SCEC Award Number 17090 View PDF
Proposal Category Individual Proposal (Integration and Theory)
Proposal Title Enabling visoelastic calculations on global scales through neural network acceleration
Name Organization
Brendan Meade Harvard University
Other Participants One graduate student
SCEC Priorities 1c, 1d SCEC Groups SDOT
Report Due Date 06/15/2018 Date Report Submitted 07/14/2019
Project Abstract
One of the most significant challenges involved in efforts to understand the effects of repeated earthquake cycle activity is the computational costs of large-scale viscoelastic earthquake cycle models. Computationally intensive viscoelastic codes must be evaluated at thousands of times and locations, and as a result, studies tend to adopt a few fixed rheological structures and model geometries and examine the predicted time-dependent deformation over short (<10 years) time periods at a given depth after a large earthquake. Training a deep neural network to learn a computationally efficient representation of viscoelastic solutions, at any time, location, and for a large range of rheological structures, allows these calculations to be done quickly and reliably, with high spatial and temporal resolutions. We demonstrate that this machine learning approach accelerates viscoelastic calculations by more than 50,000%. This magnitude of acceleration will enable the modeling of geometrically complex faults over thousands of earthquake cycles across wider ranges of model parameters and at larger spatial and temporal scales than have been previously possible.
Intellectual Merit It represents a bit of progress on viscoelasticity
Broader Impacts Not really
Exemplary Figure Figure 1