Petrel

E&P software platform

Release Notes
Machine Learning for Petrel 2023.3
Version 2023

Installation Guide
2023.3.1.0
Copyright Notice
Copyright © 2023 SLB. All rights reserved.
This work contains the confidential and proprietary trade secrets of SLB and may not
be copied or stored in an information retrieval system, transferred, used, distributed,
translated, or retransmitted in any form or by any means, electronic or mechanical, in
whole or in part, without the express written permission of the copyright owner.

Trademarks & Service Marks

SLB, Schlumberger, the SLB logotype, and other words or symbols used to identify the
products and services described herein are either trademarks, trade names or service
marks of SLB and its licensors or are the property of their respective owners. These
marks may not be copied, imitated, or used, in whole or in part, without the express
prior written permission of SLB. In addition, covers, page headers, custom graphics,
icons, and other design elements may be service marks, trademarks, and/or trade
dress of SLB, and may not be copied, imitated, or used, in whole or in part, without the
express prior written permission of SLB. Other company, product, and service names
are the properties of their respective owners.
ECLIPSE® is a mark of SLB.
An asterisk (*) is used throughout this document to designate other marks of SLB.

Security Notice
The software described herein is configured to operate with at least the
minimum specifications set out by SLB. You are advised that such minimum
specifications are merely recommendations and not intended to be limiting to
configurations that may be used to operate the software. Similarly, you are
advised that the software should be operated in a secure environment
whether such software is operated across a network, on a single system
and/or on a plurality of systems. It is up to you to configure and maintain your
networks and/or system(s) in a secure manner. If you have further questions
as to recommendations regarding recommended specifications or security,
please feel free to contact your local SLB representative.
Contents

1. Machine Learning for Petrel installation guide ....................................................................................................................................................... 1

Hardware recommendations ................................................................................................................................................................................................ 1
Software requirements ............................................................................................................................................................................................................... 1
NVIDIA drivers.................................................................................................................................................................................................................................... 2
Versioning scheme........................................................................................................................................................................................................................ 2
Required Petrel license features list ................................................................................................................................................................................ 3
Operating systems ......................................................................................................................................................................................................................... 3

2. Installation procedure.................................................................................................................................................................................................................. 4
If Python 3.10 is not installed ................................................................................................................................................................................................ 4
If plug-in is already installed without ML Fault Prediction.............................................................................................................................. 6
With Python 3.10............................................................................................................................................................................................................................. 8
Nvml availability ............................................................................................................................................................................................................................ 10

3. Installation process results .................................................................................................................................................................................................. 11

Plug-ins................................................................................................................................................................................................................................................ 11
Python Virtual Environment setup ................................................................................................................................................................................. 13

4. Uninstallation procedure....................................................................................................................................................................................................... 15

5. Uninstallation process results ........................................................................................................................................................................................... 17

6. Help and Support Information.......................................................................................................................................................................................... 18

 1. Machine Learning for Petrel
installation guide
Petrel The plugin works with Petrel 2023.3 or higher.

License It provides the Machine Learning Property Modeling, which

contains "ML Property Modeling"; the Machine Learning
Assisted Seismic Interpretation which contains ML Fault
Prediction , Fault Extraction , and ML Horizon Prediction
(NN) . These features are licensed and require dedicated
license feature on a dongle or a license server.

Country of origin: Netherlands/Norway with US comingled

content

Public Key Token: 74f56ef7d8625d2d

Hardware recommendations
Minimum Preferred
Quad-core processor (best with Dual 4 to 8 core processor (best with a
Processor
fast clock speed and high cache fast clock speed and high cache)
Memory 64GB 256GB
The quality of the viewing experience increases with the size and number of
Display
monitors
Graphics desktop NVIDIA RTX A4000 NVIDIA RTX A6000 or A5000
Graphics mobile NVIDIA RTX A5000 NVIDIA RTX A5000
GPU memory 16GB 24GB+
Fast rotational speed HDD (10K,
Primary storage PCIe based Flash or SSD
15K RPM) or SSD
SSD or Fast rotational speed HDD
Secondary storage Optional
(10K, 15K)

Software requirements
Install Petrel 2023.3 or higher to use Machine Learning for Petrel 2023.3.

1
 Additional requirements for ML Fault Prediction:
Install Python 3.10 64-bits
Install CUDA 11.2
Install cuDNN 8.1.1
Download cuDNN for Windows.
Unzip the downloaded file. Inside the "\cuda\bin" folder of the
unzipped file, copy all the cudnnXXXX.dll files to "C:\Program
Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2\bin".
If you face any issues with this installing cuDNN, refer to the cuDNN
official installation guide to see more.
Note: Python is not distributed with the installer, the user needs to download
from the Python official website. CUDA and cuDNN are not distributed with the
installer, the user needs to download from the NVIDIA official website.

NVIDIA drivers
Release 528.24 is the latest recommended and tested official driver from
NVIDIA for both workstations and mobile workstations. SLB recommends
upgrading to the latest official drivers from your PC vendor's home page or
directly from NVIDIA.
Earlier drivers are still supported, although testing shows that NVIDIA drivers
430.64 and later fix many critical issues that support Petrel.
Accordingly, release 430.64 is the minimum required driver for NVIDIA
graphics cards when working with Petrel.

Versioning scheme
The convention for Machine Learning for Petrel 2023.3 versioning is x.y
where:
• x is the major version of the plug-in
• y is the minor version of the plug-in

2
Required Petrel license features list

Machine Learning for Petrel Petrel Core Required Module

Machine Learning Property Geoscience Core, or Petrophysical Modeling
Modeling Combined Core

Machine Learning Assisted Geophysics Core, or Seismic Interpretation

Seismic Interpretation Geoscience Core, or
Combined Core

Operating systems
Microsoft Windows 10 Professional or Enterprise Edition (64-bit)
Microsoft Windows 11 Professional or Enterprise Edition

3
 2. Installation procedure
The installer installs features differently depending on what is available on the
computer.
• Machine Learning Property Modeling will always be installed.
• Machine Learning Assisted Seismic Interpretation will install without ML
Fault Prediction if Python 3.10 is not installed.
• Machine Learning Assisted Seismic Interpretation will install entirely if
Python 3.10 is installed.
Therefore, there are three possible scenarios:

Scenarios Target Users

Machine Learning Property Modeling
Machine Learning Assisted Seismic
When Python 3.10 is not installed
Interpretation without ML Fault
Prediction
When plug-in is already installed
without ML Fault Prediction Machine Learning Assisted Seismic
Interpretation including ML Fault
When Python 3.10 is installed Prediction

Note: After installing the plug-in with ML Fault Prediction, ensure Nvml
availability to complete the installation process successfully.

If Python 3.10 is not installed

If Python 3.10 is not installed, the installer can still be run, but ML Fault
Prediction feature will be skipped as this feature requires Python 3.10.

Steps to install the plug-in for this scenario:

1 Install Petrel 2023.3.
2 Double-click MachineLearning.2023.3.msi to open the installation dialog
box.

4
3 On the Welcome to Machine Learning for Petrel 2023.3 Setup dialog box,
click Next.

4 On the Ready to install Machine Learning for Petrel 2023.3 page, click
Install.
5 New files will be copied, and the progress of the installation will be shown.

5
 6 On the Installation Complete page, a warning is shown related to the
unavailability of the ML Fault Prediction feature. Click Finish.

If plug-in is already installed without ML Fault Prediction

If you already have the Machine Learning for Petrel 2023.3 installed without the
ML Fault Prediction feature and try to run the ML Fault Prediction in Petrel, you
will see the following error messages about missing python environment:

To be able to use the ML Fault Prediction feature, you must install Machine
Learning for Petrel 2023.3 following these steps below:
1 Uninstall the already installed Machine Learning for Petrel 2023.3 (see
Uninstallation procedure).
6
2 Download and install Python 3.10 (64-bits) following software installation
guidelines.
3 Double-click MachineLearning.2023.3.msi to open the installation dialog
box.

4 On the Welcome to Machine Learning for Petrel 2023.3 Setup dialog box,
click Next.

5 On the Ready to install Machine Learning for Petrel 2023.3 page, click
Install.
6 New files will be copied, and the progress of the installation will be shown.

7
 7 On the Installation Complete page, click Finish.

With Python 3.10

If Python 3.10 is already installed and an internet connection is available:
1 Install Petrel 2023.3.
2 Double-click MachineLearning.2023.3.msi to open the installation dialog
box.

8
3 On the Welcome to Machine Learning for Petrel 2023.3 Setup dialog box,
click Next.

4 On the Ready to install Machine Learning for Petrel 2023.3 page, click
Install.
5 New files will be copied, and the progress of the installation will be shown.

9
 6 On the Installation Complete page, click Finish.

Nvml availability
In order for ML Fault Prediction to run successfully, nvml.dll is required.
Recent NVIDIA driver installations do not install the nvml.dll to the expected
location, therefore the file must be manually copied.
1 Ensure nvml.dll is available in "C:\Program Files\NVIDIA
Corporation\NVSMI".

2 If the folder NVSMI or the nvml.dll does not exist, you must copy it from the
drivers installed on your machine.
• Open file explorer in the C drive
• Type "nvml.dll" in the search bar

10
 • Copy the nvml.dll located in the folder starting with
"C:\Windows\System32\DriverStore\FileRepository\"
o The file should be in a folder with a name similar to
"nvdm.inf_amd64_587def1a11645486", this name
depends on your driver installation.
o If windows search does not find the nvml.dll file, you may
need to update your graphics driver for it to appear.
• Paste the nvml.dll into the folder "C:\Program Files\NVIDIA
Corporation\NVSMI"
o You may need to create the folder if it does not exist.

3. Installation process results

Installation of the .msi installer will:
• Install two plugins: Machine Learning and Machine Learning Enabler.
• Set up the Python virtual environment required to run machine learning
solutions, only if the installer is installed with ML Fault Prediction
feature.

Plug-ins
1 Start Petrel.
2 In the license selection dialog, you can see the features the plug-in
provides.

11
3 Open the Plug-in Manager dialog box.

4 Under the installed plug-ins list, you can find the plug-ins installed with the
msi installation.

As the result of the installation process:

1 The following files and libraries are deployed after the installation process
into "Petrel 2023\Extensions\Machine Learning_2023.3.1.0":
Slb.Petrel.Ffb.MachineLearning.Plugin_Manifest.xml
12
 • Plugin.xml
• Slb.Petrel.Ffb.MachineLearning.dll
• Slb.Petrel.Ffb.MachineLearning.FaultPrediction.dll
• Slb.Petrel.Ffb.MachineLearning.Plugin.dll
• MachineLearningPropertyModeling_UserGuide.pdf
• MachineLearningAssistedSeismicInterpretation_UserGuide.pdf
• MachineLearningForPetrel_InstallationGuide.pdf
• MachineLearningForPetrel_ReleaseNotes.pdf

2 The following files and libraries are deployed after the installation process
into "Petrel 2023\Extensions\Machine Learning Enabler_2023.1.0.0":
Plugin.xml
Slb.ML.Core.dll
Slb.ML.Core.Execution.dll
Slb.ML.Core.UI.dll
Slb.ML.Ocean.Module.dll
Slb.ML.Ocean.Plugin.dll
Slb.ML.Ocean.Plugin.Plugin_Manifest.xml

3 The following files and libraries are deployed after the installation process
into "Petrel 2023\Extensions\MLEnrichments":
InstallPlugins.xml
MachineLearning.2023.3.pip
Petrel.ML.Connector.2023.1.pip
In addition to these files, "Petrel 2023\Extensions\MLEnrichments" will
contain the following files and folders as well, if the plug-in is installed with
the ML Fault Prediction feature:
• keras
• tensorflow
• OpenZgyBindings-0.2.5568903-cp310-cp310-win_amd64.whl
• requirements.txt
• setup.bat

4 Files modified: The Petrel PluginManagerSettings.xml

Python virtual environment setup

Python virtual environment is setup only if Python 3.10 was installed before the
installation of the plug-in and an internet connection is available at the time of
installation.

The following folders are created:

C:\Program Files\SLB\MLEnrichment 2023\FP\env

13
C:\Program Files\SLB\MLEnrichment 2023\FP\ml
The following dependencies will be installed into the python virtual environment
folder (C:\Program Files\SLB\MLEnrichment 2023\FP\env) after the MSI
installation is completed.
• Imageio 2.31.1
• Numpy 1.25.1
• Overrides 7.3.1
• Scipy 1.11.1
• Tensorflow 2.10.0
• nvidia-ml-py3 7.352.0

14
4. Uninstallation procedure
Note: Before you uninstall the Machine Learning for Petrel plug-in, close Petrel.

You can uninstall Machine Learning for Petrel from:

Apps & features
Control Panel
Using MachineLearning.2023.3.msi itself.

To uninstall Machine Learning for Petrel from the Apps & features:
1 Click Start, perform a search, and click Apps & features.
2 Click on Machine Learning for Petrel 2023.3.
3 Click Uninstall.

To uninstall Machine Learning for Petrel from the Control Panel:

1 Click Start, click Control Panel, and then under Programs, click Uninstall a
program.
2 On the list of currently installed programs, click Machine Learning for
Petrel 2023.3, and then click Uninstall.

To uninstall Machine Learning for Petrel from the .msi file:

3 Double-click the MachineLearning.2023.3.msi installer.

4 On the Welcome to Machine Learning for Petrel 2023.3 Setup dialog box,

15
 click Next.

5 Click Remove in the Change, Repair or Remove installation.

6 Click Remove in the Ready to remove dialog box. The plug-in uninstalls.

16
7 Click Finish.
8 Machine Learning for Petrel is uninstalled.

5. Uninstallation process results

As the result of the uninstallation process:
1 Folder "Petrel 2023\Extensions\Machine Learning_2023.3.1.0" will be
deleted with the following files and libraries:
• Slb.Petrel.Ffb.MachineLearning.Plugin_Manifest.xml
• Plugin.xml
• Slb.Petrel.Ffb.MachineLearning.dll
• Slb.Petrel.Ffb.MachineLearning.FaultPrediction.dll
• Slb.Petrel.Ffb.MachineLearning.Plugin.dll
• MachineLearningPropertyModeling_UserGuide.pdf
• MachineLearningAssistedSeismicInterpretation_UserGuide.pdf
• MachineLearningForPetrel_InstallationGuide.pdf
• MachineLearningForPetrel_ReleaseNotes.pdf

2 Folder "Petrel 2023\Extensions\Machine Learning Enabler_2023.1.0.0"

will be deleted with the following files and libraries:
Plugin.xml
Slb.ML.Core.dll
Slb.ML.Core.Execution.dll
Slb.ML.Core.UI.dll
17
Slb.ML.Ocean.Module.dll
Slb.ML.Ocean.Plugin.dll
Slb.ML.Ocean.Plugin.Plugin_Manifest.xml

3 Folder "Petrel 2023\Extensions\MLEnrichments" will be deleted with the

following files and libraries:
InstallPlugins.xml
MachineLearning.2023.3.pip
Petrel.ML.Connector.2023.1.pip
In addition to these files, if the "Petrel 2023\Extensions\MLEnrichments"
contains the following files and folders, these will be deleted as well:
keras
tensorflow
OpenZgyBindings-0.2.5568903-cp310-cp310-win_amd64.whl
requirements.txt
setup.bat

4 If the plugin was installed with ML Fault Prediction feature, then the folder
"C:\Program Files\SLB\MLEnrichment 2023", which contains "\FP\env"
and "\FP\ml" folders, will also be deleted with the uninstallation.
If the SLB folder does not have any other contents except "C:\Program
Files\SLB\MLEnrichment 2023", the "C:\Program Files\SLB" will be
deleted as well.

5 Files modified:
The Petrel PluginManagerSettings.xml

6. Help and Support Information

The Machine Learning for Petrel 2023.3 is provided by SLB. For support
information contact Petrel support at your location or send request to:
https://www.software.slb.com/support

18
*Mark of SLB.
Copyright © 2023 SLB. All rights reserved