The main objective of this work is to determine whether is it possible to use the Phase Variation Methodology in an early warning context. For this, it is sought to determine the value of alpha that best reproduces the inundation observed for the Maule event (2010), and that is capable of reproducing the uncertainty that a tsunami prediction process implies. A range that goes from alpha=pi/6 and alpha=pi/5 is proposed, since these values provide an acceptable fit between the models and the actual inundation, in addition to providing the expected epistemic uncertainty.Recorded Presentation from the vICCE (YouTube Link): https://youtu.be/JKDPLRCJq2M