We propose a coupled physics-driven and data-driven algorithm to improve standard deep learning workflow. In order to evaluate the proposed method, a 2.5D geological model including dip, fault and anisotropic formation is considered.  Comparing the inversion imaging performance of the proposed physics-driven method with the traditional classical residual network (Resnet), it shows a significant improvement in resistivity accuracy.

Dataset Files

You must be an IEEE Dataport Subscriber to access these files. Subscribe now or login.

Documentation: 
AttachmentSize
File Documentation.pdf105.7 KB
[1] Ning Li, "Physics-driven Deep Learning Pixel-Based Inversion of Logging-While-Drilling in Anisotropic Formation ", IEEE Dataport, 2023. [Online]. Available: http://dx.doi.org/10.21227/cwgf-g832. Accessed: Jul. 22, 2024.
@data{cwgf-g832-23,
doi = {10.21227/cwgf-g832},
url = {http://dx.doi.org/10.21227/cwgf-g832},
author = {Ning Li },
publisher = {IEEE Dataport},
title = {Physics-driven Deep Learning Pixel-Based Inversion of Logging-While-Drilling in Anisotropic Formation },
year = {2023} }
TY - DATA
T1 - Physics-driven Deep Learning Pixel-Based Inversion of Logging-While-Drilling in Anisotropic Formation
AU - Ning Li
PY - 2023
PB - IEEE Dataport
UR - 10.21227/cwgf-g832
ER -
Ning Li. (2023). Physics-driven Deep Learning Pixel-Based Inversion of Logging-While-Drilling in Anisotropic Formation . IEEE Dataport. http://dx.doi.org/10.21227/cwgf-g832
Ning Li, 2023. Physics-driven Deep Learning Pixel-Based Inversion of Logging-While-Drilling in Anisotropic Formation . Available at: http://dx.doi.org/10.21227/cwgf-g832.
Ning Li. (2023). "Physics-driven Deep Learning Pixel-Based Inversion of Logging-While-Drilling in Anisotropic Formation ." Web.
1. Ning Li. Physics-driven Deep Learning Pixel-Based Inversion of Logging-While-Drilling in Anisotropic Formation [Internet]. IEEE Dataport; 2023. Available from : http://dx.doi.org/10.21227/cwgf-g832
Ning Li. "Physics-driven Deep Learning Pixel-Based Inversion of Logging-While-Drilling in Anisotropic Formation ." doi: 10.21227/cwgf-g832