Amortized Opacity Marginalization Improves C/O Interval Calibration for Brown-Dwarf Retrievals
Abstract
Molecular line lists disagree at a level that measurably shifts retrieved C/O, so retrievals conditioned on a single list omit a dominant systematic from their error bars. Classical marginalization re-runs a full retrieval under K opacity realizations per object. We move that cost into simulation: while generating the training set we randomize opacities (smooth multiplicative Fourier fields in log(nu) plus a discrete line-list mixture, under a deliberately broad prior informed by measured inter-list differences), so a neural posterior estimator learns an already-marginalized posterior. On perturbed held-out spectra (n=2048) a standard NPE covers nominal 90% C/O intervals 43.3% of the time against 82.4% for a compute-matched marginalized network; three-seed control ensembles reach 93.2% on clean data but 61.4% under perturbation, against 89.4% marginalized, isolating the deficit as opacity-induced (TARP joint expected-coverage deviation 0.005 against 0.035 for a single control network). An axis ablation traces the gain to the continuous field (45.4% for the discrete swaps alone, 79.3% for the field alone). In simulation, real JWST bad-pixel masks with median filling cut the marginalized ensemble's C/O coverage from 0.894 to 0.683; an ensemble retrained with mask augmentation holds 0.918 under the full deployment preprocessing (n=1024). We apply the networks to one pipeline-combined JWST/NIRSpec G395H spectrum each of 14 late-T and Y dwarfs. The recommended mask-augmented ensemble returns C/O medians between 0.24 and 0.62 and contains the Hood et al. (2024) value of 0.53 for the T8 benchmark 2MASS J0415-0935, which every fixed-opacity control network excludes. With 90% intervals spanning about 0.43 of the prior width, this is a consistency check, not a validation.
Figures & tables
Appendix figures & tables9 assets
Supplementary material from the paper’s appendix.
Appendix
| Nominal (C/O) | control s0 | ctrl-ens. | marg s0 | marg 3-seed ens. |
|---|---|---|---|---|
| 0.50 | 0.195 | 0.342 | 0.442 | 0.513 |
| 0.68 | 0.284 | 0.448 | 0.599 | 0.695 |
| 0.90 | 0.433 | 0.614 | 0.824 | 0.894 |
| 0.95 | 0.504 | 0.680 | 0.884 | 0.934 |
| Overall @0.90 | 0.747 | 0.845 | 0.831 | 0.902 |
| Width/prior @0.90 | 0.055 | 0.081 | 0.142 | 0.168 |
| Training axis ( test) | ||
|---|---|---|
| Trained on | raw | recalibrated |
| discrete swap only | 0.454 | 0.746 |
| smooth field only | 0.793 | 0.873 |
| both (marg. seed 0) | 0.825 | 0.877 |
| Test axis (raw, no retraining) | ||
| Perturbed spectra | fixed-opacity control | marg. 3-seed ens. |
| Deployment stress ( , masks of the 14 real spectra) | |||
| Preprocessing | control s0 | marg. 3-seed ens. | mask-aug. 3-seed ens. |
| none (unmasked) | 0.451 | 0.894 | 0.924 |
| real-mask median fill | 0.430 | 0.683 | 0.928 |
| full path | 0.456 | 0.702 | 0.918 |
| Overall @0.90, full path | 0.643 | 0.800 | 0.894 |
| Width/prior, unmasked | 0.051 | 0.164 | 0.209 |
| Species | |||||
|---|---|---|---|---|---|
| CH 4 | 0.226 | 0.244 | 0.184 | 0.114 | 0.057 |
| H 2 O | 0.083 | 0.107 | 0.072 | 0.043 | 0.016 |
| CO, NH 3 , H 2 S | 0.154 | 0.176 | 0.128 | 0.078 | 0.036 |
| CO 2 | 0.339 | 0.366 | 0.276 | 0.171 | 0.085 |
| Network | C/O | 68% interval | 90% interval | contains |
|---|---|---|---|---|
| control, seed 0 | 0.642 | neither | ||
| control, seed 1 | 0.670 | neither | ||
| control, seed 2 | 0.704 | neither | ||
| control, 3-seed ens. | 0.673 | neither | ||
| marg., seed 0 | 0.660 | 68% & 90% | ||
| marg., seed 1 | 0.918 | neither |
| Object | Program/obs. | Mode | Pipeline | SNR | C/O (68%) |
|---|---|---|---|---|---|
| WISEA J235402.79 024014.1 | 2124/012 | slit | 3.0.0 | 6.3 | |
| WISEU J050305.68 564834.0 | 2124/052 | slit | 3.0.0 | 8.0 | |
| CWISEP J193518.59 154620.3 | 2124/051 | slit | 3.0.0 | 8.1 | |
| WISE J140518.39 553421.3 | 2124/011 | slit | 3.0.0 | 10.1 | |
| WISE J014656.66 423410.0 | 2124/056 | slit | 3.0.0 | 11.6 | |
| WISE J222055.31 362817.4 | 2124/010 | slit | 3.0.0 | 11.9 |
Uncertainty Calibration
Uncertainty calibration aligns model confidence and predictive intervals with observed correctness and outcome frequencies.
See all 295 papers