An autoencoder-based reduced-order model for eigenvalue problems with application to neutron diffusion
This work addresses eigenvalue problems in nuclear reactor physics with incremental improvements in reduced-order modeling.
The paper tackled the problem of dimensionality reduction for eigenvalue problems by developing autoencoder-based reduced-order models, achieving more efficient feature capture compared to standard POD-Galerkin methods in nuclear reactor physics test cases.
Using an autoencoder for dimensionality reduction, this paper presents a novel projection-based reduced-order model for eigenvalue problems. Reduced-order modelling relies on finding suitable basis functions which define a low-dimensional space in which a high-dimensional system is approximated. Proper orthogonal decomposition (POD) and singular value decomposition (SVD) are often used for this purpose and yield an optimal linear subspace. Autoencoders provide a nonlinear alternative to POD/SVD, that may capture, more efficiently, features or patterns in the high-fidelity model results. Reduced-order models based on an autoencoder and a novel hybrid SVD-autoencoder are developed. These methods are compared with the standard POD-Galerkin approach and are applied to two test cases taken from the field of nuclear reactor physics.