A robust stacking model for predicting oil and natural gas consumption in China

ABSTRACT

Accurate prediction of oil and natural gas consumption (ONGC) is crucial for energy security and greenhouse gas emission control. This study uses machine learning to improve forecast accuracy by transforming time series predictions into supervised learning models. A novel stacking learning method, with added cross-validation, enhances model diversity and robustness. The key findings are: (1) The stacking model outperforms base models in predicting China’s ONGC. It achieves R2 scores of 94.44% for oil and 98.33% for natural gas, with corresponding RMSE scores of 0.5325 and 0.2919. (2) When comparing the scores of the models in the validation set using cross-validation, it can be observed that the stacking model exhibits the most consistent performance. (3) Through the diversification of models, the stacking approach enhances robustness and achieves better generalization on new datasets. The study provides fresh insights into model stacking for energy consumption prediction.

KEYWORDS:

• Machine learning
• stacking
• oil consumption
• natural gas consumption
• prediction

Abbreviations

ONGC	=	oil and natural gas consumption
ARDL	=	autoregressive distributed lag
SD	=	system dynamics
ML	=	machine learning
LR	=	linear regression
LASSO	=	least absolute shrinkage and selection operator
SVR	=	support vector regression
LSTM	=	long short-term memory
GDP	=	gross domestic product
CI	=	carbon intensity
MTS	=	multivariate time series
OC	=	oil consumption
NGC	=	natural gas consumption
CO2	=	carbon dioxide
K-CV	=	k-fold cross validation
R2	=	R-squared
RMSE	=	root mean squared error
MAE	=	mean absolute error
DT	=	decision tree
RF	=	random forest
GBDT	=	gradient boosting decision trees
MS	=	mean scores
OECD	=	organization for economic co-operation and development
CASS	=	Chinese Academy of Social Sciences
DRCI	=	decline rate of carbon intensity
GGDP	=	growth rate of GDP
MT	=	million tons
BCM	=	billion cubic meters

Availability of data and materials

The datasets used and analyzed during the current study can be provided on reasonable request.

Consent to publish

The manuscript is approved by all authors for publication.

Competing interests

The authors declare that they have no conflict of interest exits in the submission of this manuscript.

Ethical approval

The authors declare that the work described was original research that has not been published previously, and not under consideration for publication elsewhere, in whole or in part.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [71603127].