Data-driven models

Summary

File: src/models/data_driven/. All use DiscreteIntegrator. ESN_model (and its save/load config, ESNConfig) lives in the rnns/ subpackage — future RNN architectures join it there. ESN_model mixes in EchoStateNetwork — the reservoir core from the external echostatenetwork package (re-exported by romda.models.data_driven for convenience; see its own documentation for the reservoir API) — and POD_ESN mixes in ESN_model and POD.

Class	Key parameters	Notes
ESN_model	N_units, rho, sigma_in, N_wash	Inherits EchoStateNetwork; requires training data at init
POD_ESN	N_modes, sensor_locations	Inherits ESN_model + POD; sensor placement via QR
LinearModel	F (transition matrix), Q_noise	\(\boldsymbol{\psi}_{t+1} = \mathbf{F}\boldsymbol{\psi}_t + \boldsymbol{\eta}_t\)

Model pages

• Echo State Network model
• POD-ESN model
• Linear model
• Projectors and modal decompositions

The Projector hierarchy (POD/SPOD) and the standalone decomposition functions (pod_utils.py) live in the autoencoders/ subpackage. Import everything from romda.models.data_driven (or its autoencoders subpackage).

Model pages

• Echo State Network model
• POD-ESN model
• Linear model
• Projectors and modal decompositions