Measuring Global Warming Effect by the Prediction of Climate Change on the Different Countries Using Machine Learning Approaches

In recent years, the escalating phenomenon of global warming, also known as global warning, has brought widespread fear from the severe implications of various facets of our environment. The most crucial effect is the transformation in the earth climate, which correspondingly leads to all the catastrophic events that became inevitable nowadays such as floods and earthquakes. This paper investigates the critical and directly proportional relationship between global warming and climate change. Recognizing that the quantification of climate change is essential for effective resource management, our study introduces a novel approach for determining the direct effect of global warming, proving the feasibility of climate prediction from such measures. Different approaches such as Regression, Neural Networks, Support Vector Machines, Decision trees and Ensemble trees were employed to predict climate change, providing a new perspective on this controversial issue. The proposed methodology achieved the highest accuracy. Another contribution in this paper is its novelty predicting the relation between climate change and global warming. Step wise linear regression was used which gave R squared measure of 100%