Addressing Disparities in Clean Cooking Fuel Adoption Through a Fuzzy Rule-Based Classification and Gradient Boosting Approach

The transition to clean cooking fuels is critical for sustainable energy development, yet disparities in adoption remain a significant global challenge. This paper proposes a novel fuzzy rule-based classification framework that integrates Gradient Boosting with multiple Takagi-Sugeno-Kang (TSK) classifiers to analyze energy consumption patterns, carbon emission levels, and economic development. By leveraging machine learning algorithms, particularly those based on fuzzy rules, the framework provides a robust and interpretable solution for addressing uncertainty and complexity in clean energy adoption. Validated using both synthetic and real-world datasets, including global sustainable energy data, the framework demonstrates better performance compared to traditional machine learning methods. This research advances clean energy modeling by offering actionable insights, aligning with global sustainability goals, and promoting practical applications in energy policy optimization.