Application of Deep Learning Neural Network to the Inverse Analysis of Experimental Scale Turbidity Currents

Despite its importance in environmental and resource geology, the flow conditions and mechanism of turbidity current remains unclear. Direct observation of turbidity current remains limited due to its destructive nature and its unpredictable occurrences. In order to better understand the structure of turbidity current, inverse analysis of turbidity current had been used to reconstruct the initial flow conditions from its turbidite deposits. However, past optimization methods had been computationally over expensive, making it impractical to be applied to actual turbidite deposits in nature. To resolve the issue of computational cost from the previous methods, a new method for the inverse analysis of turbidity current using deep learning neural network (DNN) was proposed, and this research verified the method using artificial data and actual flume experiment data. Our results demonstrate that inverse analysis using DNN can reconstruct the hydraulic conditions and deposit profile of flume experiment scale turbidite with high accuracy. Future application to actual data of natural scale turbidite is anticipated.