Trained emulators from the spheroid90gp software package
Dates
Publication Date
2024-05-28
Citation
Anderson, K.R., 2024, Trained emulators from the spheroid90gp software package. U.S. Geological Survey data release, https://doi.org/10.5066/P9KAX1QP.
Summary
This data release contains materials related to the spheroid90gp software package, including pre-trained Gaussian Process emulators and model input files. The emulators predict cavity compressibility and surface displacements produced by pressure changes in a vertical spheroidal cavity embedded in an elastic halfspace. The methodology is documented in a journal publication ("Computationally efficient emulation of spheroidal elastic deformation sources using machine learning models: a Gaussian-process-based approach" by K. R. Anderson and M. Gu.). The first child item contains model input files and trained emulators developed for the manuscript. Additional child items may be added in the future as new emulators are developed. Additional [...]
Summary
This data release contains materials related to the spheroid90gp software package, including pre-trained Gaussian Process emulators and model input files. The emulators predict cavity compressibility and surface displacements produced by pressure changes in a vertical spheroidal cavity embedded in an elastic halfspace. The methodology is documented in a journal publication ("Computationally efficient emulation of spheroidal elastic deformation sources using machine learning models: a Gaussian-process-based approach" by K. R. Anderson and M. Gu.).
The first child item contains model input files and trained emulators developed for the manuscript. Additional child items may be added in the future as new emulators are developed.
Additional information may be found in the child items below.
Anderson, K. R. and M. Gu (2024), Computationally efficient emulation of spheroidal elastic deformation sources using machine learning models: a Gaussian-process-based approach: Journal of Geophysical Research: Machine Learning and Computation, 1, https://doi.org/10.1029/2024JH000161