Abstract
Mineral phase transformations significantly alter the bulk density and
elastic properties of mantle rocks and consequently have profound
effects on mantle dynamics and seismic wave propagation. These changes
in the physical properties of mantle rocks result from evolution in the
equilibrium mineralogical composition, which can be predicted by the
minimization of the Gibbs Free Energy with respect to pressure (P),
temperature (T), and chemical composition (X). Thus, numerical models
that simulate mantle convection and/or probe the elastic structure of
the Earth’s mantle must account for varying mineralogical compositions
to be self-consistent. Yet coupling Gibbs Free Energy minimization
(GFEM) approaches with numerical geodynamic models is currently
intractable for high-resolution simulations because execution speeds of
widely-used GFEM programs (100–102 ms) are impractical in many cases.
As an alternative, this study introduces machine learning models
(RocMLMs) that have been trained to predict thermodynamically
self-consistent rock properties at arbitrary PTX conditions between
1–28 GPa, 773–2273 K, and mantle compositions ranging from fertile
(lherzolitic) to refractory (harzburgitic) end-members defined with a
large dataset of published mantle compositions. RocMLMs are 101–103
times faster than GFEM calculations or GFEM-based look-up table
approaches with equivalent accuracy. Depth profiles of RocMLMs
predictions are nearly indistinguishable from reference models PREM and
STW105, demonstrating good agreement between thermodynamic-based
predictions of density, Vp, and Vs and geophysical observations. RocMLMs
are therefore capable, for the first time, of emulating dynamic
evolution of density, Vp, and Vs in high-resolution numerical geodynamic
models.