Abstract
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 3.3 Mt 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.
Original language | English |
---|---|
Pages (from-to) | 6525-6535 |
Number of pages | 11 |
Journal | Global Change Biology |
Volume | 27 |
Issue number | 24 |
Early online date | 3 Sept 2021 |
DOIs | |
Publication status | Published - Dec 2021 |
Bibliographical note
Funding Information:This work was financially supported by Natural Science Foundation of China under a grant number 41877546, and a BBSRC–Newton Fund project N‐Circle (BB/N013484/1). Global climate model data was extracted and converted by Dr. Jie Pan from Institute of Environment and Sustainable Development in Agricultural, Chinese Academy of Agricultural Sciences. The authors have no conflict of interest to declare.
Keywords
- cereal
- climate change scenario
- machine learning
- mineral nitrogen fertilizer
- NH volatilization
- nonlinear model