Modelling carbon dioxide emissions under a maize-soy rotation using machine learning. (December 2021)

• Record Type: Journal Article
• Authors: Abbasi, Naeem A.; Hamrani, Abderrachid; Madramootoo, Chandra A.; Zhang, Tiequan; Tan, Chin S.; Goyal, Manish K.
• Is Part Of: Biosystems engineering. Volume 212(2021)
• Page Start: 1
• Page End: 18
• Publication Date: 2021-12
• Subjects: CO2 emissions -- Agricultural soils -- Machine learning algorithms -- Classic regression -- Shallow neural networks; Bioengineering -- Periodicals; Agricultural engineering -- Periodicals; Biological systems -- Periodicals; Génie rural -- Périodiques; Systèmes biologiques -- Périodiques; 631
• DOI: 10.1016/j.biosystemseng.2021.09.013
• Languages: English
• ISSNs: 1537-5110

Abstract

Abstract : Climatic parameters influence CO2 emissions and the complexity of the relationship is not fully captured in biophysical models. Machine learning (ML) is now being applied to environmental problems, and it is, therefore, opportune to investigate ML models in CO2 predictions from agricultural soils. In this study, six ML models were compared for their predictive performance by comparing field measurements of CO2 emissions from two fertiliser treatments: inorganic fertiliser (IF) and solid cattle manure supplemented with inorganic fertiliser (SCM) applied to a maize-soy rotation. The study also included a generalised scenario where all the data from IF and SCM were included in one dataset. The ML models include support vector machine (SVM), random forest (RF), least absolute shrinkage and selection operator (LASSO), feed-forward neural network (FNN), radial basis function neural network (RBFNN), and extreme learning machine (ELM). The input parameters were soil moisture, soil temperature, soil organic matter, soil total carbon, soil total nitrogen, air temperature, solar radiation and pan evaporation, while the output parameter was field measured CO2 emissions. The results of this study demonstrated that RF was the best at predicting CO2 emissions from IF [coefficient of determination (R 2 ) = 0.92 and root mean square error (RMSE) = 2.27], SCM (R 2 = 0.94 and RMSE = 2.86) and generalised scenarios (R 2 = 0.86 and RMSE = 3.05). We conclude that ML models provide an innovative, robust and time-efficient alternative to biophysical models. Graphical abstract: Image 1 Highlights: Machine learning (ML) models are an effective and efficient alternative to mechanistic models for predicting CO2 emissions from agricultural soils. Random forest (RF), a classical regression ML model, is a suitable algorithm to predict soil CO2 emissions regardless of fertiliser scenario. Feed-forward neural network (FNN) provides acceptable predictive performance for CO2 emissions, but it does not provide consistent predictive performance in K-Fold cross-validation. 75% data in the training phase is optimum to provide robust ML performance when predicting CO2 emissions from agricultural soils under maize-soy rotation.