Lab 8. Scaling Geospatial Machine Learning: Exploring the Spatial Transferability of RF Models

Описание: Summary
In this tutorial, we explore how to scale geospatial machine learning by testing the spatial transferability of a Random Forest model trained in Bulawayo, Zimbabwe, on satellite imagery from Gweru. You'll learn how to apply a pre-trained model using Sentinel-2 and ALOS PALSAR HV data, generate a new land cover map, and evaluate whether the model generalizes across space.

🔍 What you will learn:

How to apply a Random Forest model to a new region

What spatial transferability means in geospatial ML

The limitations and challenges of transferring models

How to generate and export a land cover classification map

📦 Tools Used: Google Colab • Python • scikit-learn • rasterio • joblib • Sentinel-2 • ALOS PALSAR

Watch now to make your land cover models more scalable and reusable!

Additional Materials:

1. Python Script
https://github.com/ck1972/Geospatial-...

2. Access courses at Ai. Geelabs
https://aigeolabs.com/courses/
https://aigeolabs.com/sign-up/

3. Buy 'Explainable Machine Learning for Geospatial Data Analysis: A Data-Centric Approach' book
https://aigeolabs.com/books/explainab...