Introduction: Childhood pneumonia has been the commonest global cause of morbidity and mortality among under-five children. In developing countries like Ethiopia, it remains to be the highest burden of the health care system. In our country, where the problem varies in space and time, exploring its spatial distribution is of supreme importance for monitoring and designing effective intervention programs.Methods: The two stage stratified cluster sampling technique was utilized along with the 2016 Ethiopian Demographic and Health Survey data to deal with 10,006 under-five children who took part in the study. The Bernoulli model was used by applying the Kulldorff method using the SaTScan software to analyze the purely spatial clusters of under-five pneumonia. Arc GIS version 10.1 was used to visualize the distribution of cases across the country. The mixed-effect Logistic regression model was used to identify the determinants of childhood pneumonia.Result: In this study, the spatial distribution of pneumonia among under-five children was non-random at cluster level (Moran’s I: 0.34, p < 0.001). Statistical significant clusters were found in Tigrai (LLR = 38.53, p < 0.001) and Oromia (LLR = 22.27, p < 0.001) National Regional States.  History of Diarrhea (AOR=4.71, 95% CI:  (3.89-5.71)), 45-59 months of age (AOR= 0.63, 95% CI: (0.45-0.89)), working mothers (AOR=1.27, 95% CI: (1.06-1.52)), mothers’ secondary school education (AOR= 0.65; 95 % CI: (0.43–0.99)), and stunting (AOR= 1.24, 95% CI: (1.00-1.54)) were significant predictors of under-five pneumonia.Conclusion and recommendation: In Ethiopia, pneumonia had spatial variations across the country. Areas with high hotspots of child pneumonia should more focused on by allocating additional resources and providing appropriate interventions that have public health implications.