Probabilistic forecasting of temperature: comments on the Bayesian Model Averaging approach

2004/09/24 by Stephen Jewson, Jewson, Stephen
Physics and Astronomy · #Atmospheric and Oceanic Physics (physics.ao-ph) #FOS: Physical sciences #physics.ao-ph

paper · pdf · doi:10.48550/arxiv.physics/0409127

arxiv created 2004/09/24 · arxiv updated 2009/12/01

Abstract

A specific implementation of Bayesian model averaging has recently been suggested as a method for the calibration of ensemble temperature forecasts. We point out the similarities between this new approach and an earlier method known as kernel regression. We also argue that the Bayesian model averaging method (as applied) has a number of flaws that would result in forecasts with suboptimally calibrated mean and uncertainty.

Related

• Moment based methods for ensemble assessment and calibration
• Do probabilistic medium-range temperature forecasts need to allow for non-normality?
• Probabilistic temperature forecasting: a summary of our recent research results
• Comparing the ensemble mean and the ensemble standard deviation as inputs for probabilistic medium-range temperature forecasts
• Probabilistic temperature forecasting: a comparison of four spread-regression models