Extremely Weak Supervision Inversion of Multi-physical Properties
This addresses the challenge of inferring geophysical properties like velocity, conductivity, and CO2 saturation from seismic and EM data for geophysics applications, representing an incremental improvement in reducing label requirements.
The paper tackles the problem of multi-physical inversion in geophysics without explicit governing equations, which traditionally requires expensive full labels, by developing a data-driven technique with extremely weak supervision that reduces label data by 50 times from 100 to only 2 locations.
Multi-physical inversion plays a critical role in geophysics. It has been widely used to infer various physical properties~(such as velocity and conductivity). Among those inversion problems, some are explicitly governed by partial differential equations~(PDEs), while others are not. Without explicit governing equations, conventional multi-physical inversion techniques will not be feasible and data-driven inversion requires expensive full labels. To overcome this issue, we develop a new data-driven multi-physics inversion technique with extremely weak supervision. Our key finding is that the pseudo labels can be constructed by learning the local relationship among geophysical properties at very sparse well-logging locations. We explore a multi-physics inversion problem from two distinct measurements~(seismic and EM data) to three geophysical properties~(velocity, conductivity, and CO$_2$ saturation). Our results show that we are able to invert for properties without explicit governing equations. Moreover, the label data on three geophysical properties can be significantly reduced by 50 times~(from 100 down to only 2 locations).