Internet Explorer 9 and Safari users must enable TLS in their browser settings
(The new Ocean website uses TLS for enhanced security).
Accept
*
Internet Explorer version 9: Enable TLS versions 1.0. 1.1 and 1.2 in your Browser settings (Internet options > Advanced > Settings > Security).
*
Safari: Enable TLS versions 1.0. 1.1 and 1.2 in your Browser settings (Preferences > Advanced Icon > Change Settings > Advanced Tab > Settings).
Ocean does not support Internet Explorer versions 8 and below.
Get Latest Version
If you still have trouble, you should also clear your browser cache: press Shift-Ctrl-Delete [any browser, except Safari] and delete all items.
Further questions can be submitted via
Contact Us
Welcome
Sign out
Register/Login
Contact Us
Plug-Ins
Featured
Plug-in Webinars
Plug-in Status
Platforms
Petrel
Studio
Techlog
Domains
Drilling
Geology & Modelling
Geophysics
Information Management
Reservoir Engineering
Reservoir Geomechanics
View All
OCEAN APIs
Ecosystem
Academia
Competitions
Software Companies
Partner Program
Become a Certified Partner
Knowledge Base
Getting Started
Developing Plug-ins
Testing Plug-ins
Publishing Plug-ins
References
Learning
Developer
Petrel
Getting Started
Developing Plug-ins
Testing Plug-ins
Publishing Plug-ins
References
Learning
Technical Alerts
Studio
Getting Started
Developing Plug-ins
Testing Plug-ins
Learning
Techlog
Getting Started
Developing Plug-ins
Testing Plug-ins
Learning
Submit/View Ticket
Services
Consulting
Training
Ocean Training Schedules
Support
Ocean Software Support
 
 
Home
>
Plug-ins
>
Plug-in Details
IPLAB Sweet Spot Analysis Prediction2D
By
IPLAB LLC
Previous
Next
Previous
Next
14Days - Evaluation
Quantity:
Request Quote
Sweet spot analysis results
Result of well log parameter predictions using seismic attributes based on machine-learning algorithms (neural network). Twenty-five realizations using 70% randomly selected well log points on each of these realizations were applied for this prediction. Several maps (average, standard deviation, P10, P50, and P90) were calculated using these realizations. The size of the points reflects the well logs parameter.
Input parameters example
For prediction, it is possible to use several seismic attributes or waveforms in the layer from several seismic cubes.
Quality of the prediction
Multirealization approach with randomly removed learning points allows estimating the quality of predictions.
Correlation table
Correlation table and factor analysis allow estimating influence of each input parameter.
Show Me Video
Plug-in Attributes
Platform:
Petrel
Lifecycle
Domain:
Geophysics
|
Geology and Modelling
Challenges:
Unconventional Heavy Oil | Carbonate and Fractures | Deepwater Exploration and Production | Unconventional Shale
ECCN:
Russia origin, EAR99
Version
2018 | 2019 | 2020
Supporting Documents
Installation Guide
2018
|
2019
|
2020
|
Release Notes
2018
|
2019
|
2020
|
User Manual
2018
|
2019
|
2020
|
Others
Overview
The sweet spot analysis plug-in is based on machine-learning algorithms applying a set of maps (seismic attributes) or seismic waveform in the layer. The result will be one or several maps (average, standard deviation, P10, P50, and P90) with predictive parameters per the cross-validation option.
Specifications
Learning algorithms allow using cross-validation options
Applying of all learning points.
applying the defined number of realizations based on random selected well log points on each of these realizations; several maps (average, standard deviation, P10, P50, and P90) were calculated using this realization
Features
Predictive algorithms
Linear regression
Alternating conditional expectations (ACE) regression
Nearest neighbour
Random forest
T-neural network
Additional Information
For predictions, it is proposed to use
set of maps—seismic attributes or any other maps arranged like a set of surface attributes
seismic waveforms defined in the layer (top and bottom surface) using several seismic cubes (full-angle stacks of seismic attributes)
Associated Plug-ins
×