Course Curriculum

Install Python, configure virtual environments, and set up Jupyter for engineering workflows.

Variables, functions, control flow, and OOP — tailored for petroleum engineers.

Lists, dicts, sets, and tuples for organizing well data and production records.

Vectorized computation with NumPy arrays and tabular analysis with Pandas DataFrames.

Matplotlib, Seaborn, and Plotly for well logs, cross-plots, and production charts.

Import LAS files, clean production CSVs, and handle missing data in field datasets.

Compute porosity, water saturation, and net pay from triple-combo logs.

Standing, Vasquez-Beggs, and Lee-Gonzalez correlations for oil, gas, and water properties.

Arps hyperbolic, exponential, and harmonic models for production forecasting.

Havlena-Odeh graphical method and generalized material balance for OOIP estimation.

Finite-difference grids, IMPES method, and history matching with Python.

Inflow performance, vertical lift performance, and system analysis for well optimization.

Gas lift, ESP sizing, and rate allocation across multi-well pad systems.

Predict rate of penetration and detect drilling dysfunctions from sensor data.

Z-factor correlations, gas compressibility, and deliverability calculations.

Scikit-learn basics — train/test splits, cross-validation, and feature engineering.

Regression and classification models for facies prediction and production estimation.

K-means, PCA, and DBSCAN for rock typing and anomaly detection.

Four standalone capstone projects: from raw, broken data to a signed engineering decision.

Build the data contract behind a surveillance dashboard: KPIs, honest downsampling, and alerts.

Deploy a model safely: ship the artifact, validate every payload, and cost managed vs self-hosted.

Prove what you can do: map your skills to a role and score your portfolio the way a reviewer does.