التفاصيل البيبلوغرافية
| العنوان: |
Uncertainty quantification of nitrogen use efficiency prediction in China using Monte Carlo simulation and quantile regression forests. |
| المؤلفون: |
Liu, Yingxia1,2,3 (AUTHOR), Heuvelink, Gerard B.M.2,3 (AUTHOR), Bai, Zhanguo3 (AUTHOR), He, Ping1 (AUTHOR) heping02@caas.cn |
| المصدر: |
Computers & Electronics in Agriculture. Jan2023, Vol. 204, pN.PAG-N.PAG. 1p. |
| مصطلحات موضوعية: |
*MONTE Carlo method, *QUANTILE regression, *RANDOM forest algorithms, *FORECASTING, *NITROGEN, *SUSTAINABILITY |
| مصطلحات جغرافية: |
CHINA |
| مستخلص: |
[Display omitted] • Nitrogen use efficiency prediction uncertainty in China decreased over time. • Northeast China had a lower partial factor productivity uncertainty in 2015. • Northeast China had a higher partial nutrient balance uncertainty in 2015. • Most provinces in China had smaller input uncertainty than model uncertainty. • The partial nutrient balance had a higher input uncertainty contribution in 2015. Nitrogen use efficiency (NUE) plays an essential role in food security and environmental sustainability. With the development of technology, NUE prediction by models has come available. However, the prediction uncertainty of NUE models is still poorly understood. This study aimed to analyze uncertainty in NUE predictions obtained from a random forest machine learning model. Input and model uncertainties were quantified using Monte Carlo simulation in three scenarios and quantile regression forests (QRF), respectively, to analyze how these uncertainties propagate to the NUE predictions for 31 provinces in China from 1978 to 2015. Two NUE indicators were considered: the partial factor productivity of nitrogen (PFP N) and the partial nutrient balance of nitrogen (PNB N). The results indicated that the prediction uncertainty for both NUE indicators decreased over time. In 2015, PFP N had a higher 90% prediction interval ratio (PIR 90) of input data in south and west China and a higher 90% prediction interval width (PIW 90) in south and east-coastal China, while PNB N had a higher PIR 90 in north China and a higher PIW 90 in northeast China. The NUE prediction uncertainty propagated from QRF models had similar spatial patterns as those resulting from uncertainty in input data. NUE in most provinces had smaller input uncertainty than model uncertainty, except PNB N , which had smaller model uncertainty than input uncertainty after 2010. Generally, PNB N had higher input uncertainty contributions than PFP N in 2015, especially in south and northeast China. Overall, the uncertainties in NUE predictions were substantial. A series of recommendations were made to improve the accuracy of NUE predictions. These may be applied by the government, in order to inform sustainable nitrogen management in agroecological systems. [ABSTRACT FROM AUTHOR] |
| قاعدة البيانات: |
Academic Search Index |
