Physics-Informed Data-Driven Seismic Inversion: Recent Progress and
Future Opportunities
Abstract
The goal of seismic inversion is to obtain subsurface properties from
surface measurements. Seismic images have proven valuable, even crucial,
for a variety of applications, including subsurface energy exploration,
earthquake early warning, carbon capture and sequestration, estimating
pathways of sub-surface contaminant transport, etc. These subsurface
properties~(such as wave speed, density, impedance, and
reflectivity) influence the transmission of seismic waves through the
subsurface media, and well-understood physics models (so-called
“forward models”) can be used to predict what surface measurements
would be made, for any given subsurface configuration. Seismic inversion
is the inverse problem: given actual surface measurements, infer what
subsurface configuration would give rise to those measurements. Like
most inverse problems, seismic imaging is ill-posed. There is more below
the surface than on the surface, and many different subsurface
configurations can give rise to the same surface measurements. Because
the forward model is itself computationally expensive – the inverse
inference is even more so. But recent advances in algorithms and
computing provide an opportunity for remarkable progress in seismic
inversion, and efficient solutions to previously infeasible problems
have been obtained using data-driven approaches (such as the deep
learning methods that were developed primarily for problems in computer
vision). The excellent performance of learning-based methods arises from
its ability to exploit large amounts of high-quality training data,
without the need for hand-designed features. Unlike computer vision,
however, seismic inversion is not a data-rich domain. The technical
challenges and high cost of acquiring field data prevent the
accumulation of large quantities of data (and the commercial value of
that data, once acquired) prevents much of the existing data from being
widely available. To alleviate the data scarcity issue and improve model
generalization, there has been growing interest in combining physics
knowledge with machine learning for solving seismic inversion problems.
This review will survey methods for incorporating physics knowledge with
machine learning (primarily deep neural networks) to solve computational
seismic inversion problems. We will provide a structured framework of
the existing research in the seismic inversion community, and will
identify technical challenges, insights, and trends.