Abstract

Geophysical inversion allows predicting the spatial distribution of subsurface rock properties from geophysical data. This is a challenging inverse, nonlinear with non-unique solution problem. We introduce deep generative learning as a flexible way to perform geophysical inversion accounting for multiple data assimilation, uncertainties and a priori geological knowledge. Several methods are introduced with synthetic and real case applications.

Speaker Bio

Leonardo Azevedo is an invited speaker at AIEPS 2026 and will present online.

Materials and Images

  • Slides: To be added.
  • Related links: To be added.
  • Images: To be added.
Back to top