全球变化知识资源中心

Artificial Intelligence is a topical trend employed to solve engineering and industrial problems by virtue of its abilities to deal with data uncertainty such as methane emissions. Hard computing methods are not suitable for determining the optimal emission in a methane emission data set. Instead, soft computing solutions should be considered in an effort to obtain better optimal solutions for industrial problems. This paper utilized the Guidelines provided in the 2006 Intergovernmental Panel on Climate Change (IPCC) to calculate and project methane emissions front selected six livestock in Sarawak, Malaysia. A particle swarm optimization (PSO) model was developed to project future methane emission by using number of livestock as the input parameter. The total CH4 inventory from the enteric fermentation of cattle, buffaloes, goats, sheep, swine and deer in Sarawak decreased front 1.860 to 1.856 Gg when calculation was carried out using the Tier 1 method. This decrease was due to population growth and the emission factors employed. Three statistical measures, root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) were employed for evaluation. PSO has been shown to be able to give an accurate projection. The results of this study provide a benchmark information which can be used by the Sarawak government to develop appropriate policies and mitigation strategies to reduce future carbon footprint in the Sarawak livestock sector.