

Data Science Application in Regional Oil and Gas Fields Study (with R and SQL)
This course provides a comprehensive introduction to data science applications in the analysis of regional oil and gas fields. Using powerful tools like R and SQL, participants will learn to extract insights from data, enabling them to make informed decisions in exploration and production strategies
Description
Data science is transforming the oil and gas industry by enabling data-driven decisions that optimize operations, reduce risks, and enhance profitability. This course focuses on applying data science techniques to regional oil and gas field studies using R and SQL. Participants will learn how to handle and analyze complex datasets, develop predictive models, and gain actionable insights to support exploration and production activities. This training is ideal for professionals seeking to leverage data analytics for strategic decision-making in the energy sector.
Demo Class
Introduction
Data-driven approaches are becoming essential in the oil and gas industry to maximize efficiency and uncover opportunities. This course equips participants with the knowledge and skills needed to apply data science methods to regional oil and gas field studies. Through hands-on exercises and real-world examples, you will explore how to utilize R and SQL to analyze geological and production data, generate predictive models, and make data-backed decisions that improve operational outcomes.
Objectives
Training Methodology
The course employs a practical, hands-on training approach that blends theoretical knowledge with interactive sessions. Participants will engage in real-life case studies, guided exercises, and collaborative projects that focus on solving problems specific to oil and gas exploration. The use of R and SQL will be emphasized, with step-by-step demonstrations and practice sessions to ensure a deep understanding of data science applications.
Organisational Impact
Personal Impact
Who Should Attend?
Day 1: Introduction
Introduction important aspects of reservoir characterization and all data
Introducing industrial datasets from different fields such as well log data, core data, pressure data, production, drilling, and pore pressure.
Introduction of data science approach in data analytics from scratch
Introduction R programming
Introduction of SQL role in database management
Brief introduction of RStudio
Brief introduction of various R Packages
Introduction of different applications of data analytics in upstream
Introduction of data analytics steps by R
Day 2: Data analytics
Data importing, data appending, data transforming, handling missing data,
Data Wrangling such as wells data Joining, Combining, and Reshaping
Well-log data Aggregation and Group Operations
Confidently use R to solve different reservoir parameters such as porosity, water saturation evaluation in sandstone and carbonate reservoirs, different approaches in shale evaluation, logs relationship, and representing various cross-plot
Easily create high-quality visualization of different well data
Visualizations I
Day 3: Database computation
Preparation of field data management by SQL
Database organization, SELECT, TABLES, FILTERING, JOINING, AGGREGATION… with well-log data by SQL
Connecting R and SQL to extract useful data from the database
Core Analytics (FZI investigation in multi-wells)
Advanced Visualizations II
Day 4: Report/Dashboard publishing
Web scrapping to import live data from a website to R and Store in the Database
Preparing informative dashboard from well data analysis in R Markdown
Publishing report/dashboard on the internet
Day 5: Fundamentals of Machine Learning
Introduction of Machine Learning approaches in the oil and gas industry
Preparing raw data to use in ML algorithm (Regression method)
Run the actual ML Stream from scratch (Regression method)
How to evaluate and select the best ML approach
On successful completion of this training course, PEA Certificate will be awarded to the delegates
Experienced Energy Professional: Over 19 years of expertise in roles including Geoscientist, Petrophysicist, Drilling/Reservoir Geomechanics, and Renewable Data Scientist, with a career spanning Iran, Oman, Malaysia, China, Austria, Turkey, and New Zealand.
Data Science and Machine Learning Specialist: Skilled in applying data science techniques using Python, SQL, R, Power BI, and other tools to forecast attributes like inflow rates, wind speed, and solar radiation in the energy industry.
Strategic Role in Renewable Energy: Member of the analytics team at Genesis Energy, focused on strategic planning for renewable projects, decarbonization, and sustainability in the wholesale electricity market.
Advocate for Energy Transition: Involved in subsurface studies for underground gas storage and carbon capture, and actively engaged in teaching advanced courses on machine learning applications in energy transition and renewable energy data. Passionate about New Zealand's renewable energy development, CCS, and hydrogen storage potential.