Fertilizer management for global ammonia emission reduction

• Published in: Nature (London) Vol. 626; no. 8000; pp. 792 - 798
• Main Authors: Xu, Peng, Li, Geng, Zheng, Yi, Fung, Jimmy C. H., Chen, Anping, Zeng, Zhenzhong, Shen, Huizhong, Hu, Min, Mao, Jiafu, Zheng, Yan, Cui, Xiaoqing, Guo, Zhilin, Chen, Yilin, Feng, Lian, He, Shaokun, Zhang, Xuguo, Lau, Alexis K. H., Tao, Shu, Houlton, Benjamin Z.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 22.02.2024; Nature Publishing Group
• Subjects: 704/844/2739/2807; 706/1143; Agricultural land; agriculture; Air pollution; Air quality; Ammonia; Artificial intelligence; Climate change; Climate change scenarios; Corn; Crop production; Crops; Cultivation; Datasets; Emissions; Emissions control; environmental health; Environmental policy; ENVIRONMENTAL SCIENCES; Fertilizers; Future climates; Grain cultivation; Humanities and Social Sciences; Learning algorithms; Machine learning; multidisciplinary; Nitrogen; Outdoor air quality; Rice; Science; Science (multidisciplinary); Wheat; Southeast Asia; United States > US; Asia; Europe; China; Africa; Brazil; North America; Oceania; India
• ISSN: 0028-0836; 1476-4687; 1476-4687
• DOI: 10.1038/s41586-024-07020-z

Crop production is a large source of atmospheric ammonia (NH 3 ), which poses risks to air quality, human health and ecosystems 1 – 5 . However, estimating global NH 3 emissions from croplands is subject to uncertainties because of data limitations, thereby limiting the accurate identification of mitigation options and efficacy 4 , 5 . Here we develop a machine learning model for generating crop-specific and spatially explicit NH 3 emission factors globally (5-arcmin resolution) based on a compiled dataset of field observations. We show that global NH 3 emissions from rice, wheat and maize fields in 2018 were 4.3 ± 1.0 Tg N yr −1 , lower than previous estimates that did not fully consider fertilizer management practices 6 – 9 . Furthermore, spatially optimizing fertilizer management, as guided by the machine learning model, has the potential to reduce the NH 3 emissions by about 38% (1.6 ± 0.4 Tg N yr −1 ) without altering total fertilizer nitrogen inputs. Specifically, we estimate potential NH 3 emissions reductions of 47% (44–56%) for rice, 27% (24–28%) for maize and 26% (20–28%) for wheat cultivation, respectively. Under future climate change scenarios, we estimate that NH 3 emissions could increase by 4.0 ± 2.7% under SSP1–2.6 and 5.5 ± 5.7% under SSP5–8.5 by 2030–2060. However, targeted fertilizer management has the potential to mitigate these increases. A machine learning model for generating crop-specific and spatially explicit NH 3 emission factors globally shows that global NH 3 emissions in 2018 were lower than previous estimates that did not fully consider fertilizer management practices.