Applied Machine Learning for Geoscientists

Machine Learning
By OgbonLab

Python, models, and the subsurface, all in one course you can run end-to-end.

Machine learning fundamentals applied to Earth and subsurface data, from Python basics through deep learning.

16 parts 46 sections Free, browser-native
Start reading → First up: Why ML for Geoscience? Problem Framing and Inference

Table of contents

Every section is a working session: text, math, code, interactive widgets. Click any title to jump in.

Part 1: Chapter 1: Welcome, ML for Earth and Subsurface Data

  1. Why ML for Geoscience? Problem Framing and Inference
  2. Workshop: Setting Up Your Python Environment
  3. Chapter 1 Quiz: Introduction to ML in Geosciences

Part 2: Chapter 2: Statistical Foundations for ML

  1. Background Statistics
  2. Statistics Practice with Python
  3. Chapter 4 Quiz: Background Statistics

Part 3: Chapter 3: Numerical Optimization for Learning

  1. Gradient Descent and Sampling Strategies
  2. Workshop: Implementing Gradient Descent from Scratch
  3. Chapter 3 Quiz: Optimization Methods

Part 4: Chapter 4: Linear Models, Regression and Classification

  1. Linear and Logistic Regression
  2. Regression Practice with Python
  3. Chapter 5 Quiz: Linear & Logistic Regression

Part 5: Chapter 5: Distance-Based Learning, K-Nearest Neighbors

  1. Nearest Neighbor and KNN
  2. KNN with Geoscience Data
  3. Chapter 7 Quiz: K-Nearest Neighbors

Part 6: Chapter 6: Probabilistic Classification, Naive Bayes

  1. Naive Bayes
  2. Naive Bayes Practice
  3. Chapter 13 Quiz: Naive Bayes

Part 7: Chapter 7: Tree-Based Models I, Decision Trees

  1. Decision Trees
  2. Decision Tree Practice with Python
  3. Chapter 8 Quiz: Decision Trees

Part 8: Chapter 8: Tree-Based Models II, Random Forests

  1. Random Forest
  2. Random Forest Practice
  3. Chapter 9 Quiz: Random Forest

Part 9: Chapter 9: Engineering Features from Geoscience Data

  1. Feature Engineering
  2. Feature Engineering Practice
  3. Chapter 10 Quiz: Feature Engineering

Part 10: Chapter 10: Generalization, Bias, and Variance

  1. Overfitting, Underfitting, Variance, and Bias
  2. Chapter 11 Quiz: Overfitting & Bias-Variance Tradeoff

Part 11: Chapter 11: Reducing Dimensions, PCA and Beyond

  1. Dimensionality Reduction
  2. Dimensionality Reduction Practice
  3. Chapter 12 Quiz: Dimensionality Reduction

Part 12: Chapter 12: Big Data Pipelines in Earth Science

  1. From Sensors to Petabytes: The Geoscience Data Pipeline
  2. Workshop: Working with NumPy, Pandas, and Matplotlib
  3. Chapter 2 Quiz: Big Data & ML Overview

Part 13: Chapter 13: From Perceptrons to Deep Networks

  1. Perceptrons and Neurons: A Simple NN Model
  2. Building a Simple Neural Network
  3. Chapter 6 Quiz: Perceptrons & Neural Networks

Part 14: Chapter 14: Convolutional Networks for Spatial Data

  1. Deep Learning: Convolutional Neural Networks
  2. CNN Practice
  3. Chapter 14 Quiz: Convolutional Neural Networks

Part 15: Chapter 15: Recurrent Networks for Sequential Data

  1. Recurrent Neural Networks
  2. Chapter 16 Quiz: Recurrent Neural Networks

Part 16: Chapter 16: Representation Learning with Auto-encoders

  1. Auto-encoders
  2. Auto-encoder Practice
  3. Chapter 15 Quiz: Auto-encoders

This page is prerendered for SEO and accessibility. The book hydrates on JavaScript load with progress tracking, bookmarks, and the AI tutor.