Exploring the impact of key performance factors on energy markets: From energy risk management perspectives

Sachin Kumar Mangla, Praveen Ranjan Srivastava, Prajwal Eachempati and Aviral Tiwari

Energy Economics, 2024, vol. 131, issue C

Abstract: Currently, there are limited mechanisms to control harmful greenhouse gas emissions. There is a need to contain these emissions at the source level; understanding the root cause is imperative. This would aid in monitoring and curbing those factors to minimize these harmful emissions and control incidences of energy risk. While there are studies evidencing the role of generic indicators like per capita carbon consumption on greenhouse gas levels, these are also equally influenced by climatic risk factors such as surface temperature. Research suggests that climatic factors significantly impact fluctuating greenhouse gas emissions. However, existing studies have not quantified the precise extent to which these factors drive harmful emissions, which, in turn, also curb energy efficiency and increase the costs of generation of energy alternatives. To address this gap, the outcome variable ‘Total greenhouse gas emissions including land-use change and forestry' is examined using advanced machine learning algorithms such as Random Forest, Multi-layer perceptron models and Deep Neural Networks. Algorithms are chosen in the hierarchical order of accuracy to capture the differential capabilities of detecting the causation factors of harmful emissions. While the above algorithms see the essential features in terms of absolute value, there is a need to examine how each factor contributes to the emissions relative to the others. The Shapley framework of Explainable AI is therefore employed to scientifically assess the influence of different factors on consumption levels. The outcomes of the Shapley analysis are then validated through regression and further supported by the Fuzzy Analytical Hierarchy Process (AHP). The research also proposes adopting association rule mining to analyze the co-occurrence of specific climatic conditions on energy consumption. The findings of this study offer valuable insights for both society and experts in climate and energy, enabling them to develop specific strategies and targeted climatic policies for effective energy risk management. This would present an opportunity for economic transformation, job creation, technological advancement, and improved environmental and public health outcomes. While initial costs and challenges may be associated with a transition, the long-term benefits would help attain sustainable energy economics.

Keywords: Random Forest; Multi-layer perceptron; Deep Neural Network; XAI; Regression; Fuzzy AHP; Association rule mining; Shapley; Climatic risk; Weather; Energy risk management; Energy economics; Energy efficiency; Energy demand forecasting (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0140988324000811
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:eneeco:v:131:y:2024:i:c:s0140988324000811

DOI: 10.1016/j.eneco.2024.107373

Access Statistics for this article

Energy Economics is currently edited by R. S. J. Tol, Beng Ang, Lance Bachmeier, Perry Sadorsky, Ugur Soytas and J. P. Weyant

More articles in Energy Economics from Elsevier
Bibliographic data for series maintained by Catherine Liu ().