COURSE OVERVIEW:

As seismic datasets grow in complexity and volume, the integration of advanced attributes with Machine Learning (ML) has become essential for efficient reservoir characterization. This course explores the synergy between data-driven algorithms and the physical insights provided by seismic attributes. Participants will investigate how ML can automate the identification of patterns, classify facies, and predict reservoir properties with a degree of detail and speed unattainable through traditional manual interpretation.

The scope of this training focuses on the practical application of supervised and unsupervised learning techniques to 3D seismic volumes. Attendees will learn to build, train, and validate neural networks, decision trees, and clustering algorithms specifically tailored for subsurface data. We will explore the selection of "optimal" attribute sets that serve as the input for ML models, ensuring that the results are grounded in geological and geophysical reality rather than just statistical correlation.

Coverage includes the use of Deep Learning and Convolutional Neural Networks (CNNs) for automated fault extraction and horizon tracking. By integrating rock physics and well-log data with ML-enhanced seismic attributes, geoscientists can create more accurate and predictive reservoir models. This course provides the technical skills necessary to leverage the "Digital Transformation" in geosciences, turning vast amounts of seismic data into actionable reservoir intelligence.

COURSE OBJECTIVES:

After completion of this course, the participants will be able to:

• Identify the most effective seismic attributes for machine learning workflows.
• Distinguish between supervised and unsupervised learning in a geoscience context.
• Utilize K-means and Self-Organizing Maps (SOM) for seismic facies clustering.
• Implement Artificial Neural Networks (ANN) for reservoir property prediction.
• Apply Deep Learning (CNNs) for automated seismic structural interpretation.
• Perform feature selection and dimensionality reduction (PCA) on attribute sets.
• Integrate well-log labels with seismic cubes to train supervised models.
• Evaluate ML model performance using cross-validation and confusion matrices.
• Utilize machine learning to automate the detection of seismic geohazards.
• Combine multi-attribute volumes through RGB blending and meta-attributes.
• Predict porosity and lithology volumes using ML-driven seismic inversion.
• Assess the risk of "overfitting" and ensure geological validity of ML results.
• Design automated workflows to handle large-scale "Big Data" seismic projects.

TARGET AUDIENCE:

Geophysicists, Data Scientists, Geomodellers, and Interpretation Specialists interested in the application of AI and Machine Learning to subsurface challenges.

TRAINING COURSE METHODOLOGY:

A highly interactive combination of lectures, discussion sessions, and case studies will be employed to maximise the transfer of information, knowledge, and experience. The course will be intensive, practical, and highly interactive. The sessions will start by raising the most relevant questions and motivating everybody to find the right answers. The attendants will also be encouraged to raise more of their questions and to share in developing the right answers using their analysis and experience. There will also be some indoor experiential activities to enhance the learning experience. Course material will be provided in PowerPoint, with necessary animations, learning videos, and general discussions.

The course participants shall be evaluated before, during, and at the end of the course.

COURSE CERTIFICATE:

National Consultant Centre for Training LLC (NCC) will issue an Attendance Certificate to all participants completing a minimum of 80% of the total attendance time requirement.