Metraipolis › archive › dc_f3b45fc96368
Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events — arXiv:2609.30746
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30746
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:10:40.379Z
- SHA-256 of the archived text
6e2bb810b9a1eeef6bfe342494944846cb4d79a7fc71ba10aa707d9d72675ed6- Stable URL of this page
https://metraipolis.com/documento/dc_f3b45fc96368
How to cite
Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events — arXiv:2609.30746 — arXiv (en), https://arxiv.org/abs/2609.30746 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3b45fc96368 (Metraipolis archive dc_f3b45fc96368, sha256 6e2bb810b9a1eeef6bfe342494944846cb4d79a7fc71ba10aa707d9d72675ed6)
BibTeX
@misc{dcf3b45fc96368,
title = {Mechanism-Aware Ensemble Conditioning for Data-Limited Emulation of Extreme Events — arXiv:2609.30746},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30746},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3b45fc96368; sha256 6e2bb810b9a1eeef6bfe342494944846cb4d79a7fc71ba10aa707d9d72675ed6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30746. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Extreme events in chaotic systems are difficult to learn from short trajectories because they are controlled by transient finite-time instability rather than by frequently observed bulk dynamics. We propose a mechanism-aware conditioning plug-in framework that turns a nudged coarse ensemble into a non-intrusive sensor of local instability geometry. In the small-noise regime, the ensemble covariance aggregates the same finite-time deformation kernels that govern local instability, providing a Jacobian-free proxy for the local amplification structure around a synchronized coarse trajectory. A small FiLM module injects statistics of this ensemble geometry into an otherwise unchanged backbone while leaving the coarse simulator unchanged. We demonstrate this interface in two distinct pipelines: a Transformer-style residual-attention corrector for a controlled low-dimensional chaotic system and a probabilistic recurrent STORN corrector for topographic two-layer quasi-geostrophic (QG) flow. In the low-dimensional benchmark, ensemble covariance directions co-activate with OTD modes and FiLM conditioning improves 99th-percentile exceedance-frequency errors over an identical no-context Transformer baseline. In QG, a fixed ensemble-conditioned FiLM-STORN model trained on only \(50\) time units substantially improves long-horizon rare-event statistics in the data-limited regime, including density-tail errors, exceedance frequencies, and spatial exceedance-area distributions relative to an unconditioned STORN trained on the same data; on averaged high-threshold exceedance diagnostics, it also outperforms the baseline STORN trained with $20$ times more high-resolution data. These results show that local instability geometry is not merely interpretable post hoc, but an actionable conditioning signal for data-efficient rare-event emulation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Dynamical Systems (math.DS); Atmospheric and Oceanic Physics (physics.ao-ph). Pagina del lavoro: https://arxiv.org/abs/2609.30746 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T01:43:06.695Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).