Bayesian Learning and Predictability in a Stochastic Nonlinear Dynamical Model

TL;DR

This paper applies Bayesian hierarchical methods to a nonlinear marine biogeochemical model, demonstrating how prior information and advanced computational techniques enable effective state estimation and forecasting from sparse data.

Contribution

It introduces a novel stochastic process formulation for plankton properties and demonstrates its application with Particle MCMC in a real-world case study.

Findings

Effective state and parameter estimation from sparse data

Long-term forecasts are feasible with objective priors

Novel autoregressive stochastic process model for plankton properties

Abstract

Bayesian inference methods are applied within a Bayesian hierarchical modelling framework to the problems of joint state and parameter estimation, and of state forecasting. We explore and demonstrate the ideas in the context of a simple nonlinear marine biogeochemical model. A novel approach is proposed to the formulation of the stochastic process model, in which ecophysiological properties of plankton communities are represented by autoregressive stochastic processes. This approach captures the effects of changes in plankton communities over time, and it allows the incorporation of literature metadata on individual species into prior distributions for process model parameters. The approach is applied to a case study at Ocean Station Papa, using Particle Markov chain Monte Carlo computational techniques. The results suggest that, by drawing on objective prior information, it is possible to extract useful information about model state and a subset of parameters, and even to make useful long-term forecasts, based on sparse and noisy observations.