Every published paper that uses multispectral optical remote sensing for the identification of Glacial Lake Outburst Flood events (GLOFs) from Ice Marginal Lakes (IMLs) relies on only two methods: the Normalized Difference Water Index (NDWI) or visual identification. While up until this point, these two methods have been the industry standard for GLOF identification using remote sensing techniques, both methods have their limitations, especially when covering a large geographic area. While NDWI thresholds can be accurately tuned to an individual lake with a high level of confidence, this method does not perform as well over large study areas as the lake's composition and surroundings can vary and lead to poor results. Meanwhile, the visual inspection method is inherently subjective and very time-consuming. Despite these challenges, the academic community continues to rely on these techniques due to the lack of improved and more comprehensive automated alternatives. To address the limitations of current GLOF tracking methods, I propose that the first chapter of my doctoral research focus on identifying approaches that leverage machine learning techniques to improve the accuracy and reliability of monitoring GLOFs. To accomplish this, I will create 10 new methods that track the surface area of IMLs to identify GLOF events and compare them to the NDWI and visual inspection methodologies. Through comparative analysis, I aim to provide an improved method that is not only more accurate for the tracking of GLOF events but one that can then be rapidly applied to any region in the world to increase our collective knowledge of how these events are changing on a global scale.