Accurate quantification of soil nitric oxide (NO) emissions can establish a scientific foundation for developing targeted strategies to mitigate emissions, thereby reducing their environmental impact. Using a database with 476 field measurements across China, a NO emission model was constructed by employing four machine learning algorithms including Extreme Gradient Boosting (XGBoost), Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN). Our validation with independent observational data revealed that the XGBoost model performed the best, achieving a R