A Python repository for guiding the construction of forecasting models using SURD.
This work presents a causality-based approach for input selection in turbulence forecasting. The approach is grounded in the Synergistic–Unique–Redundant Decomposition (SURD) of causality, which dissects the information that candidate inputs provide about a target variable into unique, redundant, and synergistic causal components. These components are directly linked to the theoretical limits of predictive performance, quantified through the information-theoretic notion of irreducible error. To estimate these causal contributions in practice, we leverage neural mutual information estimators.
If you use our method in your research or software, please cite the following paper:
@article{martinez2026,
title={Cause-and-effect approach to turbulence forecasting},
author={Mart{\'\i}nez-S{\'a}nchez, {\'A}lvaro and Lozano-Dur{\'a}n, Adri{\'a}n},
journal={International Journal of Numerical Methods for Heat \& Fluid Flow},
pages={1--29},
year={2026},
publisher={Emerald Publishing Limited}
}This project is licensed under the MIT License - see the LICENSE.md file for details.