Loading...
Dynamic frequency-gated fourier neural operators: architecture, principles, and applications
Journal Title
Readers/Advisors
Curry, Michael, Easwaran, Chirakkal, Brainard, Katherine
Journal Title
Term and Year
Spring 2025
Publication Date
2025-05
Book Title
Publication Volume
Publication Issue
Publication Begin
Publication End
Number of pages
Collections
Files
Loading...
Tangirala_Thesis.pdf
Adobe PDF, 2.09 MB
Research Projects
Organizational Units
Journal Issue
Abstract
Solving parametric partial differential equations (PDEs) has historically been an area of research focused on identifying computationally efficient methods. Because analytic solutions are often impractical, numerical solvers have traditionally been used to approximate these functions. However, with the rise of deep learning, data-driven methods are now widely used and can learn the underlying PDE operators that govern complex fluid mechanics [1, 2]. In this thesis, we propose a dynamic adaptive Fourier neural operator (DA-FNO) that employs frequency gating as a masking mechanism to modulate spectral content directly in the frequency domain. The prevailing “one-size-fits-all” treatment of Fourier modes in the original FNO [3] limits dynamism when certain instances demand finer spectral focus. By learning a frequency gate 𝐺 that controls both the count of modes and their granularity—per quadrant, per sample—within each Fourier layer, the model bypasses costly convolutions on irrelevant modes, yielding a more efficient and adaptive architecture. We train the baseline FNO, our DA-FNO, and several ablated variants on the publicly released MegaFlow2D benchmark dataset.
Citation
DOI
Description
Accessibility Statement
If this SOAR repository item is not accessible to you (e.g. able to be used in the context of a disability), please email libraryaccessibility@newpaltz.edu