Inferring, Predicting, and Denoising Causal Wave Dynamics

TL;DR

DISTANA is a novel neural network architecture designed to model, predict, and denoise complex spatial-temporal wave dynamics, outperforming existing methods in stability and accuracy for real-world applications.

Contribution

The paper introduces DISTANA, a new generative recurrent graph convolution neural network architecture tailored for causality inference and denoising in spatially distributed dynamical systems.

Findings

DISTANA outperforms temporal convolution networks and ConvLSTMs on wave propagation benchmarks.

It produces stable, accurate predictions over hundreds of time steps.

DISTANA effectively filters noise, with potential improvements via autoencoder principles.

Abstract

The novel DISTributed Artificial neural Network Architecture (DISTANA) is a generative, recurrent graph convolution neural network. It implements a grid or mesh of locally parameterizable laterally connected network modules. DISTANA is specifically designed to identify the causality behind spatially distributed, non-linear dynamical processes. We show that DISTANA is very well-suited to denoise data streams, given that re-occurring patterns are observed, significantly outperforming alternative approaches, such as temporal convolution networks and ConvLSTMs, on a complex spatial wave propagation benchmark. It produces stable and accurate closed-loop predictions even over hundreds of time steps. Moreover, it is able to effectively filter noise -- an ability that can be improved further by applying denoising autoencoder principles or by actively tuning latent neural state activities retrospectively. Results confirm that DISTANA is ready to model real-world spatio-temporal dynamics such as brain imaging, supply networks, water flow, or soil and weather data patterns.