Renewable Energy, Environmental Sustainability and Economic Growth: A Machine Learning Analysis of MINT Countries

The transition toward sustainable energy systems and environmentally responsible development has become a central policy objective for emerging economies. Within the framework of green growth, this study investigates the nonlinear relationships among renewable energy consumption, carbon emissions, health expenditures, tourism, and economic growth in MINT countries (Mexico, Indonesia, Nigeria, and Türkiye) over the period 2000–2023. Annual data obtained from the World Bank were analyzed using the Kernel Regularized Least Squares (KRLS) approach, a machine learning technique capable of capturing heterogeneous and nonlinear relationships without imposing restrictive functional form assumptions. The findings reveal that renewable energy consumption is statistically significantly associated with lower economic growth on average, suggesting the existence of short-term transition costs associated with the shift toward cleaner energy systems. However, the magnitude of this negative association decreases across the distribution of the estimated marginal effects, indicating substantial heterogeneity across observations. Tourism is positively associated with economic growth, whereas the estimated marginal association between health expenditures and economic growth varies across observations. Although carbon emissions do not exhibit a statistically significant average marginal association with economic growth, their estimated marginal association also varies across observations, highlighting the heterogeneous nature of the growth–environment nexus. The results provide important implications for energy and environmental policies in developing economies. They emphasize the need to support renewable energy investments through technological innovation, energy efficiency improvements, and long-term financing mechanisms to reduce transition costs and promote sustainable growth.