Premium
On the observational assessment of climate model performance
Author(s) -
Annan J. D.,
Hargreaves J. C.,
Tachiiri K.
Publication year - 2011
Publication title -
geophysical research letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.007
H-Index - 273
eISSN - 1944-8007
pISSN - 0094-8276
DOI - 10.1029/2011gl049812
Subject(s) - probabilistic logic , component (thermodynamics) , climate model , computer science , observational study , econometrics , ensemble forecasting , ensemble average , climate system , statistical model , climate change , environmental science , climatology , machine learning , statistics , artificial intelligence , mathematics , geology , physics , oceanography , thermodynamics
Comparison of model outputs with observations of the climate system forms an essential component of model assessment and is crucial for building our confidence in model predictions. Methods for undertaking this comparison are not always clearly justified and understood. Here we show that the popular approach of comparing the ensemble spread to a so‐called “observationally‐constrained pdf” can be highly misleading. Such a comparison will almost certainly result in disagreement, but in reality tells us little about the performance of the ensemble. We present an alternative approach, and show how it may lead to very different, and rather more encouraging, conclusions. We additionally present some necessary conditions for an ensemble (or more generally, a probabilistic prediction) to be challenged by an observation.