BACKGROUND: For pediatric pneumonia, the meteorological and air pollution indicators had been frequently investigated for their association with viral circulation, however, not for their impact on disease severity. METHODS: We performed a 10-year prospective observational study in one hospital in Chongqing, China to recruit children with pneumonia. Eight commonly seen respiratory viruses were tested. Autoregressive distributed lag (ADL) and Random forest (RF) models were performed to fit monthly detection rates of each virus at population level and predict the possibility of severe pneumonia at individual level, respectively. RESULTS: Between 2009?2018, 6 611 pediatric pneumonia patients were included, and 4 846 (73.3%) tested positive for at least one respiratory virus. The median age of the patients was 9 (IQR: 4?20) months. ADL models demonstrated a decent fitting of detection rates of four viruses (R2 >0.7 for RSV, HRV, PIV, and HMPV). Based on the RF models, the AUC for host-related factors alone is 0.88 (95% CI: 0.87?0.89), 0.86 (95% CI: 0.85?0.88) for meteorological and air pollution indicators alone, and 0.62 (95% CI: 0.60?0.63) for viral infections alone. The final model indicated that nine weather and air pollution indicators were important determinants of severe pneumonia, with relative contribution of 62.53%, significantly higher than respiratory viral infections (7.36%). CONCLUSIONS: Meteorological and air pollution predictors contributed more to severe pneumonia in children than respiratory viruses. These meteorological data could help predict times when children would be at increased risk for severe pneumonia, and interventions such as reducing outdoor activities, may be warranted.