Tyler G Paladino, Ph.D.

My research here at CVO focuses on both explosive eruption plume dynamics/ash dispersal as well as volcanic deformation detection using machine learning approaches. On the explosive eruption side, I seek to understand the dynamics of explosive eruption plumes better, including the effects of wind as well as connections to deposits using 3-dimensional modeling techniques. I’m also interested in estimating the probability of ash dispersal and deposition on long timescales as well as over short forecasts of ashfall during periods of unrest for volcano-adjacent communities. 

On the volcanic deformation side, I use machine learning approaches and explainability methods to create trustworthy algorithms that automatically detect volcanic deformation. These algorithms can ingest massive amounts of geodetic data including Interferometric Synthetic Aperture Radar (InSAR) and Global Navigation Satellite System (GNSS) data to detect deformation over both rapid and slow timescales. Peering into the “black-box” nature of these algorithms can reveal interesting aspects of the magmatic system that can help constrain or validate other approaches.