发表机构
University of Oxford; European Southern Observatory; INAF - Osservatorio Astronomico di Capodimonte; University of Warwick; Université Côte d’Azur; CNRS, Laboratoire Lagrange; V.N. Karazin Kharkiv National University; Institute of Radio Astronomy of National Academy of Science of Ukraine; Instituto de Astrofísica de Canarias; Universidad de La Laguna（牛津大学; 欧洲南方天文台; 意大利国家天体物理研究所卡波迪蒙特天文台; 华威大学; 蔚蓝海岸大学; 法国国家科学研究中心拉格朗日实验室; 哈尔科夫国立大学; 乌克兰国家科学院射电天文研究所; 加那利群岛天体物理学研究所; 拉古纳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本论文训练机器学习回归模型，从可观测星系性质重建光谱学推断的遗迹度，发现支持向量回归最佳，预测高遗迹度星系可作为后续观测目标，为广域巡天遗迹候选体选择提供基础。
AI 中文摘要
在E-INSPIRE系列的第二篇论文中，我们在约430个邻近（z<0.5）的超致密大质量星系（UCMGs）上训练了基于机器学习的回归模型，这些星系具有光谱学推断的运动学、恒星种群参数以及测得的“遗迹度”（DoR）。我们的目标是研究光谱学推断的DoR如何稳健地从可观测的星系性质中被统计重建，并探索该框架在未来广域巡天中的潜在适用性。我们测试了几种回归算法，发现支持向量回归（SVR）提供了最佳性能。我们探索了多种输入特征配置，从仅包含年龄和金属丰度的最小集，到包含恒星种群参数、运动学、结构性质及相关不确定性的更全面配置。所有测试模型在训练集上都实现了相似的高性能（R²≥0.81），除了最小配置（R²~0.78）。当在独立的INSPIRE样本（52个UCMGs）上评估时，预测能力保持稳健，尽管模型间差异有所增加。DoR分布显示出三个区域，低值（DoR<0.3）和高值（DoR>0.6）稀疏分布，导致向中间值的轻微回归收缩。然而，这种行为使得保守选择策略成为可能：预测DoR≥0.6的星系强烈偏向于真正的极端遗迹，使其成为后续观测的主要目标。这一概念验证证实了光谱学推断的DoR与可观测的恒星种群和运动学性质稳健相关，并为未来在大型测光和光谱巡天中遗迹候选体选择策略提供了第一步。
英文摘要
In this second paper of the E-INSPIRE series, we train a machine-learning-based regression on $\sim430$ nearby ($z<0.5$) ultra-compact massive galaxies (UCMGs) with spectroscopically inferred kinematics, stellar population parameters and a measured ``degree of relicness'' (DoR). Our goal is to investigate how robustly the spectroscopically inferred DoR can be statistically reconstructed from observable galaxy properties, and to explore the potential applicability of this framework to future wide-area surveys. We test several regression algorithms finding that Support Vector Regression (SVR) provides the best performance. We explore multiple input feature configurations, from a minimal set including only age and metallicity to more comprehensive ones incorporating stellar population parameters, kinematics, structural properties, and the associated uncertainties. All tested models achieve similarly high performance on the training set ($R^2\ge0.81$), except for the minimal configuration ($R^2\sim0.78$). When evaluated on an independent INSPIRE sample of 52 UCMGs, the predictive power remains robust, although with increased model-to-model variation. The DoR distribution shows three regimes, with low (DoR$<0.3$) and high (DoR$>0.6$) values sparsely populated, leading to mild regression shrinkage toward intermediate values. However, this behaviour enables a conservative selection strategy: galaxies with predicted DoR$\ge0.6$ are strongly biased toward genuine extreme relics, making them prime targets for follow-up observations. This proof-of-concept confirms that the spectroscopically inferred DoR is robustly connected to observable stellar population and kinematical properties, and provides a first step toward future relic-candidate selection strategies in large photometric and spectroscopic surveys.
Comments12 pages, 6 figures, accepted for publication in MNRAS
