Pith. sign in

REVIEW 5 cited by

Reconstructing Cosmological Initial Conditions from Late-Time Structure with Convolutional Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2207.12511 v2 pith:AWKGTRI6 submitted 2022-07-25 astro-ph.CO astro-ph.IM

classification astro-ph.COastro-ph.IM
keywords densityreconstructionmethodinitiallate-timecnnslocalscales
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present a method to reconstruct the initial linear-regime matter density field from the late-time non-linearly evolved density field in which we channel the output of standard first-order reconstruction to a convolutional neural network (CNN). Our method shows dramatic improvement over the reconstruction of either component alone. We show why CNNs are not well-suited for reconstructing the initial density directly from the late-time density: CNNs are local models, but the relationship between initial and late-time density is not local. Our method leverages standard reconstruction as a preprocessing step, which inverts bulk gravitational flows sourced over very large scales, transforming the residual reconstruction problem from long-range to local and making it ideally suited for a CNN. We develop additional techniques to account for redshift distortions, which warp the density fields measured by galaxy surveys. Our method improves the range of scales of high-fidelity reconstruction by a factor of 2 in wavenumber above standard reconstruction, corresponding to a factor of 8 increase in the number of well-reconstructed modes. In addition, our method almost completely eliminates the anisotropy caused by redshift distortions. As galaxy surveys continue to map the Universe in increasingly greater detail, our results demonstrate the opportunity offered by CNNs to untangle the non-linear clustering at intermediate scales more accurately than ever before.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. On the Relation Between Field-Level Posteriors, Correlators, and their Likelihoods

    astro-ph.CO 2026-04 unverdicted novelty 7.0 of 10

    A general non-perturbative field-level posterior is constructed and expanded around its Gaussian limit to express Fisher information in terms of connected correlators, recovering standard results for power spectrum an...

  2. Standard Reconstruction Shifts the Optimal Input Scale for CNN-Based Density-Field Reconstruction

    astro-ph.CO 2026-07 conditional novelty 6.0 of 10

    Applying standard reconstruction before a CNN shifts the optimal input cube for z=10 density reconstruction from ~150-200 h^-1 Mpc to ~38-114 h^-1 Mpc, and a single post-reconstruction CNN beats dual-scale CNN inputs.

  3. The Linear Point Standard Ruler with DESI DR1 and DR2 Data

    astro-ph.CO 2026-01 conditional novelty 6.0 of 10

    Linear-point distance measurements on DESI DR1/DR2 galaxy samples agree with template-based BAO measurements once a cosmology-dependent smearing correction is applied.

  4. Non-Gaussian Galaxy Stochasticity and the Noise-Field Formulation

    astro-ph.CO 2025-11 conditional novelty 6.0 of 10

    Galaxy stochasticity in EFT of large-scale structure reduces to nonlinear couplings of one Gaussian noise field, yielding a samplable field-level likelihood that stabilizes the inferred noise amplitude.

  5. DISCO-DJ II: a differentiable particle-mesh code for cosmology

    astro-ph.CO 2025-10 conditional novelty 6.0 of 10

    A GPU-accelerated, differentiable particle-mesh N-body code achieves per-cent-level power-spectrum accuracy with few time steps and recovers sigma_8 plus initial conditions from a noisy mock field.

Pith tools