BIBLIOS

Tipo
Artigos em Revista

Tipo de Documento
Artigo Completo

Título
A comparison of two causal methods in the context of climate analyses

Participantes na publicação
David Docquier (Author)
Giorgia Di Capua (Author)
Reik V. Donner (Author)
Carlos A. L. Pires (Author)
Dep. Engenharia Geográfica, Geofísica e Energia
Amélie Simon (Author)
Stéphane Vannitsem (Author)

Resumo
Correlation does not necessarily imply causation, and this is why causal methods have been developed to try to disentangle true causal links from spurious relationships. In our study, we use two causal methods,\nnamely, the Liang–Kleeman information flow (LKIF) and the Peter and Clark momentary conditional independence (PCMCI) algorithm, and we apply them to four different artificial models of increasing complexity and one\nreal-world case study based on climate indices in the Atlantic and Pacific regions. We show that both methods\nare superior to the classical correlation analysis, especially in removing spurious links. LKIF and PCMCI display some strengths and weaknesses for the three simplest models, with LKIF performing better with a smaller\nnumber of variables and with PCMCI being best with a larger number of variables. Detecting causal links from\nthe fourth model is more challenging as the system is nonlinear and chaotic. For the real-world case study with\nclimate indices, both methods present some similarities and differences at monthly timescale. One of the key\ndifferences is that LKIF identifies the Arctic Oscillation (AO) as the largest driver, while the El Niño–Southern\nOscillation (ENSO) is the main influencing variable for PCMCI. More research is needed to confirm these links,\nin particular including nonlinear causal methods.


Instituição
Instituto Dom Luiz (IDL), Faculdade de Ciências, Universidade de Lisboa, Campo Grande, 1749–016, Lisboa, Portugal

Suporte
Nonlinear Processes in Geophysics

Identificadores da Publicação
ISSN - 1607-7946

Editora
Copernicus GmbH



Identificadores do Documento
DOI - https://doi.org/10.5194/npg-31-115-2024
URL - http://dx.doi.org/10.5194/npg-31-115-2024