Predicting and Applying the Electricity-Related Carbon Emission Coefficient based on Recurrent Neural Network: A Decision-Making Reference for Carbon Emission Policies

Le résumé fourni par la source

Carbon emissions exert a profound influence on global climatic variations, with China emerging as a pivotal player in curbing these emissions via energy consumption and transformation. This research elucidates the principles and computational methodologies of the electricity-related carbon emission coefficient, and employs neural network modelling to forecast future carbon emission trajectories and to estimate this coefficient. The findings indicate a prospective decline in overall carbon emissions. Nevertheless, industrial carbon emissions remain predominant and show no substantial reduction; the residential, transport, storage, and postal sectors also exhibit considerable carbon emissions. Consequently, there is an immediate necessity for the industry to undergo a transformation, adopt cleaner energy alternatives to fossil fuels, fully leverage the dual-carbon target for green investment in the industry, and devise policies for carbon emission reduction. By predicting the electricity-related carbon emission coefficient and harnessing its unique attributes prior to calculating carbon emissions, this study offers a crucial foundation and reference for decision-making. Moreover, it aids in the development of emission reduction policies and encourages scientifically sound and reasonable industrial adjustments.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.