English

Identifying the Causes of Pyrocumulonimbus (PyroCb)

Machine Learning 2022-11-21 v3 Machine Learning

Abstract

A first causal discovery analysis from observational data of pyroCb (storm clouds generated from extreme wildfires) is presented. Invariant Causal Prediction was used to develop tools to understand the causal drivers of pyroCb formation. This includes a conditional independence test for testing YY conditionally independent of EE given XX for binary variable YY and multivariate, continuous variables XX and EE, and a greedy-ICP search algorithm that relies on fewer conditional independence tests to obtain a smaller more manageable set of causal predictors. With these tools, we identified a subset of seven causal predictors which are plausible when contrasted with domain knowledge: surface sensible heat flux, relative humidity at 850850 hPa, a component of wind at 250250 hPa, 13.313.3 micro-meters, thermal emissions, convective available potential energy, and altitude.

Cite

@article{arxiv.2211.08883,
  title  = {Identifying the Causes of Pyrocumulonimbus (PyroCb)},
  author = {Emiliano Díaz Salas-Porras and Kenza Tazi and Ashwin Braude and Daniel Okoh and Kara D. Lamb and Duncan Watson-Parris and Paula Harder and Nis Meinert},
  journal= {arXiv preprint arXiv:2211.08883},
  year   = {2022}
}

Comments

14 pages 9 figures. To be published in the 2022 NeurIPS Workshop on Causal Machine Learning for Real-World Impact

R2 v1 2026-06-28T06:02:11.947Z