Characterization of the non-Gaussian hydraulic conductivity field via deep learning-based inversion of hydraulic-head and self-potential data

•A deep learning-based hydrogeophysical inversion framework is developed.•Using limited head data may lose the fine structure of channelized aquifer.•Integrating hydraulic-head and self-potential data can improve the characterization of non-Gaussian hydraulic conductivity. Accurate characterization...

Ausführliche Beschreibung