# Tracing the Unlabeled Storm: Cross-Variable Transfer in a Lagrangian Atmospheric JEPA Framework

arXiv: https://arxiv.org/abs/2608.22358 · HTML: https://mlsanity.com/paper/2608.22358/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 1 of its 47 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 1 of 1)

- [A Foundation Model for the Earth System](https://mlsanity.com/paper/2405.13063/) (2024)

## Built on by (most cited first, 1 of 1)

- [S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales](https://mlsanity.com/paper/2610.03106/) (2026)

## Abstract (arXiv)

Deep atmospheric convection governs South Asian monsoon variability, yet attempting to learn its latent world model directly from zero-inflated, heavy-tailed precipitation yields suboptimal predictive representations. Continuous atmospheric proxies, such as outgoing longwave radiation (OLR), express this convective organization far more coherently. We address this mismatch with cross-variable proxy learning: M-JEPA, a multiscale Monsoon Joint-Embedding Predictive Architecture, is pretrained on five continuous proxy fields over Lagrangian patches tracking moving convective systems---without rainfall supervision at any point. The resulting frozen representation is transferred to daily precipitation forecasts through a shared decoder trunk featuring parallel probabilistic and deterministic branches. Because rainfall is strictly unobserved during pretraining, downstream skill directly measures the predictive information captured in the latent rollout. A frozen-backbone probing framework with two controls (an identical architecture trained on rainfall alone, and a randomly initialized backbone) attributes the transfer specifically to proxy pretraining: direct rainfall training exhibits 36% higher CRPS error (7.52 vs. 5.54,mm/day). Against the 51-member operational ECMWF ensemble, the transferred model attains a statistically resolved CRPS advantage (6.81 vs. 6.89,mm/day) and higher Brier skill (+0.05 vs. -0.04) using 15.4M parameters on a single consumer GPU, concentrated at heavy-rain thresholds and fine spatial scales, while the ensemble retains an advantage in neighborhood skill and deterministic references on point metrics. The result provides a competitive monsoon precipitation forecast grounded in intraseasonal dynamics and a diagnostic framework for evaluating transferred atmospheric representations.