Lightning accompanied by inconsequential rainfall (i.e., ''dry'' lightning) is the primary natural ignition source for wildfires globally. This paper presents a machine-learning and statistical-classification analysis of dry and ''wet'' thunderstorm days in relation to associated atmospheric conditions. The study is based on daily data for lightning-flash count and precipitation from ground-based sensors and gauges and a comprehensive set of atmospheric variables that are based on ERA-Interim for the period from 2004 to 2013 at six locations in Australia. These locations represent a wide range of climatic zones (temperate, subtropical, and tropical).Quadratic surface representations and low-dimensional summary statistics were used to characterize the main features of the atmospheric fields. Four prediction skill scores were considered, and 10-fold cross validation was used to evaluate the performance of each classifier. The results were compared with those obtained by adopting the approach used in an earlier study for the U.S. Pacific Northwest. It was found that both approaches have prediction skill when tested against independent data, that mean atmospheric field quantities proved to be the most influential variables in determining dry-lightning activity, and that no single classifier or set of atmospheric variables proved to be consistently superior to its counterpart for the six sites examined here.