Thursday, April 2, 2020     [ login ]

SEMINARIO GRUPO DE HIDROLOGIA SUBTERRÁNEA, Jueves 17 de Octubre a las 12:15 h (Barcelona)

Published: 16/10/2019

Deep Learning Inversion of Borehole Resistivity Measurements. Part I: Choice of Loss Function
a cargo de
David Pardo
UPV/EHU, BCAM, and Ikerbasque Research Professor

Jueves 17 de Octubre a las 12:15 h
Departamento de Ingeniería Civil y Ambiental, Modulo D2-Aula CIHS, Planta Baja

In geosteering operations, it is necessary to invert (interpret) borehole resistivity measurements in real-time. Recently, Deep Neural Networks (DNNs) have arisen as an alternative to perform such a complex task due to their unique ability to approximate different unknown functions.
In this presentation, we describe the application of interest and the need for real-time inversion. Then, we review basic concepts of DNNs when applied to inverse problems. Thereafter, we focus on the selection of proper loss functions for solving geosteering inverse problems. Some numerical results illustrate the performance and limitations of various loss functions.
Most derivations and ideas contained in the presentation are directly applicable to other inverse problems across different areas of engineering.
--  ----------------------------------------------------
Universidad Politécnica de Cataluña
Grupo de Hidrologia Subterranea (UPC-CSIC)
C/. Jordi Girona 31, Edifici D2,08034 Barcelona