Modeling of energy and emissions from animal manure using machine learning methods: the case of the Western Mediterranean Region, Turkey.

Abstract

In Turkey, facilities for the use of biomass resources in energy production are increasing, and new conversion facilities are commissioned every year to provide environmentally friendly energy production. Therefore, reliable energy potential estimates are needed. In this study, the animal manure-based-biogas potentials of Antalya, Isparta, and Burdur provinces in the Western Mediterranean Region of Turkey were calculated. Here, special information on cattle, small ruminants, and poultry, and animal age, number, and manure amount information were used in detail. In addition, carbon dioxide emissions, coal, electricity, and thermal energy, methane emission values with the Tier 1 and Tier 2 approaches were calculated and predicted by machine learning algorithms. To determine the model with the best results, machine learning algorithms support vector machine (SVM), multi-layer perceptron (MLP), and linear regression (LR) were used, and hyper-parameter optimization was performed. According to the results of biogas potential, CO2 emission, electricity production, and thermal energy estimations SVM models are seen as the best models with R2 = 0.999. When the coal amount estimation is examined, the LR models produce better results than SVM and MLP with R2 = 0.997. In the estimation of CH4 using the Tier 1 approach, the MLP model can perform the best estimation with R2 = 0.977. In the CH4 modeling obtained using the Tier 2 approach, the LR models were superior to the other models with the performance value of R2 = 0.962.