Time Series Classification on Salmon Harvest Deviation

In Spring 2025, ReLU built on the findings from the Autumn 2024 project to develop a predictive model for Salmon Harvest Deviation.

We framed the task as a classification problem, aiming to predict whether the harvest deviation at the end of a farming cycle would be high or low. To address this, we explored a range of models, from traditional approaches like ARIMA and XGBoost to more advanced time series classifiers such as LSTM and ROCKET.

Our final deliverable was an ensemble classification model that integrated several of these techniques. This was accompanied by a comprehensive report outlining our methodology, model performance, and the results of supplementary experiments.

  • Grieg Seafood is an international seafood company specializing in fresh Atlantic salmon. Headquartered in Bergen, Norway, the company operates fish farms in Rogaland and Finnmark in Norway, British Columbia, and Shetland. Annually, Grieg Seafood produces significant quantities of salmon, primarily serving the North American and Asian markets.

    The company was founded as a subsidiary of the Grieg Group and is listed on the Oslo Stock Exchange. It has a history of expansion and innovation, including a merger with the Volden Group and past operations in Denmark and Chile. Grieg Seafood is recognized for its commitment to sustainable practices, having been awarded by the Global Aquaculture Alliance for Best Aquaculture Practices. It is a major player in the salmon farming industry, particularly in British Columbia, Canada.