Cause-and-effect approach to turbulence forecasting

A Python repository for guiding the construction of forecasting models using SURD.

Introduction

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.

Citation

If you use our method in your research or software, please cite the following paper:

@misc{forecast2025,
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},
archivePrefix={arXiv},
primaryClass={physics.flu-dyn},
eprint={2509.25065},
year={2025}
}

License

This project is licensed under the MIT License - see the LICENSE.md file for details.