![]() ![]() Recent progress towards these goals has been achieved by applying a variety of machine learning (ML) approaches 2, 3, 4 in the laboratory using shear experimental data to describe physical properties 5, 6, 7, 8, 9, 10, 11 and in the Earth using geophysical data to characterize episodic slow-slip that occurs in subduction zones 8, 12, as well as transform faults 13. In Earth, predicting instantaneous and future characteristics of fault slip has long been a fundamental goal of geoscientists from an earthquake hazards perspective, but also to improve the basic understanding of fault mechanics 1. The transfer learning results elucidate the potential of using models trained on numerical simulations and fine-tuned with small geophysical data sets for potential applications to faults in Earth. Notably, the predictions improve by further training the model latent space using only a portion of data from a single laboratory earthquake-cycle. The model learns a mapping between acoustic emission and fault friction histories from numerical simulations, and generalizes to produce accurate predictions of laboratory fault friction. Here we describe a transfer learning approach using numerical simulations to train a convolutional encoder-decoder that predicts fault-slip behavior in laboratory experiments. Sparse data presents a serious challenge to training machine learning models for predicting fault slip in Earth. In Earth however, earthquake interevent times range from 10’s-100’s of years and geophysical data typically exist for only a portion of an earthquake cycle. Data-driven machine-learning for predicting instantaneous and future fault-slip in laboratory experiments has recently progressed markedly, primarily due to large training data sets. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |