Artificial intelligence carbon neutrality strategy in sports event management based on STIRPAT-GRU and transfer learning

Abstract

IntroductionWith the growing concern over carbon emissions and their impact on climate change, achieving carbon neutrality has become a critical objective in various sectors, including sports event management. Artificial intelligence (AI) offers promising solutions for addressing environmental challenges and enhancing sustainability. This paper presents a novel approach to developing AI-powered carbon neutrality strategies for sports event management.MethodsIn this research, we combine the STIRPAT model for analyzing the influence of population, wealth, and technology on carbon emissions in sports events with a GRU neural network for predicting future emissions trends and enhance the model's accuracy using transfer learning, creating a comprehensive approach for carbon emissions analysis in sports event management. ResultsOur experimental results demonstrate the efficacy of the proposed approach. The combination of the STIRPAT model, GRU neural network, and transfer learning outperforms alternative methods. This success highlights the model's ability to predict carbon emissions in sports events accurately and to develop effective carbon neutrality strategies. DiscussionThe significance of this research lies in its potential to empower sports event managers with a data-driven approach to carbon emissions management. By understanding the key drivers and leveraging AI for prediction and strategy development, the sports industry can transition towards greater sustainability and environmental friendliness. This paper contributes to the broader effort of mitigating carbon emissions and addressing climate change concerns across various domains, ultimately leading to a more sustainable future.