Machine Learning For Oil and Gas Using Python The Ultimate Data Driven Adventure

Python Module

This module will cover all python basics to get started and feel confident in writing code and maintain future code bases.

Part 1:

1.      Introduction to python for oil and gas Industry

2.      Python tools and package options

3.      Data types and basic python functions

4.      Introduction to data casting

5.      Introduction to string and string manipulation

Part 2:

·        Data container (Lists and Dictionaries)

·        Operation on containers.

·        Introduction to loops

·        Introduction to Branching (IF Statements)

·        Mixing Lops and Branching

·        Introduction to User Functions

Part 3:

·        Working with Arrays and Applying mathematics to them

·        Working with tabulated data

·        Basic Pandas functions for data manipulation

·        Introduction to visualization.

    EDA – Exploratory Data Analysis

Machine Learning Module:

This module will introduce the trainee to machine learning concept and various uses and implementations, in this module user will learn how to utilize python as a tool for various ML related projects

Part 4:

• Processing Tabulated Data.

• Data Filter, cleansing and Outlier handing

• Imputations and it’s methodologies.

• Feature Engineering

• Plotting for ML (Distribution, Pair plots, box, LMPlots, Heat)

• Machine Learning Workflows (Putting Everything in place)

Part 5 :

• Introduction to machine learning Types

• Introduction to Unsupervised Learning

• K-Mean Clustering using Sklearn

• Clustering Oil wells based on petrophysical properties

• Clustering Gas Wells Based on Liquid Loading Index

• Hierarchal clustering and Dendrogram.

• Hierarchal Cluster Based Water Cut in Oil Wells

Part 6:

• Introduction to Regression

• Basics of Regressions using NumPy Poly1d.

• Introduction to Linear Regression in SKlearn

• Multivariate Regression in ML

• Regression Applied to Oil and Gas Production Prediction

• Evaluation of Regression Models

• Regression Sensitivity Analysis using OVAT

• Predicting Drilling Performance Using Multilinear Regression

Part 7:

• Introduction to classification problems

• Classifications as applied to Oil and Gas Industry Problems.

• Introduction to Logistic Regression.

• Introduction to KNN.

• Classifying Flow Stability in Oil Wells.

• Comparing Decline Curve Analysis to ML Regression

• Introduction to Support Vectors (SVM)

• Predicting Geomechanically Properties using SVM

• Shale Formation Simulation Classification

Part 8:

• Introduction to Neural Networks

• Introduction to deep learning

• Introduction to fuzzy logic

• Applications of NN in oil and gas industry

• Model Optimization

• Dashboarding and ML Implementation

• Notes on OOP approach and Production Grade Code.