Scalable Remote Sensing Workflows with Xarray Workshop
11-17, 13:30–16:30 (Pacific/Auckland), WF502

XArray is a powerful Python package for working with climate and earth observation datasets. This workshop will be a structured introduction to XArray, STAC and Dask with use-cases focused on cloud-based remote sensing applications.


Xarray is an evolution of rasterio and is inspired by libraries like pandas to work with raster datasets. It is particularly suited for working with multi-dimensional time-series raster datasets. With the growing ecosystem of spatial extensions like rioxarray and xarray-spatial and built-in support for parallel computing with Dask, it has become the de-facto standard for working with large spatio-temporal raster datasets. This workshop will show you a modern scalable approach to remote sensing with cloud-native datasets and parallel computation..

  1. Basics of XArray
  2. Basics of STAC and Dask
  3. Computation with XArray
  4. Cloud Masking
  5. Extracting Time-Series
  6. Calculating Zonal Statistics

Pre-requisites:
- This is an intermediate-level workshop where familiarity with Python is useful but beginners are welcome too.
- We will be using Google Colab as the computing environment for the workshop. Participants will need a Google Account to access the platform.

Ujaval is the founder of Spatial Thoughts - a learning platform for modern geospatial technologies. Ujaval got his Masters in Geospatial Information Engineering from the University of Wisconsin-Madison. After joining Google Inc. in California, he moved to India in 2006. He was one of the early employees at Google India and part of the team that launched Google Maps for India. He worked on multiple Geo teams at Google and led the GIS team in India.

After 15 years of corporate experience, he left Google in 2020 to work on his startup - Spatial Thoughts - to create a learning platform to bridge the skill gap in the geospatial industry. His online academy has trained participants from over 100 countries. His learning materials on QGIS, Python, Earth Engine, and GDAL are cited as the top learning resources globally and are used by more than 1 million people every year.

Ujaval is a world-renowned training facilitator and is passionate about advancing the use of open-source technologies in teaching and research. He is an active QGIS community contributor and a QGIS.org certified training provider.

This speaker also appears in: