Displacements in concrete dams present a critical challenge affecting structural integrity. They are influenced by various factors, including environmental, seismic, and operational factors, among others. Many researchers are exploring this significant deformation and working to resolve the problem using statistical methods, particularly Hydrostatic Seasonal Time (HST) and Hydrostatic-Temperature-Time (HTT). Over the years, authors have developed advanced approaches such as artificial intelligence models that demonstrate improved performance and reduced errors. In this paper, a comparison of two methods for predicting displacements in concrete dams is presented, utilizing a database collected from sensors installed in a Moroccan concrete dam structure. Both methods yield promising results; the HTT method, which incorporates hydrostatic, temperature, and aging components, shows a correlation coefficient of 0.80. In contrast, the advanced artificial intelligence model, employing neural networks, achieves a higher correlation coefficient of 0.91. Both models are continuously evolving through the combination of methods or the application of single approaches to address limitations caused by data in the first case.