Deep Learning, Scientific Machine Learning and AI for Reservoir & Production Engineering is an advanced workshop designed for petroleum professionals who want to explore modern AI-driven methods for solving complex subsurface problems. The workshop focuses on the practical use of deep learning, scientific machine learning, and artificial intelligence in reservoir and production engineering workflows, with emphasis on real-world engineering applications rather than theory alone.


Participants will gain exposure to how these methods can be used to improve prediction, accelerate analysis, and support better engineering decisions across areas such as reservoir characterization, production forecasting, and workflow automation. The workshop is structured to help attendees understand where AI adds value in oil and gas operations and how it can complement engineering judgment in subsurface applications.

All content in this session is copyrighted by Mr. Nashat. Access to recordings, slides, and the Excel workbook is provided exclusively through this platform. Any unauthorized use, reproduction, or distribution outside the portal is strictly prohibited and may result in legal action under applicable laws.


Recordings, data sets, and certificates will be provided within one business day after the event is completed.

Workshop Objectives

By the end of this workshop, participants will be able to:


Understand the core concepts of deep learning, scientific machine learning, and AI in the context of reservoir and production engineering.


Identify practical use cases where AI methods can improve subsurface analysis and decision-making.


Recognize how Python-based tools such as TensorFlow and Keras support AI workflows in engineering applications.


Explore how AI techniques can be applied to reservoir modeling, production forecasting, and related engineering problems.


Build a clearer understanding of how modern machine learning approaches can support faster and more efficient engineering workflows.

About the Presenter

Nashat Jumaah Omar is a production engineer, instructor, and technical consultant with over 11 years of experience in the oil and gas industry, with particular depth in production engineering, flow assurance, subsurface workflows, and engineering data applications. His work combines petroleum engineering knowledge with practical use of digital tools such as Python, SQL, Power BI, C#, FORTRAN, and VBA to improve analysis, automate repetitive tasks, and support more efficient engineering workflows.


Over the course of his career, he has worked across production operations, well and network modeling, flow assurance, production data management, and software-enabled engineering solutions, including experience with platforms such as PIPESIM, PROSPER, OLGA, and OFM. His professional background also includes training and mentoring engineers in Python, machine learning, data analytics, and applied digital workflows for upstream oil and gas environments.


At Petroleum Engineers Association, he has contributed to the design and delivery of technical training programs for petroleum professionals, including courses in Python for petroleum engineering, machine learning, data analysis, and production and reservoir applications. His teaching style is grounded in real industry use cases, with an emphasis on helping participants translate coding and analytics concepts into practical tools for day-to-day engineering work.

Register Now

By registering for this webcast, you are sharing your registration information with PEA and acknowledged that you have read and agreed to the Privacy Policy and Terms and Conditions. By submitting your personal information, you are agreeing that PEA may contact you via the details provided.

View More

Premium Workshop
For PEA Members Only
icon
Material Balance Modeling
November 28, 2026 - November 29, 2026
Material Balance Modeling

Material balance is one of the most direct methods available to a reservoir engineer for estimating hydrocarbons in place, identifying the drive mechanism and forecasting reservoir performance. It requires far less data than a full numerical model, and when it is set up correctly it produces results that can be defended in technical reviews and reserve audits.This workshop covers the complete material balance workflow as it is applied on producing assets. It begins by placing the reservoir within the integrated production system, then moves through data preparation and quality control, tank model construction, drive mechanism identification, and the use of analytical and graphical diagnostic tools. Participants work through the classical diagnostic plots, including Dake and Campbell, and learn how to read what each plot indicates about depletion, gas cap expansion and water influx.The second part of the workshop addresses history matching using both analytical and graphical techniques, determination of STOIIP, aquifer identification and sizing, and running prediction cases to generate production forecasts and recovery estimates. Results are compared against volumetric and simulation-based estimates so that participants understand where material balance is reliable and where a numerical model becomes necessary.The workshop is delivered at an advanced level and is intended for engineers who already work with production and pressure data and want a structured, repeatable method for in-place volumes, drive mechanism evaluation and performance prediction.