Understanding nitrous oxide (N₂O) emissions from agricultural soils in semi-arid regions is required to better understand terrestrial global N₂O losses. Nitrous oxide emissions were measured from a rain-fed, cropped soil in a semi-arid region of south-western Australia for one year on a sub-daily basis. The site included N-fertilised (100 kg N/ha/yr) and non-fertilised plots. Emissions were measured using soil chambers connected to a fully automated system that measured N₂O using gas chromatography. Daily N₂O emissions were low (-1.8 to 7.3 g N₂O-N/ha/day) and culminated in an annual loss of 0.11 kg N₂O-N/ha from N fertilised soil (100 kg N/ha/yr) and 0.09 kg N₂O-N/ha from the non-fertilised soil. Over half (55%) the annual N₂O emission occurred from both N treatments when the soil was fallow, and following a series of summer rainfall events. At this time soil of the year, conditions were conducive for soil microbial N₂O production: elevated soil water contents, available N, soil temperatures generally >25 °C, and no active plant growth. The proportion of N fertiliser emitted as N₂O after one year, and after correction for the ‘background' (no N fertiliser applied) was 0.02%. The emission factor reported in this study is 60 times lower than IPPC default value for the application of synthetic fertilisers to land (1.25%), suggesting that this value may not be suitable for cropped soils in semi-arid regions. Applying N fertiliser did not significantly increase the annual N₂O emission; demonstrating that a proportion of N₂O emitted from agricultural soils may not be directly derived from the application of N fertiliser. ‘Background' emission, however, needs to be accounted for if we are to fully assess the impact of agriculture in semi-arid regions on terrestrial global N₂O emissions.