发表机构
SVKM’s NMIMS (Deemed to be University)（SVKM’s NMIMS（被视为大学））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对真实JWST光谱反演崩溃问题，发现缺失行星半径这一潜在变量而非模拟器缺陷，提出半径增强流匹配后验MIRAGE，将WASP-39b拟合误差从301降至0.06，并跨仪器与目标泛化。
AI 中文摘要
基于辐射传输模拟器训练的摊销模拟推断（SBI）能够在合成詹姆斯·韦伯空间望远镜（JWST）光谱上准确恢复系外行星大气，但在处理真实还原光谱时却失效。流后验在真实WASP-39b上崩溃（重要性采样有效样本量（ESS）=1，最佳拟合\c{hi}2/N=301），此类失败通常归咎于前向模型物理的缺失，但首先通过嵌套采样排除这些因素（温度梯度、SO2不透明度以及高保真不透明度集）后，拟合结果不变，表明崩溃并非源于模拟器设定错误，而是源于一个缺失的潜在变量——行星半径。为解决此问题，我们构建了MIRAGE，一种半径增强的流匹配后验，通过重要性采样和最优传输映射，针对独立的嵌套采样参考进行校准，从而对真实WASP-39b实现了物理上一致且与文献相符的反演（\c{hi}2/N从301降至0.06）。该方法无需修改即可跨两台仪器和三个真实JWST目标迁移，包括一个从Mikulski空间望远镜档案（MAST）原始数据端到端自行还原的光谱。这一教训具有跨领域意义，因为模拟器编码但推断忽略的潜在变量可能伪装成设定错误。
英文摘要
Amortized simulation-based inference (SBI), which is trained on radiative-transfer simulators, recovers exoplanet atmospheres accurately on synthetic James Webb Space Telescope (JWST) spectra but collapses when it comes to real reduced spectra. The flow posterior collapsed on real WASP-39b (importance-sampling effective sample size (ESS) = 1, best-fit \c{hi}2/N = 301), and such a failure is usually blamed on missing the forward-model physics, but ruling these levers out with nested sampling first (a temperature gradient, SO2 opacity, and a high-fidelity opacity set) leaves the fit unchanged, meaning the collapse is not from the simulator misspecification but instead from a missing latent, the planet radius. To fix this, we build MIRAGE, a radius-augmented flow-matching posterior calibrated against an independent nested-sampling reference with importance sampling and an optimal-transport map, which yields a physical and literature-consistent retrieval of real WASP-39b (with \c{hi}2/N from 301 to 0.06). This same method transfers unchanged across two instruments and three real JWST targets, including one spectrum self-reduced end-to-end from raw Mikulski Archive for Space Telescopes(MAST) data. The lesson is cross-domain, as a latent the simulator encodes but the inference omits can masquerade as misspecification.
Comments6 pages, 2 figures, 2 tables. Includes appendix and paper checklist
