Fourier Neural Operator
PulseAugur coverage of Fourier Neural Operator — every cluster mentioning Fourier Neural Operator across labs, papers, and developer communities, ranked by signal.
9 day(s) with sentiment data
-
Agentic AI discovers optimal sampling for sparse CT scans
Researchers have developed an agentic AI system capable of discovering optimal sampling strategies for sparse-view CT scans, specifically for predicting hemodynamic information. This AI approach, along with a Soft top-K…
-
Neural operator benchmarks on 'The Well' dataset questioned by new study
A new arXiv paper challenges the performance benchmarks of neural operator models on 'The Well' dataset. The authors found that the original baselines, which were presented as illustrative and trained with minimal tunin…
-
FC-PINO enhances precision for physics-informed neural operators
Researchers have introduced FC-PINO, a novel architecture for Physics-Informed Neural Operators (PINOs) designed to enhance precision in solving partial differential equations (PDEs). Traditional PINO methods struggle w…
-
AI accelerates subsurface reservoir modeling with neural operators
Researchers have developed a novel framework that accelerates Bayesian history matching for subsurface reservoir modeling. This approach utilizes a Fourier neural operator as a surrogate for the complex forward map, sig…
-
New framework improves fluid dynamics learning with operator splitting
Researchers have developed a new framework called Neural Operator Splitting to improve the learning of fluid dynamics in complex geometries. This method decomposes each time step into separate, physically interpretable …
-
Neural Operator Splitting framework accelerates fluid dynamics learning
Researchers have developed a new framework called Neural Operator Splitting for learning fluid dynamics in complex geometries. This method decomposes time steps into physically interpretable stages, with each operator l…
-
New research details spectral limits of graph filters on Ising Model benchmark
A new research paper published on arXiv details the spectral limits of polynomial graph filters when applied to the Long-Range Ising Model benchmark (LRIM). The study proves that standard filters, which are polynomials …
-
New neural operator L-SplineFNO tackles unstructured meshes for PDE solutions
Researchers have developed L-SplineFNO, a novel neural operator designed to efficiently approximate solutions for partial differential equations on unstructured meshes. This new architecture combines a Fourier Neural Op…
-
Fourier Neural Operators applied to Stochastic Volterra Equations
This paper explores the application of Fourier Neural Operators (FNOs) to learn solutions for stochastic Volterra integral equations (SVIEs), which model random systems with memory. The authors establish a Wong--Zakai c…
-
New AI framework FLUME rapidly emulates urban microclimates
Researchers have developed FLUME, a novel framework utilizing a Fourier Neural Operator to rapidly emulate urban microclimates, specifically wind and temperature fields. This approach addresses the computational limitat…
-
CAFE+FNO enhances Fourier Neural Operators for PDE solutions
Researchers have introduced CAFE+FNO, a novel approach to Fourier Neural Operator (FNO) kernel generation that enhances the learning of high-frequency variations in partial differential equations (PDEs). This method int…
-
New digital twin framework uses AI for bridge health monitoring
Researchers have developed a novel framework for deploying digital twins of bridges using vehicle-integrated sensing. This approach combines physics-based modeling with machine learning, specifically utilizing a Fourier…
-
New feedback design rapidly stabilizes Kuramoto--Sivashinsky equation
Researchers have developed a novel feedback design to rapidly stabilize the Kuramoto--Sivashinsky equation, a complex mathematical model. This new method addresses limitations of previous designs by introducing a second…
-
Function-Space Transformer Adapts Representation for Scientific and Visual Tasks
Researchers have introduced the Function-Space Transformer (FST), a novel framework designed to learn from functions represented by discrete samples. Unlike traditional methods that use fixed grids, FST employs a spatia…
-
Energy efficiency in neural operators for virtual sensing explored
Researchers have explored methods to reduce the energy consumption of neural operators used for virtual sensing, a process that reconstructs physical fields from observations. Their study found that techniques like comp…
-
New neural operator VIOT accelerates incompressible flow transport
Researchers have developed a new generative neural operator called Variational Incompressible Optimal Transport (VIOT) designed for efficient density transport in incompressible flows. VIOT utilizes a stream-function or…
-
New PI-CP method enhances uncertainty quantification for neural operators
Researchers have developed a new method called Physics-Informed Conformal Prediction (PI-CP) to provide reliable uncertainty estimates for neural operators used in approximating solutions to partial differential equatio…
-
Neural Cellular Automata learn long-term PDE dynamics, outperforming baselines
Researchers have developed a novel Neural Cellular Automata (NCA) model designed to learn and predict the long-term dynamics of partial differential equations (PDEs). This NCA-based surrogate model operates by learning …
-
AI models for physics: Caltech professor pioneers structure-driven approach
Anima Anandkumar, a professor at the California Institute of Technology, has pioneered the development of AI models for complex physical systems, challenging the prevailing notion that scale is the only path to progress…
-
Neural operators learn Kohn-Sham map for faster DFT calculations
Researchers have developed a novel approach to density functional theory (DFT) by using neural operators to learn the Kohn-Sham map, which bypasses the computationally intensive orbital diagonalization step. This method…