23 datasets found

The dataset used in the paper for training and testing the Physics-Informed Neural Operator (PINO) model.

The dataset used in this paper is a collection of measured responses of various physical processes, including the wave equation, chaotic response of forced Duffing oscillator,...

The dataset used in this paper for testing the DGGO for solving the 1D Burgers equation, 1D time-dependent wave advection equation, 2D Darcy flow equation, and 2D time-dependent...

The dataset used in the paper is a 2D KS system with spatial inhomogeneities. The system is simulated on a grid of size 256x256.

The dataset used in the paper is a 2D KS system with periodic boundary conditions. The system is simulated on a grid of size 256x256.

The dataset used in the paper is a sliding-window approach with an extent of ℓ = 1 and a stride of s = 2. The dataset is a 256x256 grid with 512 nodes, and the state function is...

The dataset used in this paper is a collection of parametrized PDEs, specifically the parametric diffusion equation, with affine parametric dependence on the diffusion term.

The dataset used in this paper is a set of space-time observations of PDE solutions, generated using finite element simulations.

The dataset used in this paper is a collection of slowness models for the Helmholtz equation, generated from the CIFAR-10, OpenFWI Style-A, and STL-10 datasets.

The dataset used for training and testing the neural network for linearizing the heat equation, Burgers equation, and Kuramoto-Sivashinsky equation.

A dataset for continuous PDE dynamics forecasting, including the Navier-Stokes equation.

A dataset for message passing neural PDE solvers, including the Navier-Stokes equation.

The dataset generated by D1Q3 Lattice Boltzmann simulations of the coupled FitzHugh-Nagumo PDEs.

Experimental data set of the cable equation ut = uxx/(RlC) + u/(RmC) with C the capacitance, Rl the longitudinal resistance and Rm the parallel resistance of the circuit.

Experimental data set of the 2D advection-diffusion process described by ut = −∇ · (−D∇u + (cid:126)v).

Synthetic data set of the Burgers equation ut = νuxx − uux, with a delta peak initial condition u(x, t = 0) = Aδ(x) and domain t ∈ [0.1, 1.1], x ∈ [−3, 4].

The dataset used in this paper is a collection of random residual and error vectors, as well as a set of heterogeneous slowness models.

2-D Navier-Stokes vorticity-transport equation

2-D Poisson equation

A machine-learning framework for the numerical solution of the inverse problem in chemotaxis.