Renewable energy, forest cover, export diversification, and ecological footprint: a machine learning application in moderating eco-innovations on agriculture in the BRICS-T economies

Abstract

The United Nations Climate Change Conference (COP26) recommended that the member nations enhance their technological progression and structural transformation to mitigate the problems of climate change. The BRICS-T countries consisting of Brazil, Russia, India, China, South Africa, and Turkey agreed to implement COP26's policy suggestions. These countries accounted for 40% of global greenhouse gas emissions in 2017, thus posing severe threats to the global environment. The current study explores the role of renewable energy, forest depletion, eco-innovations, and export diversification in impacting the ecological footprint for those BRICS-T countries. We further examine the moderating effect of eco-innovations on agriculture on the BRICS-T nations. The study contributes to the existing literature by providing newer empirical insights on how eco-innovations and export diversification, along with renewable energy, forest cover, and agriculture, affecting the ecological footprint in the BRICS-T nations. It utilizes novel empirical methods like parametric and non-parametric techniques to derive the short-run and long-run empirical results. The empirical findings based on the augmented mean group and the kernel regularized least square methods document that economic growth, agriculture value added, and forest depletion increase the ecological footprint. In contrast, renewable energy and eco-innovations decrease the level of ecological footprint. In the long run, a 1% rise in GDP leads to a rise in the ecological footprint by 0.64% using the augmented mean group (AMG) estimation. The mean marginal effects are - 0.27%, 0.29%, and 0.17% for renewable energy; agriculture and forest cover, respectively, using the kernel-based regularized least square methods. The study suggests that policies designed for controlling the ecological footprints focus on the use of energy efficient technologies, particularly in the agricultural sector.

Keywords: Eco-innovations; Ecological footprint; Non-parametric analysis, Machine learning; Renewable energy.