A Medium‐Sized Paleo‐Tsunami Reconstruction by a Deep Neural Network Processing Sedimentary Deposits.

Reconstructing the magnitude and recurrence time of tsunamis, one of the most destructive and unpredictable natural hazards impacting coastal communities, is essential. While major tsunamis are the most studied due to their disastrous impact, small/medium tsunamis (SMTs) are much more frequent and can still significantly impact the coast. Therefore, SMTs potentially provide an extensive archive of information preserved in the geological record. Analyzing the deposits of small/medium paleo‐tsunamis (SMPTs) opens a window into when their direct observation was unavailable. However, deposits of SMPTs are often degraded, traditional sediment deposition inversion models might fail. Recent research has shown that Deep Neural Networks (DNN) can effectively reconstruct the flow conditions of major tsunamis from their deposits. We evaluate the effectiveness of this approach in reconstructing the characteristics of a recent medium size tsunami (2006 Java) and of a medium paleo‐tsunami (1929 Grand Banks). We successfully reconstruct the flow characteristics of the 2006 Java event and show that an inversion of comparable quality is possible for the 1929 Grand Banks tsunami, despite greater uncertainties due to the deposit degradation. Our research shows that Machine Learning has the potential to unseal the meaning of data of thousands SMPTs. Plain Language Summary: While large tsunamis are more destructive than small/medium ones, the latter are more frequent and represent a greater sample for scientists investigating tsunamis. While machine learning was previously applied to invert the well constrained deposits of giant tsunamis, we test here for the first time that approach to characterize older tsunamis for which deposits are degraded and direct observation limited or non‐existing. We successfully extract the properties of the 1929 Grand Banks tsunami (Newfoundland) and compare the quality of the results with the recent and well known 2006 Java tsunami. Key Points: For the first time, Neural Networks are applied to extract the characteristics of medium sized tsunamisThe method is sufficiently robust to extract paleo tsunami parameters from highly degraded deposit dataNeural Networks can provide as good or better accurate and reliable inversion results compared to traditional approaches [ABSTRACT FROM AUTHOR]