Geoscientific models are facing increasing challenges to exploit growing datasets coming
from remote sensing. Universal Differential Equations (UDEs), aided by differentiable …

The differentiable programming paradigm is a cornerstone of modern scientific computing. It
refers to numerical methods for computing the gradient of a numerical model's output. Many …

This dissertation studies the application of machine learning in the fields of Glaciology and
Paleomagnetism. In the past few years, there have been significant advances in introducing …

We propose a systematic approach that leverages automatic differentiation (AD) to scrutinize
every element within variables (eg, arrays) necessary for checkpointing. This allows us to …