HampsonRussell Machine Learning for Seismic Reservoir Characterization Workshop

Course Overview:

HampsonRussell offers two key machine learning tools: EMERGE and GeoAI. This course provides an in-depth exploration of both programs.

• The EMERGE section focuses on techniques for estimating rock properties or facies using multiple seismic attributes. It covers the theory and application of linear, non-linear, and neural network methodologies for reservoir property prediction. Additionally, it includes a segment on estimating missing well logs using available log data.
• The GeoAI section introduces the practical use of Convolutional Neural Networks (CNN) for rock property prediction and provides an overview of essential machine learning concepts. A crucial aspect of building reliable models is having large training datasets. The course explains a rock physics-based approach to generating synthetic training data. It also details the CNN machine learning workflow, including training with synthetic and real seismic and well data, validating the network, and applying it to real seismic data for rock property and facies prediction.

Course Benefits:

• Provides a mechanism for the user to derive complex relationships between seismic attributes and petrophysical parameters
• Learn about Supervised learning, multi-linear regression, deep neural networks, and convolutional neural networks (CNN).
• Application of neural networks technology in well log prediction, petrophysical volume generation and seismic lithology classification
• Structured to teach theory alongside practical exercises, equipping the user in the operation of the Emerge and GeoAI programs.

Duration: 3 days 
Software used: HampsonRussell Emerge, GeoAI (including WellGen and CNN)
Course Format: Instructor-led, workflow-based, Virtual
Prerequisites: Prior experience with HampsonRussell software is not required for this workshop; however, attendees will gain familiarity with its functionality throughout the course.
Who should attend: This course is designed for geophysicists, geologists, engineers, and technical staff who want to understand the theory behind these advanced techniques and learn how to apply them effectively in their work.
Language: English