DID YOU KNOW? DTIC has over 3.5 million final reports on DoD funded research, development, test, and evaluation activities available to our registered users. Click
HERE to register or log in.
Accession Number:
AD1208932
Title:
Machine Learning for PAC1D and SESE
Report Date:
2023-04-03
Abstract:
This document outlines various machine learning approaches that were taken in an effort tosurrogate numerical models Python Ablation Code 1-Dimension (PAC1D) and Scalable EffectsSimulation Environment (SESE)[1], [2], with the ultimate objective of discovering the mostefficient method for approximating SESE with sparse data utilization. The methods exploredinclude; physics-informed neural networks, deep galerkin method, deep mixed residual methods,operator network, deep operator network, fourier neural operator, physics-informed fourier neuraloperator, and physics-informed kernal neural operator. Many of the methods showed strengths andweaknesses in their performance, with the physics-informed kernal neural operator showing themost potential for approximating SESEs behavior.
Document Type:
Conference:
Journal:
Pages:
44
File Size:
1.70MB
FA8650-19-C-6024
(FA865019C6024);
Contracts:
Grants:
Distribution Statement:
Approved For Public Release