**Deep learning seismic waveforms in sea ice to predict the ice parameters **
Understanding the dynamics of sea ice in the changing climate is crucial and represents a major challenge in the perspective of upcoming seasonally ice-free Arctic. In particular, accurate monitoring of the sea ice thickness and its rheology is crucial for understanding the fragmentation of the ice cover by waves, in view of forecasting the future state of polar to mid-latitude regions for both climate and short-term timescales.
Recently, it has been shown that essential sea ice parameters can be extracted from the seismic noise recorded with autonomous geophones on sea ice (Moreau, Boué et al., 2020; Moreau, Weiss et al., 2020, Serripierri et al., 2022), thus significantly reducing the logistics associated with seismic acquisitions in this hostile environment. However, the processing of thousands of icequakes requires to perform waveform inversions that are computationally heavy.
The goal of the PhD is to train a deep convolutional neural network that will replace the inversion of ice properties. To this end, the successful candidate will use data from past studies (Moreau et al., 2023), and will also participate to field experiments on sea ice to collect new data.
Applicants should have background in seismic wave propagation, signal processing and /or artificial intelligence in Earth Sciences.
Contact :
Ludovic Moreau, ludovic.moreau@univ-grenoble-alpes.fr
Marielle Malfante, marielle.malfante@cea.fr