specsr-roman

Physics-informed super-resolution of Roman grism spectra.

Roman's High Latitude Spectroscopic Survey will deliver slitless grism spectra (R ≈ 461 λ/µm over 1–1.93 µm) for millions of emission-line galaxies. At that resolving power the diagnostic complexes stay blended — Hα+[N II], [O III]+Hβ — across wide redshift ranges, biasing redshifts and everything derived from them. Assembling survey-scale high-resolution training pairs to fix that observationally is prohibitive.

specsr-roman super-resolves those spectra with a three-stage network trained on simulated Roman products, and is built around one constraint:

A model that invents plausible emission lines is worse than useless in a survey. Every design decision here follows from that.

The pipeline is calibrated on recoverability — whether the data could have revealed a given line at all — and is explicitly penalised for drawing what it could not have seen. It ships with the two audits that keep those claims honest, and both are run in CI-adjacent form on every release.

This is the Roman half of a two-instrument project. The JWST/NIRSpec original is specsr (Haghjoo et al. 2026).

Install

pip install specsr-roman                 # inference + training
pip install "specsr-roman[hub]"          # + published checkpoints and data
pip install "specsr-roman[extract]"      # + dataset building (grizli, photutils)
pip install "specsr-roman[all]"          # everything

Python 3.10 or newer.

Use it

from specsr_roman import RomanPipeline

pipe = RomanPipeline.from_pretrained()      # downloads the published chain

out = pipe.predict(
    flux_low,                                # (864,) on the native grism grid
    flux_low_err,
    phot=roman_medium_fluxes,                # F106, F129, F158 — in that order
)

out.flux_sr        # super-resolved spectrum, 2500 px over 1.0–1.93 µm
out.flux_sr_err    # per-pixel uncertainty
out.z, out.z_err   # redshift point estimate and its spread
out.pz, out.z_grid # the full P(z) — keep it, see "Redshifts are multimodal"
out.presence       # per-line presence probability, over 98 features

phot=None supplies the redshift head's training-mean colours. It is a missing-input mode of a photometry-trained head; a grism-only model would need separate training. The older release's ablation numbers do not describe these new weights.

New here? tutorials/01_getting_started.ipynb (rendered) runs the whole thing end to end on a 512-spectrum reserved-test sample: one super-resolved spectrum, the redshift PDF, what photometry buys, and the recoverability-binned line recovery below. Two minutes on a CPU, no dataset download.

From the command line:

specsr-roman info                                    # what's installed and canonical
specsr-roman predict spectra.npz --out predictions.npz
specsr-roman evaluate metrics --cache pred_cache.npz
specsr-roman evaluate figures --outdir figures/

Results

Version 0.6.0 uses the independently trained chain sr1_ou2024_v6_independent → zhead_ou2024_roman_med3_noisy_independent → sr2_ou2024_v5_romanonly_independent.

The dataset contains 23,845 spectra of 10,039 galaxies detected in H158, selected by true Hα or [O III] λ5007 flux above 10⁻¹⁶ erg s⁻¹ cm⁻². The galaxy-grouped split has 19,134 training spectra (8,042 galaxies), 2,327 validation spectra (992 galaxies), and 2,384 reserved test spectra (1,005 galaxies). Checkpoints were selected on validation only; all nine models were frozen before test predictions were generated. Evaluation uses 0.05 mag Roman photometric noise and the configured Rubin coadd noise. The previous 4,711-spectrum results used the checkpoint-selection partition and must be read as validation results.

Redshift — every reserved test spectrum, no S/N cut

Catastrophic means |Δz|/(1+z) > 0.15. The control removes the spectrum from the redshift head; its SR2 still reads the spectrum. No observed outliers in this finite sample does not imply a zero population outlier rate.

Line amplitude recovery — Roman three-band chain

Median recovered/true flux in detected line regions, binned by the best integrated line S/N in the grism. Lines below S/N 2 are excluded.

Frozen test caches, exact metrics, the split record and weight provenance are available with the dataset and models. Response and uncertainty audits from earlier weights do not validate this release. Line fluxes and ratios should not yet be treated as calibrated measurements; independent response and uncertainty calibration remain open.

How it works

Three stages, each doing one job it can be held to.

SR1 is deliberately conservative. It sees [flux, err] scaled by a shared factor, so the channel ratio is the per-pixel S/N and the network can matched-filter rather than guess which bumps are noise.

ZHead predicts a distribution, not a number. Redshift from a grism is a line-identification problem: one observed line is consistent with Hα, [O III], [O II] or Lyα. A Gaussian head must average between aliases, which is what produced the ~40 % catastrophic floor of two earlier designs. A softmax over a grid carries the whole P(z) — the point estimate is the mode, and ambiguity survives as PDF width instead of becoming a wrong answer.

SR2 refines SR1 with one attention token per rest-frame feature, run once per redshift hypothesis and combined by mode mass. That is what makes it alias-robust: when the top mode is wrong the correct identification is usually the second or third, and the right lines still get drawn.

ARCHITECTURE.md has the full design, including the losses and why each one is shaped the way it is.

Redshifts are multimodal — keep the PDF

out.z is the mode of out.pz, not its mean. For an alias-ambiguous source the second mode is real information, and out.z_err widens precisely when the model is torn between two line identifications. Discarding pz throws away the part of the answer that tells you when not to trust the rest of it.

Training

Every published checkpoint is reproducible from a config file:

specsr-roman train sr1   --config configs/sr1.yaml
specsr-roman train zhead --config configs/zhead.yaml     # needs SR1
specsr-roman train sr2   --config configs/sr2.yaml       # needs SR1 + ZHead

The configs are the published chain — configs/sr1.yaml produces sr1_ou2024_v6_independent — and record the three-way split and upstream checkpoints, so "what was this trained with" always has a readable answer. Any field can be overridden on the command line (--epochs 50, --no-augment); an unknown key is an error rather than a silent no-op.

Two settings deserve a warning if you change them:

• phot_tier must stay on bands a survey delivers with the grism. medium is the three Roman bands of the published chain; medium_rubin adds Rubin ugrizy at coadd depth (rubin_depth_offset). grids.MAX_PHOT_BANDS caps an explicit band list at those nine: hand a model more and it reads the redshift off an effectively complete SED instead of the grism.
• phot_eval_mag_err must stay above zero. A metric measured on noiseless truth photometry is not a metric.

Checkpoint selection is not the validation loss

Both SR1 and SR2 select on custom goals, and this is load-bearing rather than fussy. SR1's total validation loss is dominated by the NLL, which rises as the model commits to line amplitudes — a confident half-amplitude line costs more than a hedged flat one. SR2's plain NLL is continuum-dominated and reliably selects the model that draws nothing.

So SR1 monitors line-flux recovery plus the hallucination penalty, and SR2 monitors -recov_amp + lam_hallu * hallu_amp. The Roman SR2 best checkpoint is epoch 8 of 150, selected on validation. The final epoch is not the published checkpoint.

Building the dataset

OpenUniverse2024 provides direct images, truth catalogues and Diffsky SEDs but no grism images, so specsr-roman disperses the scene itself with grizli and extracts it back. That is not a workaround: the same configuration file disperses and extracts, so any residual is the fault of noise, blending and the extraction — not of a mismatched instrument model.

specsr-roman extract run --max-scas 60 --workers 4    # resumable; safe to kill
specsr-roman extract merge                            # → every detected galaxy
specsr-roman extract select                           # → the training npz

extract run takes every galaxy the H158 image detects, with no magnitude cut. A detection takes the identity of the brightest catalogue galaxy at its position and keeps it only if the catalogue magnitude agrees with the detected flux: the truth index lists objects far below the detection limit, and the nearest one is often not the one detected. extract select then keeps the spectra whose true Hα or [O III] flux exceeds the survey's line-flux limit (--line-flux, default 10⁻¹⁶ erg s⁻¹ cm⁻²).

Or skip it: the built dataset is on the Hub, together with a 3.8 MB, 512-row tutorial/ subset drawn from the held-out split for the notebook above.

Each (visit, SCA) runs in its own subprocess — grizli's numba disperser corrupts the heap when thousands of sources go through one process — and caches its result, so a crash costs one SCA rather than the run.

Split by object, never by row. The same galaxy appears in many visits as independent noise realisations. specsr_roman.data.get_or_make_group_split keys membership on a hash of the object id, which also makes it stable under dataset growth: adding SCAs never moves an existing galaxy across the boundary.

Limitations

Stated plainly, because they bound what the numbers mean.

• Results are on the Diffsky manifold. Targets use simulated line physics. Recovery can reflect the training prior. Response-audit results from older weights do not establish the response of this release.
• Uncertainties require calibration. Keep the full P(z), but do not assume its intervals or the spectral error bars have nominal frequentist coverage.
• Trained on simulations, not sky. Real Roman spectra will differ. Domain adaptation via cross-instrument overlaps (DESI/PFS/JWST) is the intended route once real data exists.
• The lines are not judged below S/N 2. A quarter of the held-out spectra (about 24%) have no detected line in a single exposure. The redshift numbers include them; the line-recovery numbers do not, and say nothing about what the model draws there.
• The sample is selected on the true line flux. A survey has to estimate that flux from the data. In this simulation it also follows continuum brightness closely, so the sample lacks faint galaxies with strong lines.
• The remaining outliers are physics, not a bug to be tuned away. Where the line is too faint to see, the identification rests on three colours; they settle most cases and cannot settle all.

Citation

If you use this software, please cite the paper and the code. The method paper for the JWST original is Haghjoo et al. (2026), Learning to See Sharper: A Physics-Informed Artificial Intelligence Framework for Super-Resolving Galaxy Spectra, ApJ.

The code is archived on Zenodo. Cite 10.5281/zenodo.22119689 for the software in general — it always resolves to the newest version — or the version DOI on that record to pin the exact release you ran. CITATION.cff carries both, and GitHub's "Cite this repository" button renders it as BibTeX or APA.

Simulation products: OpenUniverse et al. (2025), OpenUniverse2024; Wang et al. (2022) for the Roman GRS grism configuration.

License

MIT — see LICENSE.