Analyzing satellite image collections on public cloud platforms with R
Tutorial at CONAE spring school 2022
Overview
This tutorial demonstrates how to access and process satellite image collections on cloud computing platforms using R and modern cloud-native tools including SpatioTemporal Asset Catalogs, cloud optimized GeoTIFFs, and on-demand data cubes. After a quick introduction and overview of corresponding R packages, practical examples on image compositing, time series analysis, and the extraction of training data for machine learning models will be presented in a live demonstration. The tutorial will end with a discussion of limitations and future developments in R. Materials and further information will be published at https://github.com/appelmar/CONAE_2022.
Contents
- Introduction
- The cloud
- Satellite imagery on cloud platforms
- Cloud-native technologies: STAC, COGs, data cubes
- R ecosystem for analyzing satellite imagery
- The gdalcubes R package
- Hands-on examples
- Computing cloud-free mosaic images from Sentinel-2 images
- Time series analysis (trend, changes) using MODIS image time series
- Extraction of training data for ML applications from Sentinel-2 images
- Discussion