Generative forecasting with joint probability models

TL;DR

This paper introduces a joint probabilistic generative modeling approach for forecasting chaotic dynamical systems, capturing complex dependencies and improving long-term statistical accuracy over traditional methods.

Contribution

It reframes forecasting as a joint distribution learning problem, enabling multistep trajectory generation and robust uncertainty quantification without ground truth.

Findings

Improved short-term predictive skill on Lorenz-63 and Kuramoto-Sivashinsky systems.

Better preservation of attractor geometry compared to conditional models.

More accurate long-range statistical behavior.

Abstract

Chaotic dynamical systems exhibit strong sensitivity to initial conditions and often contain unresolved multiscale processes, making deterministic forecasting fundamentally limited. Generative models offer an appealing alternative by learning distributions over plausible system evolutions; yet, most existing approaches focus on next-step conditional prediction rather than the structure of the underlying dynamics. In this work, we reframe forecasting as a fully generative problem by learning the joint probability distribution of lagged system states over short temporal windows and obtaining forecasts through marginalization. This new perspective allows the model to capture nonlinear temporal dependencies, represent multistep trajectory segments, and produce next-step predictions consistent with the learned joint distribution. We also introduce a general, model-agnostic training and inference framework for joint generative forecasting and show how it enables assessment of forecast robustness and reliability using three complementary uncertainty quantification metrics (ensemble variance, short-horizon autocorrelation, and cumulative Wasserstein drift), without access to ground truth. We evaluate the performance of the proposed method on two canonical chaotic dynamical systems, the Lorenz-63 system and the Kuramoto-Sivashinsky equation, and show that joint generative models yield improved short-term predictive skill, preserve attractor geometry, and achieve substantially more accurate long-range statistical behaviour than conventional conditional next-step models.