Bayesian neural network modelling for estimating ecological footprints and blue economy sustainability across G20 nations

Abstract

Abstract The term “blue economy” has become synonymous with generating income from maritime pursuits while protecting and improving marine environments. Oceans provide both solutions and boosts to a sustainable environment and economy, given the growing need for resources to accomplish the global food, water, and energy nexus and the rapid reduction in land-based supplies. However, the ecological footprint (EF) is one of the significant factors that may influence the sustained capacity of oceans to deliver economic and environmental value. Therefore, this study aims to investigate the impact of ecological footprints on the sustainability of the blue economy (BE) while controlling for greenhouse gas emissions (GHG), population growth (POT), and economic growth (GDP). The study applied Bayesian neural network (BNN), OLS, fixed effects, and a two-step generalized method of moments on the panel dataset of G20 countries over the period 2000 to 2021. The study shows that the ecological footprint exerts a negative influence on the blue economy, while greenhouse gas emissions, population growth, and economic growth exhibit a positive impact. This study, by realizing the importance of blue economy development in various nations, suggests that all nations must incorporate ocean strategies within their national climate pledges in order to effectively meet the sustainable development goals (SDGs), especially those outlined in SDG 14 (Life Below Water).