气候变化领域集成服务门户(CCPortal): Machine learning for predicting greenhouse gas emissions from agricultural soils

CCPortal

DOI	10.1016/j.scitotenv.2020.140338
	Machine learning for predicting greenhouse gas emissions from agricultural soils
	Hamrani A.; Akbarzadeh A.; Madramootoo C.A.
发表日期	2020
ISSN	489697
卷号	741
英文摘要	Machine learning (ML) models are increasingly used to study complex environmental phenomena with high variability in time and space. In this study, the potential of exploiting three categories of ML regression models, including classical regression, shallow learning and deep learning for predicting soil greenhouse gas (GHG) emissions from an agricultural field was explored. Carbon dioxide (CO2) and nitrous oxide (N2O) fluxes, as well as various environmental, agronomic and soil data were measured at the site over a five-year period in Quebec, Canada. The rigorous analysis, which included statistical comparison and cross-validation for the prediction of CO2 and N2O fluxes, confirmed that the LSTM model performed the best among the considered ML models with the highest R coefficient and the lowest root mean squared error (RMSE) values (R = 0.87 and RMSE = 30.3 mg·m−2·hr−1 for CO2 flux prediction and R = 0.86 and RMSE = 0.19 mg·m−2·hr−1 for N2O flux prediction). The predictive performances of LSTM were more accurate than those simulated in a previous study conducted by a biophysical-based Root Zone Water Quality Model (RZWQM2). The classical regression models (namely RF, SVM and LASSO) satisfactorily simulated cyclical and seasonal variations of CO2 fluxes (R = 0.75, 0.71 and 0.68, respectively); however, they failed to reasonably predict the peak values of N2O fluxes (R < 0.25). Shallow ML was found to be less effective in predicting GHG fluxes than other considered ML models (R < 0.7 for CO2 flux and R < 0.3 for estimating N2O fluxes) and was the most sensitive to hyperparameter tuning. Based on this comprehensive comparison study, it was elicited that the LSTM model can be employed successfully in simulating GHG emissions from agricultural soils, providing a new perspective on the application of machine learning modeling for predicting GHG emissions to the environment. © 2020 Elsevier B.V.
英文关键词	Agricultural soil; Classical regression; Deep learning; Greenhouse gas emissions; Machine learning; Shallow learning
scopus关键词	Agricultural robots; Agriculture; Carbon dioxide; Deep learning; Forecasting; Gas emissions; Greenhouse gases; Learning algorithms; Learning systems; Logistic regression; Mean square error; Nitrogen oxides; Soils; Water quality; Agricultural fields; Comprehensive comparisons; Environmental phenomena; Machine learning models; Predictive performance; Root mean squared errors; Root Zone Water Quality Model (RZWQM2); Statistical comparisons; Long short-term memory; carbon dioxide; nitrous oxide; agricultural soil; carbon dioxide; carbon emission; greenhouse gas; machine learning; nitrous oxide; prediction; regression analysis; soil emission; agricultural soil; Article; biophysics; Canada; carbon footprint; controlled study; deep learning; greenhouse gas; machine learning; measurement accuracy; priority journal; process optimization; random forest; seasonal variation; simulation training; soil; Canada; Quebec [Canada]
来源期刊	Science of the Total Environment
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/176759
作者单位	Department of Bioresource Engineering, McGill University, Montreal, QC H9X3V9, Canada
推荐引用方式 GB/T 7714	Hamrani A.,Akbarzadeh A.,Madramootoo C.A.. Machine learning for predicting greenhouse gas emissions from agricultural soils[J],2020,741.
APA	Hamrani A.,Akbarzadeh A.,&Madramootoo C.A..(2020).Machine learning for predicting greenhouse gas emissions from agricultural soils.Science of the Total Environment,741.
MLA	Hamrani A.,et al."Machine learning for predicting greenhouse gas emissions from agricultural soils".Science of the Total Environment 741(2020).