Novel disctete grey Bernoulli seasonal model with a time powter term for predicting monthly carbon dioxide emissions in the United States DOI Creative Commons
Jianming Jiang,

Yandong Ban,

Nong Sheng

et al.

Frontiers in Environmental Science, Journal Year: 2025, Volume and Issue: 12

Published: Jan. 3, 2025

This study proposes a more efficient discrete grey prediction model to describe the seasonalvariation trends of carbon dioxide emissions. The setting bernoulli parameter and time powerterm in new ensures that can capture trend nonlinear changesin sequence. At same time, inclusion dummy variables allows for direct simulationof seasonal fluctuations emissions without need additional treatment theseasonality optimal search model’s hyperparameters is achieved using MPA algorithm. constructed applied monthly U.S. datafrom January 2003 December 2022, total 240 months. trained on 216 months 2020, data from 2021 2022 usedfor prediction, which then compared with actual values. results show proposed modelexhibits higher forecasting performance SARIMA other models. Therefore, this methodcan effectively simulate variation emissions, providing valuablereference information relevant departments formulate effective policies.

Language: Английский

Novel disctete grey Bernoulli seasonal model with a time powter term for predicting monthly carbon dioxide emissions in the United States DOI Creative Commons
Jianming Jiang,

Yandong Ban,

Nong Sheng

et al.

Frontiers in Environmental Science, Journal Year: 2025, Volume and Issue: 12

Published: Jan. 3, 2025

This study proposes a more efficient discrete grey prediction model to describe the seasonalvariation trends of carbon dioxide emissions. The setting bernoulli parameter and time powerterm in new ensures that can capture trend nonlinear changesin sequence. At same time, inclusion dummy variables allows for direct simulationof seasonal fluctuations emissions without need additional treatment theseasonality optimal search model’s hyperparameters is achieved using MPA algorithm. constructed applied monthly U.S. datafrom January 2003 December 2022, total 240 months. trained on 216 months 2020, data from 2021 2022 usedfor prediction, which then compared with actual values. results show proposed modelexhibits higher forecasting performance SARIMA other models. Therefore, this methodcan effectively simulate variation emissions, providing valuablereference information relevant departments formulate effective policies.

Language: Английский

Citations

0