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
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 ▾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。
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