Prediction of Human Development from Environmental Indicators

The Sustainable Development Goals (SDG) list the objectives and targets that should be addressed to solve the global issues regarding sustainable development. They encompass the social, economic and environmental dimensions and search for solutions that are able not only to monitor but also to control the operational indicators attributed to each objective. It is expected that many of these indicators are associated to each other and the accurate understanding of these correlations allows to build predictive statistical models that can improve the monitoring and controlling of variables. It would increase the rate of success in achieving the SDG. This study tested a linear multivariate model able to predict the human development index based on environmental variables which are related to SDG 3 (health), 4 (education), 8 (sustainable economic growth and decent work) and 15 (protect, restore and promote sustainable use of terrestrial ecosystems). We fitted the models using the Linear Discriminant Analysis and Best Subset Selection applied to a Linear Multivariate Regression. The model predictive ability was assessed by R² and cross-validation (CV). The results showed that exposure to unsafe sanitation, access to drinking water, tree cover loss, unsafe water quality, wastewater treatment level, and household air pollution are excellent predictors of human development index of a population, with R² = 0.94 and 10-fold CV Mean Squared Error equal to 0.0014. This tool can help stakeholders to monitor and control indicators attributed to good health and well-being, quality education, clean water and sanitation, decent work and economic growth, sustainable cities and communities and life on land sustainable development goals.