fips.InversionPipeline

class fips.InversionPipeline(config, problem, estimator)

Blueprint for inversion.

This class defines the standard workflow for running an inversion, including methods for loading observations and priors, building the forward operator and covariance matrices, and executing the solve process.

Subclasses should implement the abstract methods to handle the specifics of data loading and covariance construction for their particular problem domain.

Parameters:

• config (Any) – Configuration object containing necessary parameters and settings for the pipeline.

• problem (type[_Problem]) – The specific InverseProblem class that defines the mathematical formulation of the problem.

• estimator (type[Estimator] | str) – The estimator to use for solving the inverse problem, either as a class or a string identifier.

Attributes

config	Configuration object containing necessary parameters and settings for the pipeline.
estimator	The estimator to use for solving the inverse problem, either as a class or a string identifier.

Methods

aggregate_obs_space(obs, forward_operator, ...)	Aggregate the observation space.
filter_state_space(obs, prior)	Align or trim the state space before building covariances.
get_constant(obs)	Get optional constant offset vector.
get_forward_operator(obs, prior)	Get forward operator matrix.
get_inputs()	Gather all input components for the inverse problem.
get_modeldata_mismatch(obs)	Get model-data mismatch covariance matrix.
get_obs()	Get observation vector.
get_prior()	Get prior state vector.
get_prior_error(prior)	Get prior error covariance matrix.
run([estimator_kwargs])	Execute the standard inversion workflow.