ODINN.A_fake
— FunctionA_fake(temp, noise=false)
Fake law establishing a theoretical relationship between ice viscosity (A) and long-term air temperature.
ODINN.SIA!
— MethodSIA!(dH, H, context)
Compute an in-place step of the Shallow Ice Approximation PDE in a forward model
ODINN.SIA
— MethodSIA(H, A, context)
Compute a step of the Shallow Ice Approximation UDE in a forward model. Allocates memory.
ODINN.avg
— Methodavg(A)
4-point average of a matrix
ODINN.avg_surface_V
— Functionavg_surface_V(H, B, temp)
Computes the average ice velocity for a given input temperature
ODINN.avg_x
— Methodavg_x(A)
2-point average of a matrix's X axis
ODINN.avg_y
— Methodavg_y(A)
2-point average of a matrix's Y axis
ODINN.batch_iceflow_PDE
— Methodbatch_iceflow_PDE(climate, gdir, context)
Solve the Shallow Ice Approximation iceflow PDE for a given temperature series batch
ODINN.batch_iceflow_UDE
— Methodbatch_iceflow_UDE(θ, H, climate, context)
Solve the Shallow Ice Approximation iceflow UDE for a given temperature series batch
ODINN.diff_x
— Methoddiff_x(A)
2-point differential of a matrix's X axis
ODINN.diff_y
— Methoddiff_y(A)
2-point differential of a matrix's Y axis
ODINN.fillNaN!
— FunctionfillNaN!(x, fill)
Convert empty matrix grid cells into fill value
ODINN.generate_ref_dataset
— Functiongenerate_ref_dataset(temp_series, H₀)
Generate reference dataset based on the iceflow PDE
ODINN.get_NN
— Methodget_NN()
Generates a neural network.
ODINN.get_initial_geometry
— Functionget_initial_geometry(glacier_gd)
Retrieves the initial glacier geometry (bedrock + ice thickness) for a glacier.
ODINN.iceflow!
— Methodiceflow!(dH, H, context,t)
Runs a single time step of the iceflow PDE model in-place
ODINN.iceflow_NN
— Methodiceflow_NN(H, θ, t, context, temps, UA)
Runs a single time step of the iceflow UDE model
ODINN.initialize_ODINN
— MethodInitialize_ODINN(processes, python_path)
Initializes ODINN by configuring PyCall based on a given Python path. It also configures multiprocessing for a given number of processes.
ODINN.inn
— Methodinn(A)
Access the inner part of the matrix (-2,-2)
ODINN.loss_iceflow
— Methodloss_iceflow(θ, context, UA, PDE_refs::Dict{String, Any}, temp_series)
Loss function based on glacier ice velocities and/or ice thickness
ODINN.predict_A̅
— Methodpredict_A̅(UA, θ, temp)
Predicts the value of A with a neural network based on the long-term air temperature.
ODINN.predict_iceflow
— Methodpredict_iceflow(θ, UA, context, temp_series)
Makes a prediction of glacier evolution with the UDE for a given temperature series
ODINN.retrieve_context
— Methodretrieve_context(context::ArrayPartition)
Retrieves context variables for computing the surface velocities of the PDE.
ODINN.retrieve_context
— Methodretrieve_context(context::Tuple)
Retrieves context variables for computing the surface velocities of the UDE.
ODINN.simulate_iceflow_PDE
— Methodsimulate_iceflow_PDE(H, context, solver)
Make forward simulation of the SIA PDE.
ODINN.smooth!
— Methodsmooth!(A)
Smooth data contained in a matrix with one time step (CFL) of diffusion.
ODINN.train_iceflow_UDE
— Functiontrain_iceflow_UDE(H₀, UA, θ, train_settings, PDE_refs, temp_series)
Train the Shallow Ice Approximation iceflow UDE