Deep Learning Seismic Waveforms to Predict Sea Ice Properties

Accurate and continuous estimates of sea-ice properties are essential for understanding the dynamics of a warming Arctic. In this context, seismic methods are promising tools for achieving high temporal and spatial resolution estimates of sea-ice thickness and mechanical parameters. However, current approaches rely on computationally expensive waveform inversions of icequakes, which prevents their application to real-time estimation of ice properties in the field.

 

To address this limitation, we explore replacing such inversions with convolutional neural networks (CNNs) trained on physically informed synthetic waveforms to infer sea-ice thickness. The synthetic icequake waveforms are generated by a one-dimensional forward model for flexural waves in floating ice that accounts for ice thickness, mechanical properties, and source–receiver distance. Realistic source spectra are incorporated using a library of field data.

On synthetic waveforms, the networks recover ice thickness and source distance with low error, indicating that the learned relationship between waveform characteristics and physical parameters captures the dominant dispersive physics. However, when applied directly to field icequake waveforms, the accuracy decreases, reflecting the limitations of using synthetic waveforms alone for training due to idealized model assumptions. Based on additional tests, we outline strategies to improve CNN performance and robustness when applied to field data.