Predicting the future climate: Integrating renewable energy and machine learning to address temperature and GHG emissions

Abstract

Over the years, population growth has led to a sharp rise in electricity demand, which in turn has increased the use of fossil fuels, the main source of Greenhouse gas emissions. Renewable energy offers a cleaner alternative, helping reduce these emissions and lessen the impact of climate change. While recent studies primarily focus on the direct correlation between Greenhouse gas emissions and temperature elevation, this study takes a new approach by breaking the analysis into two stages. The first stage investigates the relationship between Greenhouse gas concentrations and the suppression of solar radiation trapped in the atmosphere. Subsequently, the second stage links trapped solar radiation with average temperature patterns. Two mathematical models with 95 % prediction accuracy are developed to estimate the reduction in trapped solar radiation from existing RE projects and predict resulting temperature changes. To improve the prediction accuracy, multiple Machine learning models, namely Decision Tree, Support Vector Machine, and kernel Naive Bayes, were utilized to predict the average temperature based on the two features, Greenhouse gas and the trapped solar radiation. Neural Network Clustering was also employed to capture nonlinear interactions between $C{O}_2$ and solar radiation. This approach overcomes the limitations of traditional methods while aligning with climate physics principles. The paper also addresses the impact of the climate change phenomenon on the evaporation rate in Jordan as a case study, offering insights into its regional environmental effects.