An observational approach to petrophysical modeling using recent developments in AI

Le résumé fourni par la source

We propose an observational methodology for predicting subsurface petrophysical models as an alternative to conventional physics-based approaches. Our approach utilizes post-stack seismic data and its derivatives, in conjunction with recorded well logs, to generate a threedimensional prediction of porosity. The accuracy of the predicted volume is assessed through validation against a reserved blind well.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.