loading page

Cross-Attractor Transformations: A Novel Machine Learning Framework to Minimize Forecast Error in the Presence of Model Bias
  • Niraj Agarwal,
  • Daniel E. Amrhein,
Niraj Agarwal

Corresponding Author:[email protected]

Author Profile
Daniel E. Amrhein
Author Profile
Author Profile


Imperfect models are often used for forecasting and state estimation of complex dynamical systems, typically by mapping a reference initial state into model phase space, making a forecast, and then mapping back to the reference space. In many cases these mappings are implicit, and forecast errors thus reflect a combination of model forecast errors and mapping errors. Techniques to infer parameterizations and parameters to reduce model bias have been the subject of intense scrutiny; however, we lack a general framework for discovering optimal mappings between system and model attractors. Here we propose a novel Machine Learning paradigm for inferring cross-attractor transformations (CATs) that minimize forecast error. CATs are pairs of transformations from the phase space of a reference system to the phase space of a model and vice versa that serve as a bridge between the attractors of a true system and an imperfect model. A computationally efficient analog approximation to tangent linear and adjoint models is developed to enable efficient stochastic gradient descent algorithms to train CAT parameters. Neural networks constructed with a custom analog-adjoint layer permit specification of affine transformations as well as more general nonlinear transformations.
30 Dec 2022Submitted to AGU Fall Meeting 2022
02 Jan 2023Published in AGU Fall Meeting 2022