Learning physical unknowns from hydrodynamic shock and material interface features in ICF capsule implosions

2024-12-28

AI Summary

High-energy-density physics modeling for inertial confinement fusion (ICF) capsule implosions is hindered by uncertainties in unobservable parameters—such as equation-of-state (EOS), opacity, and initial conditions—leading to significant model ambiguity. Method: We propose an end-to-end Bayesian inversion framework leveraging X-ray shadowgraph images. It extracts two sparse hydrodynamic features—shock front轮廓 and material outer edge—and employs a two-stage interpretable neural network: R2FNet (image-to-feature) and F2PNet (feature-to-parameter). Crucially, geometric physical features serve as proxy variables, enabling EOS-model-agnostic parameter learning. Contribution/Results: The framework successfully infers key material properties directly from experimental-scale images. Reconstructed density fields and interface dynamics achieve <5% error; cross-EOS validation demonstrates strong physical consistency, confirming the network’s capacity to generalize underlying physical laws.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• ICF Capsule Compression
• Uncertainty Quantification
• High Energy Density Physics

Innovation

• Machine Learning
• ICF Experiment Analysis
• High Energy Density Physics Parameters