# Hybrid Physical-Neural Simulator for Fast Cosmological Hydrodynamics

arXiv: https://arxiv.org/abs/2510.26593 · HTML: https://mlsanity.com/paper/2510.26593/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 30 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [On Neural Differential Equations](https://mlsanity.com/paper/2202.02435/) (2022)
- [A Conceptual Introduction to Hamiltonian Monte Carlo](https://mlsanity.com/paper/1701.02434/) (2017)
- [Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers](https://mlsanity.com/paper/2007.00016/) (2020)
- [Hybrid Physical-Neural ODEs for Fast N-body Simulations](https://mlsanity.com/paper/2207.05509/) (2022)
- [The CAMELS project: Expanding the galaxy formation model space with new ASTRID and 28-parameter TNG and SIMBA suites](https://mlsanity.com/paper/2304.02096/) (2023)
- [SWIFT: A modern highly-parallel gravity and smoothed particle hydrodynamics solver for astrophysical and cosmological applications](https://mlsanity.com/paper/2305.13380/) (2023)
- [Detecting Model Misspecification in Cosmology with Scale-Dependent Normalizing Flows](https://mlsanity.com/paper/2508.05744/) (2025)

## Built on by (most cited first, 1 of 1)

- [MadEvolve: Evolutionary Optimization of Cosmological Algorithms with Large Language Models](https://mlsanity.com/paper/2602.15951/) (2026)

## Abstract (arXiv)

Cosmological field-level inference requires differentiable forward models that solve the challenging dynamics of gas and dark matter under hydrodynamics and gravity. We propose a hybrid approach where gravitational forces are computed using a differentiable particle-mesh solver, while the hydrodynamics are parametrized by a neural network that maps local quantities to an effective pressure field. We demonstrate that our method improves upon alternative approaches, such as an Enthalpy Gradient Descent baseline, both at the field and summary-statistic level. The approach is furthermore highly data efficient, with a single reference simulation of cosmological structure formation being sufficient to constrain the neural pressure model. This opens the door for future applications where the model is fit directly to observational data, rather than a training set of simulations.