GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Industrial Inspection
Presentation
Media
Deep Learning with Sparse Uncertain Data: An Oil & Gas Perspective
Abstract:
Deep learning techniques have the potential to enable a step change in modeling efficiency for industrial systems. By increasing efficiency and accuracy of diagnostics, and extracting meaning from large amounts of industrial data, deep learning provides a pathway to truly differentiated outcomes. In this talk, we will discuss our experience building deep learning models for Oil & Gas applications and the CI/CD process for managing the lifecycle of the models in production. We will present novel applications of deep learning for anomaly detection, rock formation identification and optimization. The hybrid modeling framework combining physics-based models with deep learning techniques will be highlighted with specific application of production optimization.
 
Topics:
Industrial Inspection
Type:
Talk
Event:
GTC Silicon Valley
Year:
2018
Session ID:
S8789
Streaming:
Share: