A Surrogate Data Assimilation Model for the Estimation of Dynamical System in a Limited Area
This work addresses computational efficiency in data assimilation for limited-area systems, which is incremental as it builds on existing DA frameworks with a novel learning-based approach.
The authors tackled the problem of efficient state estimation in limited-area dynamical systems by proposing a learning-based surrogate data assimilation model, which eliminates the need for high-dimensional model integration and lateral boundary conditions, offering significant computational advantages over traditional methods.
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.