The problem of CO2 emissions, as an important factor of air pollution, attracts broad attention. For the purpose of pollution prevention, this paper would establish a reasonable model to study Beijing's impacting factors of carbon emissions and carry out future forecast. This paper use the non-inertia weight coefficient and particle mutation particle swarm optimization (PSO) algorithm to optimize the initial connection weights and thresholds of the traditional BP neural network, and establish a BP neural network model based on the improved PSO. Through empirical analysis of carbon emissions and its driven factors in Beijing city from 1978 to 2012, IPSO-BP is found to be a good method to make carbon emissions' forecast as it can improve the global optimization ability of traditional IPSO and BP algorithm. The results also can contribute to the local government's policy related decision-making to make control of carbon emissions. © 2016 American Institute of Chemical Engineers Environ Prog, 36: 428–434, 2017

Full Text

Published Version
Open DOI Link

Get access to 115M+ research papers

Discover from 40M+ Open access, 2M+ Pre-prints, 9.5M Topics and 32K+ Journals.

Sign Up Now! It's FREE

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call