Skip to content
Daniel Wamriew

Teaching & speaking

Sharing knowledge

Teaching machine learning to engineers and scientists, and speaking about AI for science and technology.

Courses

Technical courses

Applied Machine Learning & Data Science for Petroleum Engineers & Geoscientists course logo

ML4PEGs

Course designer and instructor

Machine Learning for Petroleum Engineers and Geoscientists

Institution
Open course
Period
June 2026 – October 2026
Teaching assistant:
Haambayi Mudenda

A course designed and taught to bring machine learning methods to petroleum engineering and geoscience problems, from Python fundamentals to deep learning and physics-informed neural networks, with well-log, seismic and reservoir examples throughout and a capstone project.

Course outline23 lessons

Month 1: Python and data foundations

  1. Course overview and environment setup
  2. Python basics: variables, lists and mathematical operations
  3. NumPy and well-log data
  4. Python essentials and Matplotlib: plotting, control flow and functions
  5. While loops, functions, lambda and exception handling
  6. Pandas and tabular well data: filtering, grouping and LAS files
  7. Advanced Pandas, plotting and multi-track well logs
  8. Introduction to machine learning: the ML workflow and a first model

Month 2: Classical machine learning

  1. Classification: predicting formation type from well logs with decision trees
  2. Model improvement: cross-validation and random forests
  3. Unsupervised learning: clustering and PCA for reservoir zonation
  4. Model optimization: hyperparameter tuning and explainable AI

Month 3: Deep learning

  1. Neural network intuition: from biological neurons to a first network
  2. Deep learning with PyTorch: tensors, autograd and a training loop from scratch
  3. Convolutional neural networks: seismic fault detection
  4. Deeper CNNs: regularization, evaluation metrics and feature maps
  5. Recurrent neural networks: forecasting reservoir pressure
  6. LSTMs: gated memory for time series

Month 4: Scientific ML and capstone

  1. Physics-informed neural networks: the diffusivity equation from scratch
  2. Capstone, part 1: scoping, data and an honest baseline
  3. Capstone, part 2: modeling, error analysis, uncertainty and delivery

Bridge lessons

  1. Git and GitHub fundamentals: version control and an ML portfolio
  2. Git and GitHub collaboration: branches, merge conflicts and teamwork

Student reviews

No reviews yet. If you took ML4PEGs, I would value your feedback.

Write a review
Your rating

Reviews are checked before they are published.

New courses and workshops on AI for science and engineering are in development. Interested in hosting one? Get in touch.

Speaking

Talks and presentations

  • Invited talk

    Laboratory-Constrained Microseismic Imaging of Hydraulic Fractures: From Acoustic Emissions to Fracture Architecture

    EAGE community webinar (geomechanics) · Online