Transfer learning driven design optimization for inertial confinement fusion

• URL: http://arxiv.org/abs/2205.13519v1
• Date: Thu, 26 May 2022 17:38:57 GMT
• Title: Transfer learning driven design optimization for inertial confinement fusion
• Authors: K. D. Humbird and J. L. Peterson
• Abstract summary: Transfer learning is a promising approach to creating predictive models that incorporate simulation and experimental data into a common framework. We demonstrate that this method is more efficient at optimizing designs than traditional model calibration techniques.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transfer learning is a promising approach to creating predictive models that incorporate simulation and experimental data into a common framework. In this technique, a neural network is first trained on a large database of simulations, then partially retrained on sparse sets of experimental data to adjust predictions to be more consistent with reality. Previously, this technique has been used to create predictive models of Omega and NIF inertial confinement fusion (ICF) experiments that are more accurate than simulations alone. In this work, we conduct a transfer learning driven hypothetical ICF campaign in which the goal is to maximize experimental neutron yield via Bayesian optimization. The transfer learning model achieves yields within 5% of the maximum achievable yield in a modest-sized design space in fewer than 20 experiments. Furthermore, we demonstrate that this method is more efficient at optimizing designs than traditional model calibration techniques commonly employed in ICF design. Such an approach to ICF design could enable robust optimization of experimental performance under uncertainty.

Related papers

• Don't You (Project Around Discs)? Neural Network Surrogate and Projected Gradient Descent for Calibrating an Intervertebral Disc Finite Element Model [9.456474817418703]
  This study introduces a novel, efficient, and effective calibration method for an L4-L5 IVD FE model using a neural network (NN) surrogate. The NN surrogate predicts simulation outcomes with high accuracy, outperforming other machine learning models. Our approach reduces calibration time to under three seconds, compared to up to 8 days per sample required by traditional calibration.
  arXiv  Detail & Related papers  (2024-08-12T11:39:21Z)
• Enhanced Bayesian Optimization via Preferential Modeling of Abstract Properties [49.351577714596544]
  We propose a human-AI collaborative Bayesian framework to incorporate expert preferences about unmeasured abstract properties into surrogate modeling. We provide an efficient strategy that can also handle any incorrect/misleading expert bias in preferential judgments.
  arXiv  Detail & Related papers  (2024-02-27T09:23:13Z)
• Bayesian Optimization for Robust State Preparation in Quantum Many-Body Systems [0.0]
  We apply Bayesian optimization to a state-preparation protocol recently implemented in an ultracold-atom system. Compared to manual ramp design, we demonstrate the superior performance of our optimization approach in a numerical simulation. The proposed protocol and workflow will pave the way toward the realization of more complex many-body quantum states in experiments.
  arXiv  Detail & Related papers  (2023-12-14T18:59:55Z)
• Transformer-Powered Surrogates Close the ICF Simulation-Experiment Gap with Extremely Limited Data [24.24053233941972]
  This paper presents a novel transformer-powered approach for enhancing prediction accuracy in multi-modal output scenarios. The proposed approach integrates transformer-based architecture with a novel graph-based hyper- parameter optimization technique. We demonstrate the efficacy of our approach on inertial confinement fusion experiments, where only 10 shots of real-world data are available.
  arXiv  Detail & Related papers  (2023-12-06T17:53:06Z)
• Machine learning enabled experimental design and parameter estimation for ultrafast spin dynamics [54.172707311728885]
  We introduce a methodology that combines machine learning with Bayesian optimal experimental design (BOED) Our method employs a neural network model for large-scale spin dynamics simulations for precise distribution and utility calculations in BOED. Our numerical benchmarks demonstrate the superior performance of our method in guiding XPFS experiments, predicting model parameters, and yielding more informative measurements within limited experimental time.
  arXiv  Detail & Related papers  (2023-06-03T06:19:20Z)
• Online simulator-based experimental design for cognitive model selection [74.76661199843284]
  We propose BOSMOS: an approach to experimental design that can select between computational models without tractable likelihoods. In simulated experiments, we demonstrate that the proposed BOSMOS technique can accurately select models in up to 2 orders of magnitude less time than existing LFI alternatives.
  arXiv  Detail & Related papers  (2023-03-03T21:41:01Z)
• Improving and generalizing flow-based generative models with minibatch optimal transport [90.01613198337833]
  We introduce the generalized conditional flow matching (CFM) technique for continuous normalizing flows (CNFs) CFM features a stable regression objective like that used to train the flow in diffusion models but enjoys the efficient inference of deterministic flow models. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference.
  arXiv  Detail & Related papers  (2023-02-01T14:47:17Z)
• When to Update Your Model: Constrained Model-based Reinforcement Learning [50.74369835934703]
  We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL) Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
  arXiv  Detail & Related papers  (2022-10-15T17:57:43Z)
• Design Amortization for Bayesian Optimal Experimental Design [70.13948372218849]
  We build off of successful variational approaches, which optimize a parameterized variational model with respect to bounds on the expected information gain (EIG) We present a novel neural architecture that allows experimenters to optimize a single variational model that can estimate the EIG for potentially infinitely many designs.
  arXiv  Detail & Related papers  (2022-10-07T02:12:34Z)
• Cognitive simulation models for inertial confinement fusion: Combining simulation and experimental data [0.0]
  Researchers rely heavily on computer simulations to explore the design space in search of high-performing implosions. For more effective design and investigation, simulations require input from past experimental data to better predict future performance. We describe a cognitive simulation method for combining simulation and experimental data into a common, predictive model.
  arXiv  Detail & Related papers  (2021-03-19T02:00:14Z)

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.