发表机构
Università del Salento; INFN, Sezione di Lecce; INAF, Sezione di Lecce（萨伦托大学; 意大利国家核物理研究所莱切分部; 意大利国家天体物理研究所莱切分部）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
LUMA是一个轻量级CNN流水线，通过物理预处理和紧凑网络在模拟数据上实现约96%准确率和0.99 AUC，为强引力透镜搜索提供高效基线。
AI 中文摘要
我们提出了LUMA，一个用于在模拟天文成像中自动检测强引力透镜的卷积神经网络（CNN）流水线。该方法结合了一个物理动机驱动的预处理阶段，该阶段增强微弱的弧和环特征，以及一个紧凑的三块CNN，该CNN使用类别重新加权和现代学习率调度进行训练。在模拟数据上，模型对非平凡类别达到了约96%的测试准确率和约0.99的接收者操作特征（ROC）曲线下面积（AUC）值，而混淆矩阵分析显示透镜候选具有高完整性和纯度。这些结果表明，相对轻量级的CNN架构可以为强透镜搜索提供有竞争力的基线，并激励未来向真实巡天图像和基于Transformer的模型的扩展。
英文摘要
We present LUMA, a convolutional neural network (CNN) pipeline for the automated detection of strong gravitational lenses in simulated astronomical imaging. The method combines a physically motivated preprocessing stage, which enhances faint arc and ring features, with a compact three-block CNN trained using class reweighting and modern learning-rate scheduling. On simulated data, the model reaches test accuracies of about $96$\% and receiver operating characteristic (ROC) area-under-the-curve (AUC) values of $\simeq 0.99$ for the non-trivial classes, while confusion-matrix analysis shows high completeness and purity for lens candidates. These results demonstrate that relatively lightweight CNN architectures can provide a competitive baseline for strong-lens searches, and they motivate future extensions toward real survey images and transformer-based models.
CommentsAccepted for publication in Astronomy and Computing, 2027, Corresponding Author: G.V. Donatiello (see associated pdf for useful e-mail addresses). 14 Pages, 8 Figures, 3 Tables
DOI：10.1016/j.ascom.2026.101198}{10.1016/j.ascom.2026.101198
