Determinants influencing ecological footprints of China; An empirical evidence from factor analysis

Abstract

China has advanced significantly in the last decades, but ecological concerns raise questions about the nation's long-term affluence. The hunt for possible determinants in explaining the quality of the environment (ecological footprint) is still in progress. Therefore, the current study attempts to investigate the influencing factors from various explanatory variables (eco-innovation, economic complexity, renewable energy consumption, economic growth, natural resource rent, foreign direct investment, the energy intensity level of primary energy, economic development, Public-private partnerships investment in energy, electric power consumption, and population growth) through factor analysis augmented with Back Propagation Neural Network (BPNN) approach. The annual data from 1995 to 2021 for China is retrieved for empirical analysis. The data set comprises the factors classified into training, validation, and testing divisions with a ratio of 2:1:1. The outcomes revealed that extracted factors are robust in explaining China's ecological footprint variation. Outcomes of the BPNN algorithm suggest that renewable energy consumption, eco-innovation, economic complexity, natural resource rent, and electric power consumption are the most useful determinants in explaining the ecological footprints of China. The study furnishes the possible policy implications of the research.