Synergistic effects of climate change and nitrogen use on future nitric oxide emissions from China's croplands.

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 R2 of 0.67. The most important management, soil, and meteorological variables affecting the NO model were mineral nitrogen input, soil organic carbon content, and air temperature, respectively. This study also found that NO emissions exhibited nonlinear responses to different variables. NO emissions from China's farmland were estimated to be approximately 204.48 kt NO-N in 2020. By 2050, we predicted that NO emissions could increase by 2.9%-9.9% under various climate change scenarios, with the highest increment of 9.9% occurring under the RCP8.5 scenario. The southern agricultural region, which was particularly vulnerable to climate change, experienced the largest increase, ranging from approximately 15%-31%. The implementation of nitrogen management strategies that are adapted to future climate conditions could potentially reduce NO emissions by 15%-16.2%.