Latent-Constrained Conditional VAEs for Augmenting Large-Scale Climate Ensembles

TL;DR

This paper introduces a latent-constrained conditional VAE approach to generate additional climate data realizations, improving generalization across ensemble members and enabling spatial prediction of climate variables.

Contribution

The paper proposes a novel latent-constrained CVAE with shared anchors and Gaussian process regression for climate ensemble augmentation, addressing generalization and spatial prediction challenges.

Findings

Latent-constrained CVAE improves generalization across ensemble members.

Using five realizations balances spatial coverage and reconstruction quality.

Latent space neighbor distance affects spatial prediction accuracy.

Abstract

Large climate-model ensembles are computationally expensive; yet many downstream analyses would benefit from additional, statistically consistent realizations of spatiotemporal climate variables. We study a generative modeling approach for producing new realizations from a limited set of available runs by transferring structure learned across an ensemble. Using monthly near-surface temperature time series from ten independent reanalysis realizations (ERA5), we find that a vanilla conditional variational autoencoder (CVAE) trained jointly across realizations yields a fragmented latent space that fails to generalize to unseen ensemble members. To address this, we introduce a latent-constrained CVAE (LC-CVAE) that enforces cross-realization homogeneity of latent embeddings at a small set of shared geographic 'anchor' locations. We then use multi-output Gaussian process regression in the latent space to predict latent coordinates at unsampled locations in a new realization, followed by decoding to generate full time series fields. Experiments and ablations demonstrate (i) instability when training on a single realization, (ii) diminishing returns after incorporating roughly five realizations, and (iii) a trade-off between spatial coverage and reconstruction quality that is closely linked to the average neighbor distance in latent space.