# Latent assimilation with implicit neural representations for unknown dynamics

Source: [Latent assimilation with implicit neural representations for unknown dynamics](<https://www.sota2.com/research/paper/68fa469d1e209131ce921a8b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T05:54:05.097Z

Authors: Zhuoyuan Li, Bin Dong, Pingwen Zhang

Published: 2023-09-18T08:33:23.000Z

## Abstract

Data assimilation is crucial in a wide range of applications, but it often faces challenges such as high computational costs due to data dimensionality and incomplete understanding of underlying mechanisms. To address these challenges, this study presents a novel assimilation framework, termed Latent Assimilation with Implicit Neural Representations (LAINR). By introducing Spherical Implicit Neural Representations (SINR) along with a data-driven uncertainty estimator of the trained neural networks, LAINR enhances efficiency in assimilation process. Experimental results indicate that LAINR holds certain advantage over existing methods based on AutoEncoders, both in terms of accuracy and efficiency.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Data Assimilation on Example 2 Advection-diffusion-reaction system](<https://www.sota2.com/research/sota/data-assimilation-on-example-2-advection-diffusion-reaction-system.md>): Data Assimilation; Example 2 Advection-diffusion-reaction system; Relative Error (ERel,1:T): 22.13.

- [Data Assimilation on 100-dimensional nonlinear toy dynamical system (test)](<https://www.sota2.com/research/sota/data-assimilation-on-100-dimensional-nonlinear-toy-dynamical-system-test.md>): Data Assimilation; 100-dimensional nonlinear toy dynamical system (test); Relative Error (1:T): 21.106.

- [Data Assimilation on Lorenz-96 Delta t = 0.1](<https://www.sota2.com/research/sota/data-assimilation-on-lorenz-96-delta-t-0-1.md>): Data Assimilation; Lorenz-96 Delta t = 0.1; Relative RMSE: 0.7254.

- [Data Assimilation on Lorenz-96 Delta t = 0.2](<https://www.sota2.com/research/sota/data-assimilation-on-lorenz-96-delta-t-0-2.md>): Data Assimilation; Lorenz-96 Delta t = 0.2; Relative RMSE: 0.659.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2309.09574>)

[PDF](<https://arxiv.org/pdf/2309.09574.pdf>)
