The Deep Latent Space Particle Filter for Real-Time Data Assimilation with Uncertainty Quantification

TL;DR

The paper introduces the Deep Latent Space Particle Filter (D-LSPF), a neural network-based method that significantly accelerates data assimilation with uncertainty quantification in complex physical systems, enabling real-time applications.

Contribution

It presents a novel particle filter using neural surrogates and latent space reduction, achieving faster and more accurate data assimilation compared to existing methods.

Findings

Runs 3-5 times faster than alternative methods

Up to an order of magnitude more accurate

Enables real-time data assimilation with uncertainty quantification

Abstract

In Data Assimilation, observations are fused with simulations to obtain an accurate estimate of the state and parameters for a given physical system. Combining data with a model, however, while accurately estimating uncertainty, is computationally expensive and infeasible to run in real-time for complex systems. Here, we present a novel particle filter methodology, the Deep Latent Space Particle filter or D-LSPF, that uses neural network-based surrogate models to overcome this computational challenge. The D-LSPF enables filtering in the low-dimensional latent space obtained using Wasserstein AEs with modified vision transformer layers for dimensionality reduction and transformers for parameterized latent space time stepping. As we demonstrate on three test cases, including leak localization in multi-phase pipe flow and seabed identification for fully nonlinear water waves, the D-LSPF runs orders of magnitude faster than a high-fidelity particle filter and 3-5 times faster than alternative methods while being up to an order of magnitude more accurate. The D-LSPF thus enables real-time data assimilation with uncertainty quantification for physical systems.