After working through the previous modules of this tutorial, you should have a basic understanding of how to access, analyze and visualize satellite data. One of the best ways to improve your skills with data science and remote sensing, as with many things, is through hands-on examples.
1.1. Economic activity in Nepal¶
This module presents an approach for assessing change in built-up land cover in Nepal. In addition to using fundamental techniques introduced in the previous tutorial modules, participants will be exposed to two new concepts in the remote sensing domain: data integration (sometimes called data fusion) and image classification.
Topics and activities include:
Framing the analysis: Designing analysis to provide meaningful insight into economic activity.
Supervised learning and image classification: Intro to basic concepts of a powerful machine learning approach.
Intro to Sentinel-2: Intro to high-resolution daytime imagery for land monitoring.
Intro to Global Human Settlement Layer: Intro to a settlement dataset to use as training labels.
Data fusion: Sentinel-2, VIIRS-DNB, GHSL: Integrating remote sensing data with other geospatial data.
Random Forest Classifier: Application of supervised learning to classify built-up land cover.
Statistical inference: Inference and analysis on change detection.