Manolin unveiled a major set of Watershed platform updates that introduce two prescriptive tools for salmon farms: a Harvest Forecaster and a Sea Lice Treatment Recommender. Both are driven by Manolin’s modeling engine and a portfolio of 19 newly built models, the largest update since Manolin’s modeling engine upgrade in fall 2024. The models span growth, quality, mortality, salmon prices, and clustering methods that define farm-specific normal ranges, including 11 harvest-planning models and 8 clustering models used for sea lice treatment planning.
Designed for more immediate farm actions, the tools deliver cage and population-level forecasts. Each forecast includes upper, lower, and average bands up to 90 days for all active cages within an organization. For harvest planning, Manolin forecasts biomass change, expected quality, and price so teams can weigh “harvest now versus wait.” For sea lice interventions, clustering establishes each farm’s normal range, flags deviations, and guides treatment choice.
“Our ability to launch this many cage-level models comes from doing the unglamorous work of cleaning and structuring farm data for advanced modeling,” said John Costantino, CTO of Manolin. “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.”
The accuracy of the models ranges from 85-97%, and the 90-day forecast bands show the expected variability for each prediction.
The models are trained on farm-generated data from ERP systems, cameras, and environmental sensors, enriched with Manolin’s proprietary algorithms. For this release, training drew on over 265 million smolts across 2,400-plus cages.
“We’re focused on bringing together multiple data signals at the cage level,” said John Costantino, CTO of Manolin. “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.”
The company’s modeling approach and validation practices are informed by peer-reviewed work, including Manolin’s collaborative big-data study with Veramaris on EPA and DHA.
“We’re proud to launch new workflows in our platform powered by some of the most advanced models available today and get this into the hands of our customers,” said Tony Chen, CEO of Manolin. “With biomass forecasts, we’ve found that getting the best result requires modeling many interdependent patterns.”
The Harvest Forecaster and Sea Lice Treatment Recommender are available now to customers on Manolin’s Watershed platform.
