Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions

• URL: http://arxiv.org/abs/2412.20192v2
• Date: Thu, 11 Sep 2025 13:51:55 GMT
• Title: Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions
• Authors: Daniel A. Serino, Evan Bell, Marc Klasky, Ben S. Southworth, Balasubramanya Nadiga, Trevor Wilcox, Oleg Korobkin,
• Abstract summary: In high energy density physics (HEDP) and inertial confinement fusion (ICF), predictive modeling is complicated by uncertainty in parameters that characterize various aspects of the modeled system.<n>In this work, we define a set of sparse hydrodynamic features derived from the outgoing shock profile and outer material edge, to directly infer such parameters.<n>We show that the estimated parameters can be used in a hydrodynamics code to obtain density fields and hydrodynamic shock and outer edge features that are consistent with the data.
• Score: 0.9576821967808625
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In high energy density physics (HEDP) and inertial confinement fusion (ICF), predictive modeling is complicated by uncertainty in parameters that characterize various aspects of the modeled system, such as those characterizing material properties, equation of state (EOS), opacities, and initial conditions. Typically, however, these parameters are not directly observable. What is observed instead is a time sequence of radiographic projections using X-rays. In this work, we define a set of sparse hydrodynamic features derived from the outgoing shock profile and outer material edge, which can be obtained from radiographic measurements, to directly infer such parameters. Our machine learning (ML)-based methodology involves a pipeline of two architectures, a radiograph-to-features network (R2FNet) and a features-to-parameters network (F2PNet), that are trained independently and later combined to approximate a posterior distribution for the parameters from radiographs. We show that the estimated parameters can be used in a hydrodynamics code to obtain density fields and hydrodynamic shock and outer edge features that are consistent with the data. Finally, we demonstrate that features resulting from an unknown EOS model can be successfully mapped onto parameters of a chosen analytical EOS model, implying that network predictions are learning physics, with a degree of invariance to the underlying choice of EOS model.

Related papers

• A neural network machine-learning approach for characterising hydrogen trapping parameters from TDS experiments [0.0]
  This work introduces a machine learning-based scheme for parameter identification from TDS spectra.<n>A multi-Neural Network (NN) model is developed and trained exclusively on synthetic data to predict trapping parameters.<n>The proposed model demonstrated strong predictive capabilities when applied to three tempered martensitic steels of different compositions.
  arXiv  Detail & Related papers  (2025-08-05T12:21:54Z)
• Learning robust parameter inference and density reconstruction in flyer plate impact experiments [0.0]
  Estimating physical parameters or material properties from experimental observations is a common objective in many areas of physics and material science.<n> radiography does not provide direct access to key state variables, such as density.<n>We propose an observable data set consisting of low and high impact velocity experiments/simulations that capture different regimes of compaction and shock propagation.<n>We show that the obtained estimates of EoS and crush model parameters can then be used in hydrodynamic simulations to obtain accurate and physically admissible density reconstructions.
  arXiv  Detail & Related papers  (2025-06-30T14:43:33Z)
• Hybrid Adaptive Modeling in Process Monitoring: Leveraging Sequence Encoders and Physics-Informed Neural Networks [0.5219568203653523]
  We introduce an architecture that employs Deep Sequences to encode dynamic parameters, boundary conditions, and initial conditions, using these encoded features as inputs for the PINN.<n>We show that the model can encode pressure data from a few points to identify the inlet velocity profile and utilize physics to compute velocity and pressure throughout the domain.
  arXiv  Detail & Related papers  (2025-05-20T12:05:17Z)
• DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion [53.70278210626701]
  We propose a data-driven multi-view reasoning approach that directly infers 3D scene geometry and camera poses from multi-view images.<n>Our framework, DiffusionSfM, parameterizes scene geometry and cameras as pixel-wise ray origins and endpoints in a global frame.<n>We empirically validate DiffusionSfM on both synthetic and real datasets, demonstrating that it outperforms classical and learning-based approaches.
  arXiv  Detail & Related papers  (2025-05-08T17:59:47Z)
• Validation and Calibration of Semi-Analytical Models for the Event Horizon Telescope Observations of Sagittarius A* [0.0]
  We use alinet, a generative machine learning model, to efficiently produce radiatively inefficient accretion flow images.<n>We estimate the uncertainty introduced by a number of anticipated unmodeled physical effects, including interstellar scattering.<n>We then use this to calibrate physical parameter estimates and their associated uncertainties from RIAF model fits to mock EHT data.
  arXiv  Detail & Related papers  (2025-04-25T18:00:04Z)
• CNN-powered micro- to macro-scale flow modeling in deformable porous media [0.0]
  This work introduces a novel application for predicting the macroscopic intrinsic permeability tensor in deformable porous media, using a limited set of micro-CT images of real microgeometries. The novelty of this work lies in leveraging Convolutional Neural Networks (CNN) to predict pore-fluid flow behavior under deformation and anisotropic flow conditions.
  arXiv  Detail & Related papers  (2025-01-11T07:36:41Z)
• Predicting Energy Budgets in Droplet Dynamics: A Recurrent Neural Network Approach [0.0]
  This study applies Long Short-Term Memory to predict transient and static outputs for fluid flows under surface tension effects. Using only dimensionless numbers and geometric time series data from numerical simulations, LSTM predicts the energy budget. Using a recurrent neural network (RNN) architecture fed with time series data derived from geometrical parameters, our study shows the accuracy of our approach in predicting energy budgets.
  arXiv  Detail & Related papers  (2024-03-24T13:32:42Z)
• Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy [55.014926694758195]
  Entropy and mutual information in neural networks provide rich information on the learning process. We leverage data geometry to access the underlying manifold and reliably compute these information-theoretic measures. We show that they form noise-resistant measures of intrinsic dimensionality and relationship strength in high-dimensional simulated data.
  arXiv  Detail & Related papers  (2023-12-04T01:32:42Z)
• Designing Observables for Measurements with Deep Learning [0.12277343096128711]
  We propose to design targeted observables with machine learning. Unfolded, differential cross sections in a neural network output contain the most information about parameters of interest. We demonstrate this idea in simulation using two physics models for inclusive measurements in deep in scattering.
  arXiv  Detail & Related papers  (2023-10-12T20:54:34Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification [64.61198351207752]
  Existing approaches to system identification (estimating the physical parameters of an object) from videos assume known object geometries. In this work, we aim to identify parameters characterizing a physical system from a set of multi-view videos without any assumption on object geometry or topology. We propose "Physics Augmented Continuum Neural Radiance Fields" (PAC-NeRF), to estimate both the unknown geometry and physical parameters of highly dynamic objects from multi-view videos.
  arXiv  Detail & Related papers  (2023-03-09T18:59:50Z)
• Neural Implicit Representations for Physical Parameter Inference from a Single Video [49.766574469284485]
  We propose to combine neural implicit representations for appearance modeling with neural ordinary differential equations (ODEs) for modelling physical phenomena. Our proposed model combines several unique advantages: (i) Contrary to existing approaches that require large training datasets, we are able to identify physical parameters from only a single video. The use of neural implicit representations enables the processing of high-resolution videos and the synthesis of photo-realistic images.
  arXiv  Detail & Related papers  (2022-04-29T11:55:35Z)
• Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data [50.23363975709122]
  We propose a probabilistic model called ME-NODE to incorporate (fixed + random) mixed effects for analyzing panel data. We show that our model can be derived using smooth approximations of SDEs provided by the Wong-Zakai theorem. We then derive Evidence Based Lower Bounds for ME-NODE, and develop (efficient) training algorithms.
  arXiv  Detail & Related papers  (2022-02-18T22:41:51Z)
• Inverting brain grey matter models with likelihood-free inference: a tool for trustable cytoarchitecture measurements [62.997667081978825]
  characterisation of the brain grey matter cytoarchitecture with quantitative sensitivity to soma density and volume remains an unsolved challenge in dMRI. We propose a new forward model, specifically a new system of equations, requiring a few relatively sparse b-shells. We then apply modern tools from Bayesian analysis known as likelihood-free inference (LFI) to invert our proposed model.
  arXiv  Detail & Related papers  (2021-11-15T09:08:27Z)
• Prediction of liquid fuel properties using machine learning models with Gaussian processes and probabilistic conditional generative learning [56.67751936864119]
  The present work aims to construct cheap-to-compute machine learning (ML) models to act as closure equations for predicting the physical properties of alternative fuels. Those models can be trained using the database from MD simulations and/or experimental measurements in a data-fusion-fidelity approach. The results show that ML models can predict accurately the fuel properties of a wide range of pressure and temperature conditions.
  arXiv  Detail & Related papers  (2021-10-18T14:43:50Z)
• Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems [0.0]
  We generalize the idea of conditional parametrization -- using trainable functions of input parameters. We show that conditionally parameterized networks provide superior performance compared to their traditional counterparts. A network architecture named CP-GNet is also proposed as the first deep learning model capable of reacting standalone prediction of flows on meshes.
  arXiv  Detail & Related papers  (2021-09-15T20:21:13Z)
• Combining data assimilation and machine learning to estimate parameters of a convective-scale model [0.0]
  Errors in the representation of clouds in convection-permitting numerical weather prediction models can be introduced by different sources. In this work, we look at the problem of parameter estimation through an artificial intelligence lens by training two types of artificial neural networks.
  arXiv  Detail & Related papers  (2021-09-07T09:17:29Z)
• Estimating permeability of 3D micro-CT images by physics-informed CNNs based on DNS [1.6274397329511197]
  This paper presents a novel methodology for permeability prediction from micro-CT scans of geological rock samples. The training data set for CNNs dedicated to permeability prediction consists of permeability labels that are typically generated by classical lattice Boltzmann methods (LBM) We instead perform direct numerical simulation (DNS) by solving the stationary Stokes equation in an efficient and distributed-parallel manner.
  arXiv  Detail & Related papers  (2021-09-04T08:43:19Z)

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.