related to poor water quality and predation. However, there is considerable upfront investment both in permitting time and startup costs to create an oyster farm. Appropriate site selection and use of the correct aquaculture practices are paramount to maximize oyster survival and growth to increase yield. Using a combination of in-situ research and machine learning, we will create a model to ascertain the best locations for oyster farming. Data needed for this model includes oyster growth and survival, oyster feeding efficiency, and water quality data such as temperature, salinity, and chlorophyll a (as a measure of food availability for oysters). We will collect these data for the model in a variety of ways. Citizen scientists in the oyster gardening program will raise oysters and provide oyster growth and water quality (salinity, temperature) data in conjunction with our team. Oyster feeding efficiency will be assessed by our team using an in-situ filter feeding technique at multiple sites along the coast. These data will be used to develop a machine learning tool that will create a model to predict oyster growth and survival. The goal is to create a tool whereby water quality and other parameters can be entered into an online form, and AI will rank site suitability for oyster farming. Having a tool that will allow short term data to be used to assess site suitability for oyster aquaculture will benefit industry partners as well as state agencies to inform permitting and nonprofit organizations that seek to restore oyster populations.