Prior information regarding subsurface spatial patterns may be used in geophysical inversion to obtain realistic subsurface models. Field experiments require prior information with sufficiently diverse patterns to accurately estimate the spatial distribution of geophysical properties in the sensed subsurface domain. A variational autoencoder (VAE) provides a way to assemble all patterns deemed possible in a single prior distribution. Such patterns may include those defined by different base training images and also their perturbed versions, for example, those resulting from geologically consistent operations such as erosion/dilation, local deformation, and intrafacies variability. Once the VAE is trained, inversion may be done in the latent space which ensures that inverted models have the patterns defined by the assembled prior. Gradient‐based inversion with both a synthetic and a field case of cross‐borehole GPR traveltime data shows that using the VAE assembled prior performs as good as using the VAE trained on the pattern with the best fit, but it has the advantage of lower computation cost and more realistic prior uncertainty. Moreover, the synthetic case shows an adequate estimation of most small‐scale structures. The absolute values of wave velocity are computed by assuming a linear mixing model which involves two additional parameters that effectively shift and scale velocity values and are included in the inversion.
Prior information regarding subsurface patterns may be used in geophysical inversion to obtain realistic subsurface models. Field experiments require prior information with sufficiently diverse patterns to accurately estimate the spatial distribution of geophysical properties in the sensed subsurface domain. A variational autoencoder (VAE) provides a way to assemble all patterns deemed possible in a single prior distribution. Such patterns may include those defined by different base training images and also their perturbed versions, e.g. those resulting from geologically consistent operations such as erosion/dilation, local deformation and intrafacies variability. Once the VAE is trained, inversion may be done in the latent space which ensures that inverted models have the patterns defined by the assembled prior. Inversion with both a synthetic and a field case of cross-borehole GPR traveltime data shows that using the VAE assembled prior performs as good as using the VAE trained on the pattern with the best fit, but it has the advantage of lower computation cost and more realistic prior uncertainty. Moreover, the synthetic case shows an adequate estimation of most small scale structures. Estimation of absolute values of wave velocity is also possible by assuming a linear mixing model and including two additional parameters in the inversion.
Groundwater is the primary water source in arid and semi-arid regions in central Mexico, including the San Juan del Rio basin. While characterizing the contribution of deep groundwater flow into the shallow volcanic aquifer systems is often challenging, it is important in tectonically controlled settings. In this study, the occurrence and the rate of deep groundwater inflow was characterized using six different hydrologic models. By using a numerical groundwater model with particle tracking and comparing simulations with both hydraulic head and groundwater age data, the most likely hydrological scenario for the basin was selected. The findings indicate that a model which incorporates deep inflow, without significant hydraulic conductivity enhancement along faults, is the best representation of the system among the scenarios considered. This highlights the importance of incorporating groundwater age data, in addition to hydraulic head data, for accurately constraining flow regimes in aquifers, particularly those situated in tectonically active regions with regional circulation patterns.