Evaluating GHG components using artificial intelligence: Connection weight approach

The obligation to control the fast increase of emitted greenhouse gas (GHG) for world climate change reduction is the duty of all countries. The significance of the contributing factors to GHG emission, i.e., fuel factor, intensity, economic structure and activity is investigated. Connection weight approach of artificial neural network (ANN) was employed for this study. This paper quantifies the variables responsible for the GHG emissions over the period 1990-2000 in the industrial sectors of Canada. It was discovered that activity effect was the main determinant of the GHG emissions with fuel factor the least significant. The investigation should give a clue to policymakers on how to reduce GHG emissions.