CNN-GRU-Attention Neural Networks for Carbon Emission Prediction of Transportation in Jiangsu Province DOI Open Access
Xiaohui Wu, Lei Chen,

Jiani Zhao

и другие.

Sustainability, Год журнала: 2024, Номер 16(19), С. 8553 - 8553

Опубликована: Окт. 1, 2024

With the increasing energy use and carbon emissions in transportation industry, its impact on greenhouse effect is gradually being recognized. Therefore, this study aims to explore achievement of emission peak neutrality through prediction. The research employs a deep learning model, CNN-GRU-Attention predict industry Jiangsu, China. We select influencing factors an extended STIRPAT model coupled with Lasso regression, construct traffic prediction according data indicators from 1995 2021. predicts Jiangsu Province between 2022 2035 under six distinct scenarios proposes corresponding reduction strategies. results show that has higher accuracy compared other models, mean absolute error (MAE) 0.061582, root square (RMSE) 0.085025, R2 0.91609 test set. Scenario-based predictions reveal can be achieved clean development comprehensive low-carbon scenarios, technological innovation primary driver reductions. This provides novel approach for forecasting explores implementation path method.

Язык: Английский

CNN-GRU-Attention Neural Networks for Carbon Emission Prediction of Transportation in Jiangsu Province DOI Open Access
Xiaohui Wu, Lei Chen,

Jiani Zhao

и другие.

Sustainability, Год журнала: 2024, Номер 16(19), С. 8553 - 8553

Опубликована: Окт. 1, 2024

With the increasing energy use and carbon emissions in transportation industry, its impact on greenhouse effect is gradually being recognized. Therefore, this study aims to explore achievement of emission peak neutrality through prediction. The research employs a deep learning model, CNN-GRU-Attention predict industry Jiangsu, China. We select influencing factors an extended STIRPAT model coupled with Lasso regression, construct traffic prediction according data indicators from 1995 2021. predicts Jiangsu Province between 2022 2035 under six distinct scenarios proposes corresponding reduction strategies. results show that has higher accuracy compared other models, mean absolute error (MAE) 0.061582, root square (RMSE) 0.085025, R2 0.91609 test set. Scenario-based predictions reveal can be achieved clean development comprehensive low-carbon scenarios, technological innovation primary driver reductions. This provides novel approach for forecasting explores implementation path method.

Язык: Английский

Процитировано

4