Environmental Pollution, June, 2013, Vol.177, p.156(8)
To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.envpol.2013.02.019 Byline: Aurore Philibert (b)(a), Chantal Loyce (b)(a), David Makowski (a)(b) Abstract: Nitrous oxide is a potent greenhouse gas, with a global warming potential 298 times greater than that of CO.sub.2. In agricultural soils, N.sub.2O emissions are influenced by a large number of environmental characteristics and crop management techniques that are not systematically reported in experiments. Random Forest (RF) is a machine learning method that can handle missing data and ranks input variables on the basis of their importance. We aimed to predict N.sub.2O emission on the basis of local information, to rank environmental and crop management variables according to their influence on N.sub.2O emission, and to compare the performances of RF with several regression models. RF outperformed the regression models for predictive purposes, and this approach led to the identification of three important input variables: N fertilization, type of crop, and experiment duration. This method could be used in the future for prediction of N.sub.2O emissions from local information. Author Affiliation: (a) INRA, UMR 211 Agronomie, F-78000 Thiverval Grignon, France (b) AgroParisTech, UMR 211 Agronomie, F-78000 Thiverval Grignon, France Article History: Received 23 November 2012; Revised 25 January 2013; Accepted 8 February 2013
Atmospheric Carbon Dioxide -- Analysis ; Global Warming Potential -- Analysis ; Greenhouse Gases -- Analysis ; Air Pollution -- Analysis ; Nitrous Oxide -- Analysis ; Global Warming -- Analysis
Cengage Learning, Inc.