Physics-informed neural network reconciles Australian displacements and tectonic stresses.

ABSTRACT: Stress orientation information is invaluable to evaluate active tectonic forces within the Earth's crust. The global dataset provided by the World Stress Map offers a rich resource of stress indicators, facilitating the calibration of mechanical models to extract complete stress and displacement fields. However, traditional inversion processes are hampered by the manual tuning of geomechanical properties and boundary conditions to reconcile simulations with observations. In this study, we introduce ML-SEISMIC (machine learning for stress estimation integrating satellite image and computational modelling), a physics-informed deep neural network approach to autonomously align stress orientation data with an elastic model. It nearly completely bypasses the need for explicit boundary condition

SUBMITTER: Poulet T 

PROVIDER: S-EPMC10754839 | biostudies-literature | 2023 Dec

REPOSITORIES: biostudies-literature