Coping with the tale of natural resources and environmental inequality: an application of the machine learning tools

With the rising momentum according to the environmentalist voices seeking climate justice for more equity and the importance of encouraging environmental justice mechanisms and tools, in this perspective, the objective of this study is to analyze in depth the substantial role of natural resources abundance in the environmental inequality issue. For this purpose, this study adopted the eXtreme Gradient Boosting (XGBoost), LightGBM, Natural Gradient Boosting (NGBoost), Hybrid hybrid upper confidence bound-long short-term memory-Genetic Algorithm (UCB-LSTM-GA), and the Shapley Additive Explanation (SAE) machine learning algorithms in the context of 21 emerging economies spanning the years 2001 to 2019. The empirical results reveal that natural resource abundance, foreign trade, and foreign direct investment inflows contribute all to higher levels of environmental inequality. However, higher levels of per capita income, gross fixed capital formation, and institutional quality contribute to lower levels of environmental inequality. Addressing climate justice holistically through an integrated supranational vision is significant since every step taken toward eradicating environmental racism matters.