Towards Machine Learning-based Fish Stock Assessment

TL;DR

This paper explores a hybrid approach combining classical statistical models with machine learning, specifically gradient boosted trees, to improve the accuracy of fish stock assessments amid changing ecosystems.

Contribution

It introduces a novel hybrid model that enhances traditional fish stock assessment methods with supervised machine learning for better forecasting accuracy.

Findings

Improved forecast accuracy for recruitment and spawning stock biomass.

Hybrid model outperforms classical models in most tested cases.

Demonstrates the potential of ML to enhance fisheries management.

Abstract

The accurate assessment of fish stocks is crucial for sustainable fisheries management. However, existing statistical stock assessment models can have low forecast performance of relevant stock parameters like recruitment or spawning stock biomass, especially in ecosystems that are changing due to global warming and other anthropogenic stressors. In this paper, we investigate the use of machine learning models to improve the estimation and forecast of such stock parameters. We propose a hybrid model that combines classical statistical stock assessment models with supervised ML, specifically gradient boosted trees. Our hybrid model leverages the initial estimate provided by the classical model and uses the ML model to make a post-hoc correction to improve accuracy. We experiment with five different stocks and find that the forecast accuracy of recruitment and spawning stock biomass improves considerably in most cases.