Despite research into the response of ammonia (NH3 ) volatilization in farmland to various meteorological factors, the potential impact of future climate change on NH3 volatilization is not fully understood. Based on a database consisting of 1063 observations across China, nonlinear NH3 models considering crop type, meteorological, soil and management variables were established via four machine learning methods, including support vector machine, multi-layer perceptron, gradient boosting machine and random forest (RF). The RF model had the highest R2 of 0.76 and the lowest RMSE of 0.82 kg NH3 -N ha-1 , showing the best simulation capability. Results of model importance indicated that NH3 volatilization was mainly controlled by total input of N fertilizer, followed by meteorological factors, human managements and soil characteristics. The NH3 emissions of China's cereal production (paddy rice, wheat and maize) in 2018 was estimated to be 3.3Mt NH3 -N. By 2050, NH3 volatilization will increase by 23.1-32.0% under different climate change scenarios (Representative Concentration Pathways, RCPs), and climate change will have the greatest impact on NH3 volatilization in the Yangtze river agro-region of China due to high warming effects. However, the potential increase in NH3 volatilization under future climate change can be mitigated by 26.1-47.5% through various N fertilizer management optimization options.