A Study on Variable Selections and Prediction for Climate Change with Global Weather Repository Using Data Mining with Machine Learning Approaches

Abstract

Climate change encompasses enduring alterations in Earth's weather patterns and temperatures, primarily instigated by human activities, notably the release of greenhouse gases like carbon dioxide, methane, nitrous oxide, and other related parameters. These gases trap heat within the Earth's atmosphere, gradually increasing global temperatures, commonly called global warming. Machine learning algorithms encompass the mathematical models and methodologies employed for the analysis and manipulation of data, with categorizations including supervised learning, unsupervised learning, and reinforcement learning, among others. This paper considers a global weather repository-related dataset for applying machine learning approaches to find suitable variables for future predictions using Linear Regression, Multilayer Perceptron, SMOreg, random forest, random tree, and REP tree. Numerical illustrations are provided to prove the proposed results with test statistics or accuracy parameters.