, 14(2). 2023.\n
\n
@article{\n title = {GHG Global Emission Prediction of Synthetic N Fertilizers Using Expectile Regression Techniques},\n type = {article},\n year = {2023},\n keywords = {air quality,bio-meteorology,expectile regression,greenhouse gas emissions,nitrogen-based fertilizers,nitrous oxide,supervised machine learning},\n volume = {14},\n websites = {https://www.mdpi.com/2073-4433/14/2/283*},\n id = {3662561c-eac2-38ab-9065-d5b6848f2493},\n created = {2023-03-14T21:54:18.604Z},\n accessed = {2023-05-23},\n file_attached = {false},\n profile_id = {be6263d9-e5f6-3436-8031-6661eb6f0f4d},\n last_modified = {2023-05-23T15:37:37.939Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {false},\n hidden = {false},\n private_publication = {true},\n abstract = {Agriculture accounts for a large percentage of nitrous oxide ((Formula presented.)) emissions, mainly due to the misapplication of nitrogen-based fertilizers, leading to an increase in the greenhouse gas (GHG) footprint. These emissions are of a direct nature, released straight into the atmosphere through nitrification and denitrification, or of an indirect nature, mainly through nitrate leaching, runoff, and (Formula presented.) volatilization processes. (Formula presented.) emissions are largely ascribed to the agricultural sector, which represents a threat to sustainability and food production, subsequent to the radical contribution to climate change. In this connection, it is crucial to unveil the relationship between synthetic N fertilizer global use and (Formula presented.) emissions. To this end, we worked on a dataset drawn from a recent study, which estimates direct and indirect (Formula presented.) emissions according to each country, by the Intergovernmental Panel on Climate Change (IPCC) guidelines. Machine learning tools are considered great explainable techniques when dealing with air quality problems. Hence, our work focuses on expectile regression (ER) based-approaches to predict (Formula presented.) emissions based on N fertilizer use. In contrast to classical linear regression (LR), this method allows for heteroscedasticity and omits a parametric specification of the underlying distribution. ER provides a complete picture of the target variable’s distribution, especially when the tails are of interest, or in dealing with heavy-tailed distributions. In this work, we applied expectile regression and the kernel expectile regression estimator (KERE) to predict direct and indirect (Formula presented.) emissions. The results outline both the flexibility and competitiveness of ER-based techniques in regard to the state-of-the-art regression approaches.},\n bibtype = {article},\n author = {Benghzial, K. and Raki, H. and Bamansour, S. and Elhamdi, M. and Aalaila, Y. and Peluffo-Ordóñez, D.H.},\n doi = {10.3390/atmos14020283},\n journal = {Atmosphere},\n number = {2}\n}
\n
\n Agriculture accounts for a large percentage of nitrous oxide ((Formula presented.)) emissions, mainly due to the misapplication of nitrogen-based fertilizers, leading to an increase in the greenhouse gas (GHG) footprint. These emissions are of a direct nature, released straight into the atmosphere through nitrification and denitrification, or of an indirect nature, mainly through nitrate leaching, runoff, and (Formula presented.) volatilization processes. (Formula presented.) emissions are largely ascribed to the agricultural sector, which represents a threat to sustainability and food production, subsequent to the radical contribution to climate change. In this connection, it is crucial to unveil the relationship between synthetic N fertilizer global use and (Formula presented.) emissions. To this end, we worked on a dataset drawn from a recent study, which estimates direct and indirect (Formula presented.) emissions according to each country, by the Intergovernmental Panel on Climate Change (IPCC) guidelines. Machine learning tools are considered great explainable techniques when dealing with air quality problems. Hence, our work focuses on expectile regression (ER) based-approaches to predict (Formula presented.) emissions based on N fertilizer use. In contrast to classical linear regression (LR), this method allows for heteroscedasticity and omits a parametric specification of the underlying distribution. ER provides a complete picture of the target variable’s distribution, especially when the tails are of interest, or in dealing with heavy-tailed distributions. In this work, we applied expectile regression and the kernel expectile regression estimator (KERE) to predict direct and indirect (Formula presented.) emissions. The results outline both the flexibility and competitiveness of ER-based techniques in regard to the state-of-the-art regression approaches.\n