Neural-Network Chemical Emulator for First-Star Formation: Robust Iterative Predictions over a Wide Density Range

• URL: http://arxiv.org/abs/2508.16114v1
• Date: Fri, 22 Aug 2025 06:11:03 GMT
• Title: Neural-Network Chemical Emulator for First-Star Formation: Robust Iterative Predictions over a Wide Density Range
• Authors: Sojun Ono, Kazuyuki Sugimura,
• Abstract summary: We present a neural-network emulator for the thermal and chemical evolution in PopulationIII star formation.<n>We partition the density range into five subregions and train separate deep operator networks (DeepONets) in each region.<n>When applied to randomly sampled thermochemical states, the emulator achieves errors below 10% in over 90% of cases for both temperature and chemical abundances.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a neural-network emulator for the thermal and chemical evolution in Population~III star formation. The emulator accurately reproduces the thermochemical evolution over a wide density range spanning 21 orders of magnitude (10$^{-3}$-10$^{18}$ cm$^{-3}$), tracking six primordial species: H, H$_2$, e$^{-}$, H$^{+}$, H$^{-}$, and H$_2^{+}$. To handle the broad dynamic range, we partition the density range into five subregions and train separate deep operator networks (DeepONets) in each region. When applied to randomly sampled thermochemical states, the emulator achieves relative errors below 10% in over 90% of cases for both temperature and chemical abundances (except for the rare species H$_2^{+}$). The emulator is roughly ten times faster on a CPU and more than 1000 times faster for batched predictions on a GPU, compared with conventional numerical integration. Furthermore, to ensure robust predictions under many iterations, we introduce a novel timescale-based update method, where a short-timestep update of each variable is computed by rescaling the predicted change over a longer timestep equal to its characteristic variation timescale. In one-zone collapse calculations, the results from the timescale-based method agree well with traditional numerical integration even with many iterations at a timestep as short as 10$^{-4}$ of the free-fall time. This proof-of-concept study suggests the potential for neural network-based chemical emulators to accelerate hydrodynamic simulations of star formation.

Related papers

• Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials [51.342983349686556]
  General-purpose 3D chemical modeling encompasses molecules and materials, requiring both generative and predictive capabilities.<n>We introduce Zatom-1, the first end-to-end, fully open-source foundation model that unifies generative and predictive learning of 3D molecules and materials.
  arXiv  Detail & Related papers  (2026-02-24T20:52:39Z)
• Fast simulations of X-ray absorption spectroscopy for battery materials on a quantum computer [36.21999915593711]
  This work proposes a highly-optimized implementation of the time-domain algorithm for X-ray absorption.<n>The low cost of our algorithm makes it attractive to use on fault-tolerant quantum devices to accelerate the development and commercialization of high-capacity battery cathodes.
  arXiv  Detail & Related papers  (2025-06-18T18:00:29Z)
• NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation [41.41450298461784]
  We propose NeuralOM, a general neural operator framework for simulating complex, slow-changing dynamics.<n>We validate NeuralOM on the challenging task of global Subseasonal-to-Seasonal (S2S) ocean simulation.<n>NeuralOM achieves a 13.3% lower RMSE compared to the best-performing baseline.
  arXiv  Detail & Related papers  (2025-05-27T10:54:40Z)
• A Deep-Learning Iterative Stacked Approach for Prediction of Reactive Dissolution in Porous Media [0.6597195879147557]
  We present a novel deep learning approach that incorporates both temporal and spatial information to predict the future states of the dissolution process.<n>The overall performance, in terms of speed and prediction accuracy, is demonstrated on a numerical simulation dataset.
  arXiv  Detail & Related papers  (2025-03-11T13:18:03Z)
• MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation [48.41289705783405]
  We propose a PDE-embedded network with multiscale time stepping (MultiPDENet)<n>In particular, we design a convolutional filter based on the structure of finite difference with a small number of parameters to optimize.<n>A Physics Block with a 4th-order Runge-Kutta integrator at the fine time scale is established that embeds the structure of PDEs to guide the prediction.
  arXiv  Detail & Related papers  (2025-01-27T12:15:51Z)
• Neural Network Emulator for Atmospheric Chemical ODE [6.84242299603086]
  We propose a Neural Network Emulator for fast chemical concentration modeling.<n>To extract the hidden correlations between initial states and future time evolution, we propose ChemNNE.<n>Our approach achieves state-of-the-art performance in modeling accuracy and computational speed.
  arXiv  Detail & Related papers  (2024-08-03T17:43:10Z)
• EM-GANSim: Real-time and Accurate EM Simulation Using Conditional GANs for 3D Indoor Scenes [55.2480439325792]
  We present a novel machine-learning (ML) approach (EM-GANSim) for real-time electromagnetic (EM) propagation.<n>In practice, it can compute the signal strength in a few milliseconds on any location in 3D indoor environments.
  arXiv  Detail & Related papers  (2024-05-27T17:19:02Z)
• Emulating the interstellar medium chemistry with neural operators [0.0]
  Galaxy formation and evolution critically depend on understanding the complex photo-chemical processes that govern the evolution and thermodynamics of the InterStellar Medium (ISM) Here, we aim at substituting such procedural solvers with fast, pre-trained, emulators based on neural operators. We emulate a non-equilibrium chemical network up to H$$ formation (9 species, 52 reactions) by adopting the DeepONet formalism, i.e. Compared with the reference solutions obtained by $textttKROME$ for single zone models, the typical precision obtained is of order $10-2$, i.e
  arXiv  Detail & Related papers  (2024-02-19T19:00:01Z)
• Continuous time recurrent neural networks: overview and application to forecasting blood glucose in the intensive care unit [56.801856519460465]
  Continuous time autoregressive recurrent neural networks (CTRNNs) are a deep learning model that account for irregular observations. We demonstrate the application of these models to probabilistic forecasting of blood glucose in a critical care setting.
  arXiv  Detail & Related papers  (2023-04-14T09:39:06Z)
• Neural networks: solving the chemistry of the interstellar medium [0.0]
  Non-equilibrium chemistry is among the most difficult tasks to include in astrophysical simulations. PINN-powered simulations are a palatable way to solve complex chemical calculation in astrophysical and cosmological problems.
  arXiv  Detail & Related papers  (2022-11-28T19:00:01Z)
• Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator [57.57321628587564]
  We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows. HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
  arXiv  Detail & Related papers  (2022-06-15T17:29:57Z)
• Computing molecular excited states on a D-Wave quantum annealer [52.5289706853773]
  We demonstrate the use of a D-Wave quantum annealer for the calculation of excited electronic states of molecular systems. These simulations play an important role in a number of areas, such as photovoltaics, semiconductor technology and nanoscience.
  arXiv  Detail & Related papers  (2021-07-01T01:02:17Z)
• A deep learning-based ODE solver for chemical kinetics [6.146046338698173]
  This work presents a deep learning-based numerical method called DeepCombustion0.0 to solve stiff ordinary differential equation systems. The homogeneous autoignition of DME/air mixture, including 54 species, is adopted as an example to illustrate the validity and accuracy of the algorithm.
  arXiv  Detail & Related papers  (2020-11-24T02:44:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.