Modeling and prediction of ammonia emission from field-applied animal manure
Sustainable process-product development & green chemistry
Sustainable & Clean Technologies - III: Combustion & Emission (T1-6P)
Keywords: ammonia emission; livestock manure; Michaelis-Menten equation; multivariate linear regression (MLR), artificial neural network (ANN); principle component analysis (PCA); weight partitioning method (WPM)
Ammonia emission from field-applied pig manure slurry is studied using Michaelis-Menten equation. The two model parameters (total emission of ammonia and time to reach half of the total emission) of the Michaelis-Menten equation are estimated using a multivariate linear regression (MLR) method and a feedforward-backpropagation artificial neural network (ANN) approach on the basis of ALFAM (Ammonia Loss from Field-applied Animal Manure) database in Europe.
The MLR method well describes the ammonia emission tendency with variation in the emission factor. However, ammonia emission from manure slurry is too complex to be captured in a linear regression model. This necessitates a model which can describe complex nonlinear effects between the ammonia emission variables such as soil and manure states, climate and agronomic factors. In the present study, a principle component analysis (PCA) based preprocessing and weight partitioning method (WPM) based postprocessing ANN approach (called the PWA approach) is proposed to account the complex nonlinear effects.
The ammonia emission is predicted with precision by the 11 emission factors, using the nonlinear ANN approach. The relative importance among the 11 emission factors is identified using the elasticity analysis in the MLR method and using the WPM in the ANN approach. The relative significance obtained quantitatively by the PWA approach in the present study gives an excellent explanation of the most important processes controlling NH3 emission.
See the full pdf manuscript of the abstract.
Presented Monday 17, 13:30 to 15:00, in session Sustainable & Clean Technologies - III: Combustion & Emission (T1-6P).
