Latent State Inference in a Spatiotemporal Generative Model

TL;DR

This paper introduces an enhanced spatiotemporal neural network architecture, DISTANA, capable of inferring hidden causal factors from time series data, demonstrated through weather prediction and land-sea mask inference.

Contribution

The paper presents an improved DISTANA model combined with active tuning for reliable latent state inference in spatiotemporal processes, requiring fewer parameters and achieving better accuracy.

Findings

DISTANA outperforms temporal CNNs in prediction accuracy.

It can infer hidden causal factors like land-sea masks from temperature data.

The approach improves future temperature predictions using inferred latent states.

Abstract

Knowledge about the hidden factors that determine particular system dynamics is crucial for both explaining them and pursuing goal-directed interventions. Inferring these factors from time series data without supervision remains an open challenge. Here, we focus on spatiotemporal processes, including wave propagation and weather dynamics, for which we assume that universal causes (e.g. physics) apply throughout space and time. A recently introduced DIstributed SpatioTemporal graph Artificial Neural network Architecture (DISTANA) is used and enhanced to learn such processes, requiring fewer parameters and achieving significantly more accurate predictions compared to temporal convolutional neural networks and other related approaches. We show that DISTANA, when combined with a retrospective latent state inference principle called active tuning, can reliably derive location-respective hidden causal factors. In a current weather prediction benchmark, DISTANA infers our planet's land-sea mask solely by observing temperature dynamics and, meanwhile, uses the self inferred information to improve its own future temperature predictions.