Climate change is an intricate and pressing worldwide concern, demanding a synchronized endeavor across local, national, and international domains to diminish its repercussions and shift toward a more sustainable future. It presents substantial obstacles to ecosystems, economies, and human communities, thus ranking as one of the paramount issues of our era. Machine learning serves as a comprehensive concept encompassing the solution of problems that would be financially impractical to address through the creation of algorithms by human programmers. Instead, it empowers machines to uncover their algorithms autonomously, obviating the need for explicit guidance from human-developed algorithms. This paper considers climate change-related datasets like year, month, MEI, CO2, CH4, N2O, CFC-11, CFC-12, TSI, aerosols, and temp. The machine learning approaches which is used to analyze and predict the dataset using linear regression, multilayer perceptron, SMOreg, M5P, random forest, random tree, and REP tree. Numerical illustrations are provided to prove the proposed results with test statistics or accuracy parameters.