DIF-FNO: Diffeomorphic Fourier Neural Operator with D'Agnese Barrier Loss

Official v1.0.0-sota-proof release for DIF-FNO (Diffeomorphic Fourier Neural Operator) powered by the D'Agnese Topological Barrier Loss. This architecture strictly resolves grid-folding anomalies (det(J_phi) > 0) across non-convex computational domains (NACA 0012, Star, L-Shape, Annulus) and high-shear physics boundary layers. Key Benchmark Results:- Absolute Topological Integrity: 0.00% grid folding guaranteed across all resolutions.- Zero-Shot Super-Resolution: Seamless extrapolation from 128x128 to 1024x1024 resolution.- Constant Memory Footprint: Fixed 4.53 MB model memory.- 1-Click Verification Suite: Includes run_all_proofs.py for deterministic reproduction. GitHub Repository: https://github.com/GiovanniDAgnese-paper/DIF-FNO

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-08-27
DOI
https://doi.org/10.5281/zenodo.22071926
Primary Topic
Model Reduction and Neural Networks
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
preprint

DIF-FNO: Diffeomorphic Fourier Neural Operator with D'Agnese Barrier Loss

GIOVANNI D'AGNESE
Zenodo (CERN European Organization for Nuclear Research)
Model Reduction and Neural Networks
preprint

DIF-FNO: Diffeomorphic Fourier Neural Operator with D'Agnese Barrier Loss

GIOVANNI D'AGNESE
preprint en

Abstract

Official v1.0.0-sota-proof release for DIF-FNO (Diffeomorphic Fourier Neural Operator) powered by the D'Agnese Topological Barrier Loss. This architecture strictly resolves grid-folding anomalies (det(J_phi) > 0) across non-convex computational domains (NACA 0012, Star, L-Shape, Annulus) and high-shear physics boundary layers. Key Benchmark Results:- Absolute Topological Integrity: 0.00% grid folding guaranteed across all resolutions.- Zero-Shot Super-Resolution: Seamless extrapolation from 128x128 to 1024x1024 resolution.- Constant Memory Footprint: Fixed 4.53 MB model memory.- 1-Click Verification Suite: Includes run_all_proofs.py for deterministic reproduction. GitHub Repository: https://github.com/GiovanniDAgnese-paper/DIF-FNO

Zenodo (CERN European Organization for Nuclear Research)
Peace, Justice and strong institutions
Model Reduction and Neural Networks
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.