# Flow Matching for Atmospheric Retrieval of Exoplanets: Where Reliability meets Adaptive Noise Levels

arXiv: https://arxiv.org/abs/2410.21477 · HTML: https://mlsanity.com/paper/2410.21477/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 52 references that are in the map.
- First posted on arXiv 28 Oct 2024.

## Builds on (most cited first, 14 of 14)

- [The frontier of simulation-based inference](https://mlsanity.com/paper/1911.01429/) (2019)
- [normflows: A PyTorch Package for Normalizing Flows](https://mlsanity.com/paper/2302.12014/) (2023)
- [An Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval](https://mlsanity.com/paper/1905.10659/) (2019)
- [Dynamic nested sampling: an improved algorithm for parameter estimation and evidence calculation](https://mlsanity.com/paper/1704.03459/) (2017)
- [Peeking inside the Black Box: Interpreting Deep Learning Models for Exoplanet Atmospheric Retrievals](https://mlsanity.com/paper/2011.11284/) (2020)
- [NAUTILUS: boosting Bayesian importance nested sampling with deep learning](https://mlsanity.com/paper/2306.16923/) (2023)
- [Exoplanet Characterization using Conditional Invertible Neural Networks](https://mlsanity.com/paper/2202.00027/) (2022)
- [Convolutional neural networks as an alternative to Bayesian retrievals](https://mlsanity.com/paper/2203.01236/) (2022)
- [Using a neural network approach to accelerate disequilibrium chemistry calculations in exoplanet atmospheres](https://mlsanity.com/paper/2306.07074/) (2023)
- [ExoMDN: Rapid characterization of exoplanet interior structures with Mixture Density Networks](https://mlsanity.com/paper/2306.09002/) (2023)
- [Approximating Rayleigh Scattering in Exoplanetary Atmospheres using Physics-informed Neural Networks (PINNs)](https://mlsanity.com/paper/2408.00084/) (2024)
- [Parameterizing pressure-temperature profiles of exoplanet atmospheres with neural networks](https://mlsanity.com/paper/2309.03075/) (2023)
- [FlopPITy: Enabling self-consistent exoplanet atmospheric retrievals with machine learning](https://mlsanity.com/paper/2401.04168/) (2024)
- [cecilia: A Machine Learning-Based Pipeline for Measuring Metal Abundances of Helium-rich Polluted White Dwarfs](https://mlsanity.com/paper/2402.05176/) (2024)

## Built on by (most cited first, 3 of 3)

- [Simulation-Based Inference: A Practical Guide](https://mlsanity.com/paper/2508.12939/) (2025)
- [Position: The Future of Bayesian Prediction Is Prior-Fitted](https://mlsanity.com/paper/2505.23947/) (2025)
- [A Missing Latent, Not a Missing Simulator: Radius-Augmented Inference for Real JWST Retrieval](https://mlsanity.com/paper/2610.02245/) (2026)

## Abstract (arXiv)

Inferring atmospheric properties of exoplanets from observed spectra is key to understanding their formation, evolution, and habitability. Since traditional Bayesian approaches to atmospheric retrieval (e.g., nested sampling) are computationally expensive, a growing number of machine learning (ML) methods such as neural posterior estimation (NPE) have been proposed. We seek to make ML-based atmospheric retrieval (1) more reliable and accurate with verified results, and (2) more flexible with respect to the underlying neural networks and the choice of the assumed noise models. First, we adopt flow matching posterior estimation (FMPE) as a new ML approach to atmospheric retrieval. FMPE maintains many advantages of NPE, but provides greater architectural flexibility and scalability. Second, we use importance sampling (IS) to verify and correct ML results, and to compute an estimate of the Bayesian evidence. Third, we condition our ML models on the assumed noise level of a spectrum (i.e., error bars), thus making them adaptable to different noise models. Both our noise level-conditional FMPE and NPE models perform on par with nested sampling across a range of noise levels when tested on simulated data. FMPE trains about 3 times faster than NPE and yields higher IS efficiencies. IS successfully corrects inaccurate ML results, identifies model failures via low efficiencies, and provides accurate estimates of the Bayesian evidence. FMPE is a powerful alternative to NPE for fast, amortized, and parallelizable atmospheric retrieval. IS can verify results, thus helping to build confidence in ML-based approaches, while also facilitating model comparison via the evidence ratio. Noise level conditioning allows design studies for future instruments to be scaled up, for example, in terms of the range of signal-to-noise ratios.