Time-dependent deformation of Uturuncu volcano, Bolivia, constrained by GPS and InSAR measurements and implications for source models

New continuous GPS observations near the summit of Uturuncu volcano, Bolivia, indicate an average uplift rate of 2.4 +/- 1.9 mm/yr between April 2010 and November 2015, while previous interferometric synthetic aperture radar (InSAR) observations between May 1992 and January 2011 predict an average vertical uplift rate of 7 +/- 2 mm/yr. However, the GPS time series is better fit with a time-dependent function, such that the uplift rate in 2010 is less than 2 mm/yr and in 2015 may be as high as 9 mm/yr. Motivated by indications of a non-constant rate in the continuous GPS time series, we examine to what extent past InSAR measurements may have been temporally aliased. We present evidence that decreased uplift since 2004 is permitted by available InSAR and is consistent with a lower average GPS rate since 2010. We discuss how these variable rates may affect previously proposed magmatic models at Uturuncu including diapir ascent and reservoir pressurization. In particular, we explore a "dipole" reservoir model consisting of a magma source in the lower crust and sink in the middle crust for which variation in magma supply could explain sub-decadal fluctuations in deformation rate. Inversion of multiple InSAR data sets using homogeneous models constrains the deeper reservoir to 55-80 km depth (lower crust and upper mantle) and the shallower reservoir to 20-35 km. Consistent with previous work, the inferred ratio of volume change between the source: sink (i.e., deep: shallow) reservoirs is up to 10:1. We also incorporate new seismic tomography results in a 3D finite-element model to explore the combined effects of multiple sources and material heterogeneity on surface deformation. An important conclusion from our modeling efforts is that the commonly used diagnostic ratio of maximum radial to vertical surface displacements for shape of the deformation source is affected by both the presence of multiple reservoirs and subsurface heterogeneity. Ultimately, the dipole and diapir models have unresolved shortcomings given the entire suite of available geophysical data, but both provide valuable insight into the conditions for magmatic ascent in the Central Andes.