arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.07960astro-ph.GAastro-ph.IM
收藏

用混合长短期记忆网络-混合密度网络增强大型综合巡天望远镜的测光红移估计

Enhancing Photometric Redshift Estimation for LSST with a Hybrid LSTM-Mixture Density Network

Shanghai Normal University（上海师范大学）；Department of Physics, Shanghai Normal University（上海师范大学物理系）

Zhijian Luo, Yangyang Li, Xinyu Luo, Hubing Xiao, Wei Fang, Shaohua Zhang, Chenggang Shu

发表信息：
A&A 714, A121 (2026)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

研究针对大型综合巡天望远镜测光红移估计问题，提出LSTM-MDNz架构，结合长短期记忆网络与混合密度网络，在HSC数据集上评估性能，相比贝叶斯神经网络基线，提高点估计精度，降低异常值率，实现良好概率校准并能构建高纯度目录。

摘要：

准确的测光红移估计和可靠的不确定性量化对于大型综合巡天望远镜实现其精确宇宙学目标至关重要。传统机器学习算法大多局限于点估计，难以刻画红移概率密度函数的多峰性质以及颜色-红移空间中的简并性。为此，我们提出并验证了长短期记忆网络-混合密度网络（LSTM-MDNz）架构，它将序列特征提取与灵活的概率密度建模相结合，以提高在宽红移范围内的预测准确性和不确定性校准，从而满足下一代宇宙学分析所需的严格数据质量要求。该框架将多波段测光视为按波长排序的序列，利用长短期记忆网络捕捉光谱能量分布中的非线性演化相关性，然后使用混合密度网络通过高斯混合模型明确建模后验概率密度函数。在HSC星系机器学习数据集上评估性能，并与琼斯等人（2024年）建立的贝叶斯神经网络架构进行基准测试。所提出的模型始终优于贝叶斯神经网络基线，在点估计精度上提高了约10%，一般和灾难性异常值率降低了约20%。均匀概率积分变换分布证实了概率输出的良好校准。此外，基于概率密度函数的置信度度量z_conf能够构建高纯度目录：排除约4%的极低置信度（z_conf < 0.05）样本可使总体异常值率降低约48%。

英文摘要：

Accurate photometric redshift (photo-$z$) estimation and robust uncertainty quantification are essential for the LSST to achieve its precision cosmology goals. Traditional machine learning algorithms are largely restricted to point estimates, struggling to characterize the multimodal nature of redshift PDFs and the degeneracies within the color-redshift space. To address this, we present and validate the LSTM-MDNz architecture, which integrates sequential feature extraction with flexible probability density modeling to enhance both prediction accuracy and uncertainty calibration across a broad redshift range, thereby meeting the stringent data quality requirements necessitated by next-generation cosmological analysis. The LSTM-MDNz framework treats multi-band photometry as wavelength-ordered sequences, utilizing LSTM networks to capture non-linear evolutionary correlations across the SED. A Mixture Density Network (MDN) is then employed to explicitly model posterior PDFs via Gaussian mixture models (GMMs). Performance is evaluated on the HSC GalaxiesML dataset (which serves as a small-scale proxy for next-generation surveys like LSST) and benchmarked against the BNN architecture established by Jones et al. (2024). The proposed model consistently outperforms the BNN baseline, achieving a $\sim 10\%$ improvement in point-estimation accuracy (specifically across RMSE, MAE, scatter, and $σ_{\text{NMAD}}$) and a $\sim 20\%$ reduction in the rates of both general and catastrophic outliers. A uniform probability integral transform (PIT) distribution confirms well-calibrated probabilistic outputs. Furthermore, the PDF-based confidence metric $z_{\text{conf}}$ enables high-purity catalog construction: excluding just approximately $4\%$ of extremely low-confidence ($z_{\text{conf}} < 0.05$) samples reduces the overall outlier rate by $\sim 48\%$.

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。

↑