The aim is to examine existing machine learning methods for predicting lake water levels. These techniques have enabled significant advances in the management and preservation of water resources, offering powerful tools for understanding and anticipating water level fluctuations. As part of this research, a database consisting of 168 scientific articles from reliable sources, including Google Scholar, IEEE Xplore, ACM, MDPI, and other open-access libraries, was assembled. After a rigorous analysis based on quality and relevance criteria, 70 articles were selected for this review. These provide an overview of the latest models and methods, while highlighting the advances and challenges associated with the application of artificial intelligence in this field.