A Surrogate Data Assimilation Model for the Estimation of Dynamical System in a Limited Area

TL;DR

This paper introduces a learning-based surrogate data assimilation model that uses neural networks for efficient and boundary-condition-free state estimation in limited-area dynamical systems, reducing computational costs.

Contribution

It presents a novel surrogate DA model employing neural networks that eliminates the need for high-dimensional model integration and boundary conditions, based on a theoretical framework involving observability and effective regions.

Findings

Significant computational efficiency over traditional DA methods.

Elimination of boundary condition requirements in online and offline computations.

Quantitative determination of observation data needed for accurate DA.

Abstract

We propose a novel learning-based surrogate data assimilation (DA) model for efficient state estimation in a limited area. Our model employs a feedforward neural network for online computation, eliminating the need for integrating high-dimensional limited-area models. This approach offers significant computational advantages over traditional DA algorithms. Furthermore, our method avoids the requirement of lateral boundary conditions for the limited-area model in both online and offline computations. The design of our surrogate DA model is built upon a robust theoretical framework that leverages two fundamental concepts: observability and effective region. The concept of observability enables us to quantitatively determine the optimal amount of observation data necessary for accurate DA. Meanwhile, the concept of effective region substantially reduces the computational burden associated with computing observability and generating training data.