Surrogate-based optimization using an artificial neural network for a parameter identification in a 3D marine ecosystem model

TL;DR

This paper explores surrogate-based optimization using artificial neural networks to efficiently identify parameters in a 3D marine ecosystem model, significantly reducing computational costs while maintaining accuracy.

Contribution

It introduces a novel approach combining ANNs with SBO for marine ecosystem models, demonstrating improved efficiency and validation potential.

Findings

ANN-based low-fidelity models enable efficient SBO with high accuracy

Using ANNs reduces computational effort compared to traditional methods

The combined approach offers a promising tool for marine ecosystem model validation

Abstract

Parameter identification for marine ecosystem models is important for the assessment and validation of marine ecosystem models against observational data. The surrogate-based optimization (SBO) is a computationally efficient method to optimize complex models. SBO replaces the computationally expensive (high-fidelity) model by a surrogate constructed from a less accurate but computationally cheaper (low-fidelity) model in combination with an appropriate correction approach, which improves the accuracy of the low-fidelity model. To construct a computationally cheap low-fidelity model, we tested three different approaches to compute an approximation of the annual periodic solution (i.e., a steady annual cycle) of a marine ecosystem model: firstly, a reduced number of spin-up iterations (several decades instead of millennia), secondly, an artificial neural network (ANN) approximating the steady annual cycle and, finally, a combination of both approaches. Except for the low-fidelity model using only the ANN, the SBO yielded a solution close to the target and reduced the computational effort significantly. If an ANN approximating appropriately a marine ecosystem model is available, the SBO using this ANN as low-fidelity model presents a promising and computational efficient method for the validation.