Real-Time Carbon Emission Monitoring and Prediction Method of Expressway Based on LSTM

You are here: Homepage > Search

Real-Time Carbon Emission Monitoring and Prediction Method of Expressway Based on LSTM

Zhao, Xinrui / Zou, Fumin / Guo, Feng / Jin, Sirui

Under the background of “double carbon” policy, it is imperative to maintain ecological balance and reduce carbon emissions. Traffic carbon emissions are the main source of carbon emissions in China, of which road traffic accounts for a relatively high proportion. Reducing road traffic carbon emissions is an important way to achieve carbon emission reduction. Improving the unified statistical monitoring system of traffic carbon emissions and quantifying the level of traffic carbon emissions are the basis for achieving traffic carbon emission reduction. To this end, this study proposes a method for measuring carbon emissions of highway vehicles based on fusion data. Firstly, the basic data of highway vehicles are cleaned. Secondly, the calculation model of highway carbon emissions based on RNN-LSTM network is established, and then the relevant calculation process is designed. Finally, taking a portal frame of a highway in Fujian Province as an example, the vehicle carbon emissions from May 6,2021 to May 30,2021 were calculated.

Access

Check access

Check availability in my library

Order at Subito €

Export, share and cite

Document information

Title :

Real-Time Carbon Emission Monitoring and Prediction Method of Expressway Based on LSTM

Additional title:

Lect. Notes Electrical Eng.

Contributors:

Pan, Jeng-Shyang (editor) / Pan, Zhigeng (editor) / Hu, Pei (editor) / Lin, Jerry Chun-Wei (editor) / Zhao, Xinrui (author) / Zou, Fumin (author) / Guo, Feng (author) / Jin, Sirui (author)

Conference:

International Conference on Genetic and Evolutionary Computing ; 2023 ; Kaohsiung, Taiwan October 06, 2023 - October 08, 2023

Published in:

Genetic and Evolutionary Computing ; Chapter : 8 ; 68-78

Lecture Notes in Electrical Engineering ; 1114

Publication date :

2024-01-25

Size :

11 pages

ISBN :

978-981-99-9412-0 , 978-981-99-9411-3

ISSN :