AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (4.1 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Original Paper | Open Access

Multivariate natural gas price forecasting model with feature selection, machine learning and chernobyl disaster optimizer

Pei Dua, Xuan-Kai Zhanga, Jun-Tao Dub( ), Jian-Zhou Wangc
School of Business, Jiangnan University, Wuxi, 214122, Jiangsu, China
School of Statistics & Applied Mathematics, Anhui University of Finance and Economics, Bengbu, 233030, Anhui, China
Institute of Systems Engineering, Macau University of Science and Technology, Macau SAR, 999078, China

Peer review under the responsibility of China University of Petroleum (Beijing).

Edited by Jia-Jia Fei

Show Author Information

Abstract

The significance of accurately forecasting natural gas prices is far-reaching and significant, not only for the stable operation of the energy market, but also as a key element in promoting sustainable development and addressing environmental challenges. However, natural gas prices are affected by multiple source factors, presenting complex, unstable nonlinear characteristics hindering the improvement of the prediction accuracy of existing models. To address this issue, this study proposes an innovative multivariate combined forecasting model for natural gas prices. Initially, the study meticulously identifies and introduces 16 variables impacting natural gas prices across five crucial dimensions: the production, marketing, commodities, political and economic indicators of the United States and temperature. Subsequently, this study employs the least absolute shrinkage and selection operator, grey relation analysis, and random forest for dimensionality reduction, effectively screening out the most influential key variables to serve as input features for the subsequent learning model. Building upon this foundation, a suite of machine learning models is constructed to ensure precise natural gas price prediction. To further elevate the predictive performance, an intelligent algorithm for parameter optimization is incorporated, addressing potential limitations of individual models. To thoroughly assess the prediction accuracy of the proposed model, this study conducts three experiments using monthly natural gas trading prices. These experiments incorporate 19 benchmark models for comparative analysis, utilizing five evaluation metrics to quantify forecasting effectiveness. Furthermore, this study conducts in-depth validation of the proposed modelʼs effectiveness through hypothesis testing, discussions on the improvement ratio of forecasting performance, and case studies on other energy prices. The empirical results demonstrate that the multivariate combined forecasting method developed in this study surpasses other comparative models in forecasting accuracy. It offers new perspectives and methodologies for natural gas price forecasting while also providing valuable insights for other energy price forecasting studies.

References

【1】
【1】
 
 
Petroleum Science
Pages 4823-4837

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Close
Close
Cite this article:
Du P, Zhang X-K, Du J-T, et al. Multivariate natural gas price forecasting model with feature selection, machine learning and chernobyl disaster optimizer. Petroleum Science, 2025, 22(11): 4823-4837. https://doi.org/10.1016/j.petsci.2025.09.034

1774

Views

3

Downloads

5

Crossref

3

Web of Science

3

Scopus

0

CSCD

Received: 23 December 2024
Revised: 18 September 2025
Accepted: 19 September 2025
Published: 24 September 2025
© 2025 The Authors.

This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).