Inverse Theory and Applications in Geophysics

Development of physics-guided and data-driven inversion methods for geophysical problems, including magnetotelluric and multi-physics inversion (gravimetry, magnetometry) for subsurface characterization and geothermal exploration.

Deep Learning for Seismic Data Reconstruction

Deep learning and diffusion-based methods for reconstructing and enhancing seismic data acquired with compressive and irregular sampling geometries, reducing acquisition costs and environmental impact.

Geophysical Modeling and Compressive Seismic Acquisition

Design of 3D survey geometries and recovery algorithms for compressive seismic acquisition, combining signal processing theory with deep learning to optimize data acquisition in complex terrestrial basins.

Computational Geosciences

Application of machine learning and computational methods to geological problems including landslide susceptibility, mineral prospectivity mapping, and paleomagnetic data analysis.