About the course:  Data science is the field of applying advanced analytics techniques and scientific principles to extract valuable information from data for quick decision-making, strategic planning and other uses. The insights that data science generates help oil and gas organizations increase operational efficiency, identify new opportunities and improve accuracy. Ultimately, they can lead to competitive advantages over well analysis.

Data science involves a plethora of disciplines and expertise areas to produce a holistic, thorough and refined look into raw data. Data scientists must be skilled in everything from data engineering, math, statistics, advanced computing and visualizations to be able to effectively sift through muddled masses of information and communicate only the most vital bits that will help drive innovation and efficiency.

Learning Objective:

• Data science is the next big thing in the oil and gas industry and this course will give you the right heads up & exposure to it.
• A unique course especially designed for Oil &Gas professionals where you will appreciate the value of data science & machine learning in the oil and gas domain.
• Application oriented approach which will enlighten you with real examples of data science in reservoir, production, geology & petrophysical domains.

Duration: 20+ hours

Outcome from this course:

• Awareness and knowledge related to the role of data science in the career path of an oil and gas professional/student.
• Understanding about the "math" of machine learning algorithms and their subsequent applications in solving industry problems.
• Exposes you to a different genre of job opportunities for oil and gas professionals/students.

Pre-requisites:  None. Good to have a basic level understanding of matrix algebra and calculus.

Topics to be covered:

1)     MACHINE LEARNING FUNDAMENTAL FOR OIL & GAS:

• Digital & Digitalization framework
• Fitment to oil & gas
• Types of ML techniques
• ML workflows
• Exploratory data analysis
• Outlier/Anomaly detection
• Data cleaning/imputation.
• Feature engineering.
• Model building & evaluation.

2)     SUPERVISED LEARNING& RELATED APPLICATIONS:

• Introduction to supervised learning.
• Supervise ML algorithms such as linear/ logistic regression KNN SVM decision trees.
• Evaluation metrics.
• Deep learning basics.
• Artificial neural network.

3)     UNSUPERVISED LEARNING & RELATED APPLICATION:

• Introduction to unsupervised learning.
• Unsupervised ML algorithms such as k-means algorithm, DB scan, hierarchical, clustering, math behind clustering.
• Use cases for unsupervised ML such as liquid loading prediction, geomechanically data clustering for hydraulic fracturing design.

4)     INTRODUCTION TO PYTHON

• Brief summary of python libraries (NumPy, pandas, matplotlib)
• Biases operation, creating string list, dictionary, tuple, data, import and visualization
• Production data visualization using python