Unveiling the effects of artificial intelligence and green technology convergence on carbon emissions: An explainable machine learning-based approach.

Journal: Journal of environmental management
PMID:

Abstract

Green technology and artificial intelligence (AI) are playing a positive role in reducing carbon emissions. Technology convergence, as a typical form of technological innovation, can expedite the realization of low-carbon goals through the outcomes of AI and green technology convergence (e.g., the smart home system and smart transportation system). To investigate the mechanisms within AI and green technologies that affect carbon emissions, this study extracts convergence features from convergence attributes and convergence networks, based on panel data from Chinese prefecture-level cities spanning the period from 1997 to 2019. By combining the eXtreme Gradient Boosting (XGBoost) algorithm and the Shapley Additive Explanations (SHAP) value method, the study explains the individual effects and interaction effects of each feature on carbon emissions. The research findings reveal that technology convergence generality and innovation team scale have a significant impact on carbon emissions, with the latter exhibiting a U-shaped effect. Cities with high convergence network efficiency are found to influence suppressing carbon emissions positively. This study and its findings provide insights for policymakers to develop AI and green convergence technologies to reduce carbon emissions.

Authors

  • Tianlong Shan
    School of Management Science and Real Estate, Chongqing University, No.174, Shazheng Street, Shapingba District, Chongqing, 400044, PR China.
  • Shuai Feng
    State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210023, China; Department of Computer Science and Technology, Nanjing University, Nanjing, 210023, China. Electronic address: shuaifeng@smail.nju.edu.cn.
  • Kaijian Li
    School of Management Science and Real Estate, Chongqing University, No.174, Shazheng Street, Shapingba District, Chongqing, 400044, PR China. Electronic address: likaijian@cqu.edu.cn.
  • Ruidong Chang
    School of Architecture and Civil Engineering, The University of Adelaide, Adelaide, 5005, Australia. Electronic address: ruidong.chang@adelaide.edu.au.
  • Ruopeng Huang
    School of Mechanics and Civil Engineering, China University of Mining and Technology, No1, Daxue Road, Xuzhou, Jiangsu, 221116, China. Electronic address: ruopenghuang@cumt.edu.cn.