ABOUT THE COURSE:Petroleum Data Analytics (PDA) is rapidly transforming the oil and gas industry through the integration of Artificial Intelligence (AI) and Machine Learning (ML). As we look ahead, it's evident that mastering these technologies will be pivotal for shaping the future of engineering disciplines, particularly in petroleum engineering.This 12- weekcourse aims to equip the next generation of petroleum professionals with essential foundations in PDA. While it's acknowledged that a single course cannot cover all aspects of becoming a PDA expert, it serves as a crucial starting point. Participants will gain a realistic understanding of AI and ML fundamentals as they apply to solving engineering challenges in the petroleum sector.For engineering-domain experts, transitioning into skilled AI and ML practitioners is becoming increasingly important. The ability to harness data-driven insights through these technologies will not only optimize existing processes but also drive innovation in exploration, production, and operational efficiency within the industry.Ultimately, this course serves as a catalyst for enthusiasts and professionals alike to grasp the transformative potential of PDA. It's a step towards unlocking the future where data-driven strategies and advanced analytics play a central role in shaping the trajectory of the oil and gas industry.INTENDED AUDIENCE: Undergraduate, post graduate and PhD students’ professional practitioner in the discipline of Petroleum Engineering, Petroleum Refinery Engineering, Chemical EngineeringPREREQUISITES: Bachelor’s degree in any Engineering disciplineINDUSTRY SUPPORT: ONGC,OIL, ESSAR, IOCL, CAIRN, GAIL

Syllabus

Week 1:

Significance of Python and Petroleum Data Analysis
Introduction to Python and Programming Fundamentals: Environmental set up- Installation of Python and anaconda, Python packages, basics of data structures.

Week 2:Programming fundamentals:

Data types (Immutable & Mutable), Operator types, loops, functions, conditions, objects, and classes)

Week 3:Implementation of Python libraries:

Pandas: Environment set up, PANDAS –series, data frame, read CSV, cleaning data, correlations, lotting, panel, basic functionality, descriptive statistics, function application, iteration, and sorting.

Week 4:Implementation of Python libraries:

NUMPY: Introduction and environment set up, data types, array, indexing & slicing, binary operators, string functions, mathematical functions, arithmetic operations, statistical functions, sort, search & counting functions.
Plotting in Python: Installation of Matplotlib, Pyplot, plotting, markers, line, labels and title, grids, subplot, scatter, bar, histograms, pie-charts

Week 5:Data wrangling and preprocessing on reservoir/Unconventional resources data:

Understanding the concept of data wrangling using sub setting, filtering, and grouping, detecting outliers and handling missing values, concatenating, merging, and joining.

Week 6:Data wrangling and preprocessing on reservoir/Unconventional resources data: