Using machine learning to inform harvest control rule design in complex fishery settings
This work addresses a long-standing and difficult problem in fishery science for managers and ecologists dealing with complex, stochastic populations like Walleye fisheries in Alberta, Canada, representing an incremental improvement by applying machine learning tools to a specific domain.
The study tackled the problem of designing harvest control rules for complex, partially observed, age-structured fish populations with variable recruitment dynamics, using reinforcement learning and Bayesian optimization, and found that numerically optimized policies outperformed standard reference-point-based policies, with the addition of mean fish weight observations improving policy decisions.
In fishery science, harvest management of size-structured stochastic populations is a long-standing and difficult problem. Rectilinear precautionary policies based on biomass and harvesting reference points have now become a standard approach to this problem. While these standard feedback policies are adapted from analytical or dynamic programming solutions assuming relatively simple ecological dynamics, they are often applied to more complicated ecological settings in the real world. In this paper we explore the problem of designing harvest control rules for partially observed, age-structured, spasmodic fish populations using tools from reinforcement learning (RL) and Bayesian optimization. Our focus is on the case of Walleye fisheries in Alberta, Canada, whose highly variable recruitment dynamics have perplexed managers and ecologists. We optimized and evaluated policies using several complementary performance metrics. The main questions we addressed were: 1. How do standard policies based on reference points perform relative to numerically optimized policies? 2. Can an observation of mean fish weight, in addition to stock biomass, aid policy decisions?