用于河外光谱学的 SpecPT（Spectroscopy Pre-trained Transformer，光谱预训练 Transformer）模型：I. 架构与自动红移测量
SpecPT (Spectroscopy Pre-trained Transformer) Model for Extragalactic Spectroscopy: I. Architecture and Automated Redshift Measurement
AI总结：
本文提出基于 transformer 的 SpecPT 模型，利用 DESI EDR 的 BGS 与 ELG 数据验证其光谱重建和自动红移测量能力，结果显示低 NMAD、低异常值率且在 0<z<1.6 范围内稳健。
摘要：
我们介绍了 Spectroscopy Pre-trained Transformer（SpecPT，光谱预训练 Transformer），这是一种基于 transformer 的模型，旨在分析光谱数据，并应用于光谱重建和红移测量。利用 DESI 巡天的早期数据发布（EDR），我们在两个不同的数据集上评估了 SpecPT 的性能：亮星系巡天（BGS）样本和发射线星系（ELG）样本。SpecPT 成功重建了光谱，准确捕捉发射线、吸收特征和连续谱形状，同时有效降低噪声。对于红移预测，SpecPT 取得了具有竞争力的精度：在 BGS 和 ELG 上，归一化中位绝对偏差（NMAD）分别为 0.0006 和 0.0008，灾难性异常值比例分别为 0.20% 和 0.80%。值得注意的是，SpecPT 在整个红移范围（0 < z < 1.6）内均表现稳定，展示了其通用性和稳健性。通过利用其学习到的潜在表示，SpecPT 为构建基础光谱模型奠定了基础，并在异常值检测、星际介质（ISM）性质估计以及迁移到其他数据集的迁移学习方面具有潜在应用。这项工作是构建可扩展至完整 DESI 数据集乃至更广范围的通用光谱分析框架的第一步。
英文摘要：
We introduce the Spectroscopy Pre-trained Transformer (SpecPT), a transformer-based model designed to analyze spectroscopic data, with applications in spectrum reconstruction and redshift measurement. Using the Early Data Release (EDR) of the DESI survey, we evaluate SpecPT's performance on two distinct datasets: the Bright Galaxy Survey (BGS) and Emission Line Galaxy (ELG) samples. SpecPT successfully reconstructs spectra, accurately capturing emission lines, absorption features, and continuum shapes while effectively reducing noise. For redshift prediction, SpecPT achieves competitive accuracy, with Normalized Median Absolute Deviation (NMAD) values of 0.0006 and 0.0008, and catastrophic outlier fractions of 0.20% and 0.80% for BGS and ELG, respectively. Notably, SpecPT performs consistently well across the full redshift range ($0 < z < 1.6$), demonstrating its versatility and robustness. By leveraging its learned latent representations, SpecPT lays the groundwork for a foundational spectroscopic model, with potential applications in outlier detection, interstellar medium (ISM) property estimation, and transfer learning to other datasets. This work represents a first step in building a generalized framework for spectroscopic analysis, capable of scaling to the full DESI dataset and beyond.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
