Description:

Sea level rise is a critical issue resulting from climate change, primarily caused by the melting of glaciers and thermal water expansion. Predicting future sea levels is essential for governments and individuals to prepare for the impending consequences of sea level rise. However, current semi-empirical models, such as Rahmstorf's 2009 model, are inaccurate as they fail to account for the constantly shifting equilibrium temperature at which sea-level is steady. Grinsted's 2009 model addressed these faults but is still limited by its approach. Our project aims to create an alternative model using the Engle and Granger Error Correction Model, a reliable econometrics model that considers both short-term and long-term factors and the constantly changing equilibrium. We also used machine learning to account for smaller causes such as precipitation. This interdisciplinary approach has the potential to improve the accuracy of sea-level rise predictions, which can inform efforts to combat climate change.