Machine Learning Lessons for Geophysics

Leonardo Uieda



I gave this presentation at the TGIF Seminar series of the Department of Earth Sciences, University of Hawaii at Manoa.

The topic merges my interest in machine learning, how we can borrow some techniques for geophysical inversion, and the similarities with gridding problems, like my work on GPS gridding.


Machine learning is the new trend sweeping across the Earth Sciences. From the oil and gas industry to oceanography, these algorithms are being trained to solve previously unsolvable (or extremely tedious) problems. But what exactly is "machine learning" and what can be done with it? In this talk, I will present a brief high-level overview of some of the core concepts and interesting applications of machine learning methods to geoscience data. I will also explore some of the best practices and techniques that can be applied to geophysical inversion and interpolation methods, including a new method for gridding 3-component GPS data.

Article Level Metrics

Comments? Let me know on Twitter (tweet @leouieda).
Found a typo/mistake? Send a fix through Github. All you need is an account and 5 minutes!

Related pages