Imaging of moho topography with conditional generative adversarial network from observed gravity anomalies

Accurate estimation of Moho topography plays a crucial role in understanding Earth's structure, geodynamic processes, and resource exploration. This study presents a novel approach that utilizes conditional Generative Adversarial Networks (cGAN) to reveal Moho topography based on observed gravity anomalies. Synthetic training datasets of Moho topography were generated using the FFT filtering method due to the scarcity of true datasets. Spherical prism-based forward gravity modeling was employed to evaluate the resulting gravity anomalies. We compared the performance of our developed deep learning algorithm cGAN (conditional Generative Adversarial Networks) with a traditional inversion technique using various synthetic datasets, and a real case study in southern peninsular India, a geologically diverse region comprising ancient continental tectonic blocks. Bott's inversion scheme was employed as a verification method for the Moho surface estimation using the presented deep learning model. Using spherical prism-based forward gravity modeling, observed gravity anomalies were corrected for multiple factors such as topography, bathymetry, sediments, crustal heterogeneities, and mantle heterogeneities. By removing these effects, we isolated the gravity contribution solely related to pure Moho undulation. The mean Moho depth and density contrast between the crust and mantle were derived from seismic constraints for improving estimation accuracy. The findings demonstrate the potential of the cGAN and spherical prism-based gravity modeling approach in accurately estimating the Moho topography, offering insights into Earth's subsurface structures and enhancing our understanding of geodynamic processes and resource exploration efforts.