高能暂现源 · 每日文献综述

HIGH-ENERGY TRANSIENTS · DAILY LITERATURE REVIEW
2026 年 6 月 15 日 星期一 · 数据截至 arXiv / ADS 最新收录日
I.

今日头条

No Breaking · 无突发
今日无通过复核的重大进展

当日 1 篇核心与相关文献均为常规推进,核心 1 篇已按优先级列于下方。

II.

核心文献

1 篇
01
优先级 90 · 高能暂现天体 · Einstein Probe

M-EPDet: Real-time Real─Bogus Classification and Transient Candidate Judgement for the EP-WXT Pipeline via Multimodal Data

M-EPDet:基于多模态数据的EP-WXT管线实时真伪分类与暂现候选体判定

Lang Chen (National Astronomical Observatories, Chinese Academy of Sciences), Yunfei Xu (National Astronomical Observatories, Chinese Academy of Sciences), Zhen Zhang (National Astronomical Observatories, Chinese Academy of Sciences) et al.

原文摘要Abstract

The Wide-field X-ray Telescope (WXT) on board the Einstein Probe (EP) produces a large postdetection candidate stream in which genuine astrophysical sources coexist with instrumental artifacts and cosmic-ray events. We present M-EPDet, a three-step postdetection framework for real-time candidate vetting in EP-WXT lobster-eye micropore optics (MPO) data. The framework combines a ResNet-based arm filter, a dual-branch temporal─spectral cosmic-ray filter, and a background-aware Bayesian Blocks module for single-exposure variability screening. Using on-orbit EP-WXT observations, we report decoupled metrics for the cascading system. M-EPDet achieves a real─bogus recall of 98.31% (98.53% × 99.78%) for genuine astrophysical sources, together with rejection rates of 92.99% for instrumental artifacts and 98.18% for cosmic-ray events. In the final step, the Bayesian Blocks module flags 0.75% of the postfiltration observations, corresponding to a 99.25% reduction in candidate volume. The system is deployed in the EP-WXT pipeline as a lightweight real-time service, reducing the manual-inspection burden in candidate vetting.

展开 ▾
AI 综述 AI-generated · 以原文为准
亮点

首次针对EP-WXT龙虾眼光学数据设计空间-时域-能谱多模态级联架构,在保留98.31%真实源的同时排除93%以上仪器伪影和98%以上宇宙线;末端引入贝叶斯块进行背景感知的变异性筛选,将候选体体积压缩至0.75%,大幅减轻人工审核负担;系统已作为CPU级实时服务部署于EP-WXT管线。

脉络与展望

此前基于LEIA路径仪数据的X射线源分类多采用手工特征与传统机器学习,难以充分捕获龙虾眼在轨复杂背景 (Zuo+ 2024)。本工作直接利用EP-WXT在轨数据,构建空间图像、光变曲线、能谱多模态输入,形成ResNet臂滤波、双分支宇宙线滤波和背景感知贝叶斯块 Scargle+ 2013 变异性筛选的三级级联框架,实现高召回率与高排除率的实时处理。未来可结合邻近源星表掩模与多波段先验 (如Gaia、AllWISE) 缓解拥挤场效应,并推动从真伪分类向精细天体类别判定的拓展。

预印本 2026-06-24 · 接收 2026-06-15 · 刊出 2026-07-16 · 收录 2026-07-22