Fundamentals of Machine Learning and Data Science for the Oil and Gas Industry
Machine learning is a growing field in technology companies, and more recently, in the Oil and Gas industry companies and research groups. This course focuses on the data preparation and machine learning application on different case of study examples:
- Introduction to Data Science in Python and R
- Predicting mass of oil (regression)
- Data analysis
- Data cleaning
- Linear regression
- Gradient boosting regressor
- Facies classification
- Data analysis
- Data imputation
- Feature engineering
- Logistic regression (imbalanced data)
- Gradient boosting classifier (imbalanced data)
- Severe injuries analysis and predictions (HSE)
- Natural language processing
- Reports classification
- Deep Learning
- Introduction to Tensorflow
- Image segmentation for salt identification in seismic sessions
- Python programming: tips for machine learning modeling
- R programming: data analysis and visualization
- Data preparation: how the data must be processed prior to modeling to improve product outcome
- Machine learning: learning the most popular ML packages for python, such as Pandas, Scikit-Learn, Tensorflow, among others
- Interpretation of the model used, and how to choose the most appropriate model for each case
Introductory to Intermediate
Data science and machine learning are growing fields that have applications in any type of industry and has shown to improve the profit of companies that implement a data science group in them. Recently, companies from the Oil&Gas industry are starting to get on board of this new tendency and are creating and implementing new technologies with the help of machine learning algorithms. Demand for data scientists is increasing every year as new methods are required on each industry.
Oil and Gas professionals that are interested on learning how to apply machine learning methods in their projects and/or workflow, and that already have some experience in Python programming.
.8 CEUs (Continuing Education Units) are awarded for this 1-day course.
- Basic knowledge in Python and R programming.
- A laptop with Python and R installed to run codes is recommended but not mandatory.
All cancellations must be received no later than 14 days prior to the course start date. Cancellations made after the 14-day window will not be refunded. Refunds will not be given due to no show situations.
Training sessions attached to SPE conferences and workshops follow the cancellation policies stated on the event information page. Please check that page for specific cancellation information.
SPE reserves the right to cancel or re-schedule courses at will. Notification of changes will be made as quickly as possible; please keep this in mind when arranging travel, as SPE is not responsible for any fees charged for cancelling or changing travel arrangements.
We reserve the right to substitute course instructors as necessary.
Marcelo Guarido a data scientist with background in physics and geophysics, with years of experience on research and application of machine learning algorithms to different types of dataset, such as images, time series, geophysical, petrophysical, among others. Marcelo worked 7+ years on Oil and Gas industry companies, most of the cases with seismic acquisition and processing in companies such as PGS and Schlumberger, and during the last 4 years, has focused on the machine learning and data science research. He worked at Verdazo Analytics doing research in machine learning applied to drilling and petrophysical data. Also, Marcelo is current a postdoctoral researcher at CREWES (University of Calgary) and is the head of the data science initiative in the consortium. Marcelo is involved on the research, training, consulting, and mentoring of Oil and Gas projects and professionals. Guarido holds a BS degree in Physics and a MSc degree in Geophysics from University of São Paulo (Brazil) and a PhD degree from University of Calgary and is a CREWES associate.