The models were trained on data from over 265 million smolts across more than 2,400 cages.
Manolin
The U.S.-based aquaculture technology company Manolin has launched two new prescriptive tools for salmon farms, marking the largest update to its services to date.
The Harvest Forecaster and Sea Lice Treatment Recommender provide cage- and population-level forecasts, and include 11 models for harvest planning and 8 clustering models used for planning sea lice treatments.
Additionally, to determine the optimal harvest time, these tools forecast biomass changes, expected quality, and price. Each forecast includes upper, lower, and average bands of up to 90 days for all active cages.
"By tying all past events and normalized product usages to each population we are able to forecast and recommend on the reality of what is going on in a cage rather than the perception, which is why many of the models out there right now struggle to generalize well especially when dealing with longer term predictions," explained John Costantino, CTO of Manolin.
Manolin has developed these models using farm-generated data from ERP systems, cameras, and environmental sensors, processed with the American company's proprietary algorithms. The models were trained on data from over 265 million smolts across more than 2,400 cages, with accuracy ranging between 85% and 97%.
"We're focused on bringing together multiple data signals at the cage level. This is the first iteration, trained on a small subset of our network data; as we add more context, we expect performance to continue improving," added Costantino.
