Explore the vast range of titles available.

By integrating statistical modeling and data analysis techniques, we systematically assess the carbon emission performance of the ceramic industry and propose targeted emission reduction pathways. Firstly, the entropy weight TOPSIS model is employed to quantitatively evaluate the carbon emission performance of the three major Chinese ceramic production areas: Foshan, Jingdezhen, and Zibo. Through data-driven quantitative analysis, it is disclosed that the carbon emission intensity in Foshan is significantly higher than that in the other two regions (with a relative closeness degree of 0.5185). The key issues identified include high energy consumption in the production process, a high reliance on raw coal, and insufficient investment in environmental protection. Furthermore, through the XGBoost-SHAP combined modeling, the key drivers of carbon emissions are precisely identified from multi-dimensional data. It is found that the elasticity coefficient of raw coal in the carbon emission proportion is as high as 25.84%, while the potential for substitution with natural gas is remarkable. Based on statistical prediction techniques, a carbon emission trend model under the scenario of energy structure optimization is constructed, predicting that after reaching a peak in 2017, Foshan’s carbon emissions will continue to decline, with the proportion of raw coal dropping to 48% and that of natural gas rising to 10%, thereby verifying the feasibility of the green transformation. Additionally, a multi-agent carbon trading simulation model is constructed to explore the emission reduction behaviors of enterprises under different carbon price scenarios. This study not only achieves precise quantitative analysis of carbon emissions through statistical method innovation but also verifies the feasible paths of low-carbon transformation through data modeling.

Agent-based models are a flexible and scalable modeling approach employed to study and describe the evolution of complex systems in different fields, such as social sciences, engineering, and economics. In the latter, they have been largely employed to model financial markets with a bottom-up approach, with the aim of understanding the price formation mechanism and to generate market scenarios. In the last few years, they have found application in the analysis of energy markets, which have experienced profound transformations driven by the introduction of energy policies to ease the penetration of renewable energy sources and the integration of electric vehicles and by the current unstable geopolitical situation. This review provides a comprehensive overview of the application of agent-based models in energy commodity markets by defining their characteristics and highlighting the different possible applications and the open-source tools available. In addition, it explores the possible integration of agent-based models with machine learning techniques, which makes them adaptable and flexible to the current market conditions, enabling the development of dynamic simulations without fixed rules and policies. The main findings reveal that while agent-based models significantly enhance the understanding of energy market mechanisms, enabling better profit optimization and technical constraint coherence for traders, scaling these models to highly complex systems with a large number of agents remains a key limitation.