发表机构
Leiden University; Deutsches Elektronen-Synchrotron (DESY); Humboldt-Universität zu Berlin（莱顿大学; 德国电子同步加速器; 柏林洪堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出与宿主无关的概率随机森林分类框架，利用ZTF光变曲线特征，经留一法验证，其对模糊TDE候选体鲁棒性优于XGBoost，还识别出新候选TDE，可避免低信噪比下的过度自信误分类。
AI 中文摘要
在大型光度巡天中对潮汐瓦解事件（TDE）进行分类颇具挑战，因为确定性机器学习模型在数据质量波动及低信噪比条件下会产生过度自信的误分类。现有的基于光变曲线的方法未纳入测量不确定性，导致输出结果不稳定。本文提出一种与宿主无关、感知不确定性的分类框架，采用概率随机森林（PRF）。该流程从兹威基瞬变巡天（ZTF）警报流中的核瞬变提取11个特征，包括上升和衰减时标、黑体温度演化及瞬变前变率指标；仅依赖光度数据、无需宿主星系信息，确保对鲁宾望远镜预期的暗弱瞬变群体有效。将特征测量视为分布的PRF，通过留一法交叉验证与XGBoost对比评估，结果显示其对模糊候选体的稳定性和鲁棒性优于XGBoost；两类分类器适用互补场景：XGBoost在平衡及高精度场景下召回率更高，其刚性决策边界可有效区分类TDE源，而PRF通过惩罚特征不确定性大的源，拒绝更多假阳性。将该框架应用于存档数据，从未分类群体中识别出11个新候选TDE，还在现有训练标签中发现3个曾被误分类为超新星或活动星系核的潜在光度TDE。本研究表明，利用光度光变曲线特征可可靠识别TDE，提供了与宿主无关的框架；感知不确定性的概率分类器对鲁宾时代至关重要，可避免确定性模型在低信噪比下固有的过度自信误分类问题。
英文摘要
The classification of Tidal Disruption Events in large-scale photometric surveys is challenging because deterministic machine learning models produce overconfident misclassifications under varying data quality and low signal-to-noise conditions. Existing lightcurve-based approaches fail to incorporate measurement uncertainties, consequently generating brittle outputs. We present a host-agnostic, uncertainty-aware classification framework using a Probabilistic Random Forest (PRF). Our pipeline extracts 11 characteristic features from nuclear transients in the ZTF alert stream, including rise and decay timescales, blackbody temperature evolution, and pre-transient variability metrics. Relying exclusively on photometric data without host galaxy information ensures effectiveness for the faint transient population expected from the Rubin Observatory. The PRF, which treats feature measurements as distributions, was evaluated against XGBoost through Leave-One-Out Cross-Validation. It yields higher stability and robustness for ambiguous candidates than XGBoost. The two classifiers occupy complementary regimes. XGBoost achieves higher recall in balanced and high-precision scenarios, where its rigid decision boundaries efficiently isolate TDE-like sources, while PRF rejects more false positives by penalizing sources with large feature uncertainties. Applying this framework to archival data identified 11 new candidate TDEs from the unclassified population and 3 potential photometric TDEs within existing training labels previously misclassified as supernovae or active galactic nuclei. This work demonstrates that TDEs can be reliably identified using photometric lightcurve features, providing a host-independent framework. Uncertainty-aware, probabilistic classifiers are essential for the Rubin era to prevent the overconfident misclassifications inherent in deterministic models at low signal-to-noise.
Comments22 pages,18 figures
