Course

GeoAI with Python

A Practical Guide to Open-Source Geospatial AI

This course is currently being developed. Stay tuned for new lessons and updates.

Description

Geospatial data is being generated faster than ever, from satellites, drones, and sensors mapping our planet every day. GeoAI with Python teaches you how to turn that flood of imagery into actionable insight using modern artificial intelligence.

In this hands-on, code-first course, you will learn to apply deep learning to real-world Earth observation problems. Starting from the Python geospatial foundations, you will progress through data acquisition and preparation, then build and train models for the core AI tasks that power today's remote sensing applications: image classification, semantic and instance segmentation, object detection, and change detection. Finally, you will harness cutting-edge geospatial foundation models and learn to use QGIS plugins that put AI directly into your everyday GIS workflows.

Every concept is taught through executable Python notebooks and open-source tools, so you are always building, not just watching. By the end, you will be able to acquire and prepare geospatial datasets, train and evaluate your own models, and integrate AI into practical geospatial workflows.

What you will learn

Set up a modern Python environment for geospatial deep learning
Access and preprocess satellite and aerial imagery for AI models
Train models for classification, segmentation, and object detection
Apply foundation models to segment and analyze remote sensing data
Use QGIS plugins that bring AI-powered geospatial analysis to end users

Who this course is for

GIS analysts, remote sensing specialists, data scientists, researchers, and students who know some Python and want to add deep learning and AI to their geospatial toolkit. No prior machine-learning experience required.

This course is the video companion to the book "GeoAI with Python" by Qiusheng Wu.

Course outline

Part I. Foundations

Section 1. Introduction to GeoAI
Section 2. Setting Up Your Environment
Section 3. Geospatial Data Essentials

Part II. Data Acquisition and Preparation

Section 4. Downloading Remote Sensing Data
Section 5. Interactive Mapping and Visualization
Section 6. Preparing Training Data

Part III. Core AI Tasks

Section 7. Image Recognition
Section 8. Object Detection
Section 9. Semantic Segmentation
Section 10. Instance Segmentation
Section 11. Image Translation
Section 12. Change Detection
Section 13. Pixel-Level Regression

Part IV. Foundation Models and Satellite Embeddings

Section 14. SAM for Geospatial Applications
Section 15. Vision-Language Models
Section 16. Satellite Embeddings

Part V. QGIS Plugins

Section 17. Setting Up the GeoAI QGIS Plugin
Section 18. Tree Segmentation in QGIS
Section 19. Water Segmentation in QGIS
Section 20. Vision-Language Models in QGIS
Section 21. Segment Anything in QGIS
Section 22. Semantic Segmentation in QGIS
Section 23. Instance Segmentation in QGIS

Curriculum · 17 lessons · 4:39:28