neural_operators

Neural operators (DeepONet, PCANet, FNO) and the supporting infrastructure (PDE forward models, Gaussian priors, MCMC, plotting) used to apply them to parametric PDE problems.

Applications (survey article, book chapter) live in a separate repo, applications_neural_operators.

Installation

FEniCSx (dolfinx, ufl, petsc4py, mpi4py) and PyTorch are installed from conda-forge, not pip – see the README for why.

conda env create -f neuralop.yml
conda activate neuralopv2

API reference

• neural_operators.data
  • DataHandler
  • DataProcessor
  • DataProcessorFNO
  • DataProcessorTF
• neural_operators.pde
  • PDEModel
  • build_vector_vertex_maps()
  • eval_at_vertices()
  • function_to_vector()
  • function_to_vertex()
  • vector_to_function()
  • vector_to_vertex()
  • vertex_to_function()
  • vertex_to_vector()
  • apply_grid_vector_dirichlet_bc()
  • get_dirichlet_bc()
  • get_grid_dirichlet_bc()
  • interpolate_mixed_vector_to_grid()
  • mesh_cells()
  • test_dirichlet_bc_functions()
  • write_mesh_xdmf()
• neural_operators.prior
  • PriorSampler
• neural_operators.nn
  • get_surrogate_specs()
  • load_data_and_model()
  • load_surrogate_model()
  • MLP
  • DeepONet
  • load_data_and_deeponet()
  • PCANet
  • load_data_and_pcanet()
  • FNO2D
  • FNO2DLayer
  • load_data_and_fno()
• neural_operators.mcmc
  • MCMC
  • State
  • Tracer
  • SurrogateModel
  • SurrogateModelFNO
  • CorrectedSurrogateModel
  • compute_sample_errors()
  • mcmc_plot_fields()
  • mcmc_plot_fields_base()
  • plot_mcmc_tracer_results()
• neural_operators.plotting
  • field_plot()
  • field_plot_grid()
  • quick_field_plot()
  • quick_field_plot_grid()
  • vector_values_at_nodes()
  • point_plot()
  • quick_point_plot()
  • get_default_plot_mix_collection_data()
  • plot_collection()
  • plot_collection_grid()
  • plot_mix_collection()
  • plot_curve()
  • plot_loss()
  • locate_index()
  • plot_s_vec_values()