# Physical Consistency of Aurora's Encoder: A Quantitative Study

arXiv: https://arxiv.org/abs/2511.07787 · HTML: https://mlsanity.com/paper/2511.07787/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 4 references that are in the map.
- First posted on arXiv 11 Nov 2025.

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

- [Does Aurora Encode Atmospheric Structure? Latent Regime Analysis and Attribution](https://mlsanity.com/paper/2606.26361/) (2026)

## Abstract (arXiv)

The high accuracy of large-scale weather forecasting models like Aurora is often accompanied by a lack of transparency, as their internal representations remain largely opaque. This "black box" nature hinders their adoption in high-stakes operational settings. In this work, we probe the physical consistency of Aurora's encoder by investigating whether its latent representations align with known physical and meteorological concepts. Using a large-scale dataset of embeddings, we train linear classifiers to identify three distinct concepts: the fundamental land-sea boundary, high-impact extreme temperature events, and atmospheric instability. Our findings provide quantitative evidence that Aurora learns physically consistent features, while also highlighting its limitations in capturing the rarest events. This work underscores the critical need for interpretability methods to validate and build trust in the next generation of Al-driven weather models.