Abstract:Predicting rare extreme events such as wildfires from meteorological data requires models that remain reliable under evolving environmental conditions. This problem is inherently long-tailed: wildfire events are rare but high-impact, while most observations correspond to non-fire conditions, causing standard learning objectives to underemphasize the minority class (fire) that matters most. In addition, models trained on historical distributions often fail under distribution shifts, exhibiting degraded performance in new environments. To this end, we propose Environment-Adaptive Preference Optimization (EAPO), a framework that adapts prediction to the target environment with long-tail distribution. Given a new input distribution, we first construct distribution-aligned datasets via $k$-nearest neighbor retrieval. We then perform a hybrid fine-tuning procedure on this local manifold, combining supervised learning with preference optimization, as well as emphasizing on rare extreme events. EAPO refines decision boundaries while avoiding conflicting signals from heterogeneous training data. We evaluate EAPO on a real-world wildfire prediction task with environmental shifts. EAPO achieves robust performance (ROC-AUC 0.7310) and improves detection in extreme regimes, demonstrating its effectiveness in dynamic wildfire prediction systems.
| Subjects: | Machine Learning (cs.LG); Computational Engineering, Finance, and Science (cs.CE) |
| Cite as: | arXiv:2605.12435 [cs.LG] |
| (or arXiv:2605.12435v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.12435 arXiv-issued DOI via DataCite (pending registration) |
From: Enyi Jiang [view email]
[v1]
Tue, 12 May 2026 17:31:00 UTC (230 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。