Geophysics meets environmental and data science: Probing our planet's dynamics from earthquakes to elephants and earthworms

The complexity of interwoven Earth systems, especially across vast scales in space and time, render closed solutions and system predictions extremely difficult for a number of reasons: a) incomplete mathematical frameworks to describe highly non-linear, multiscale, chaotic behaviour, b) exuberant computational cost even if any frameworks existed, and c) insufficient data resolution and coverage to describe system parameters.

I will present some of our recent work on b) in the context of  ML-aided wave-propagation simulation related to seismic risk and Earth's interior, and on c) with a focus on using ML for seismic monitoring of savanna wildlife at landscape scale, and for soil health monitoring at earthworm scale.