Brought to you by NumFOCUS Foundation and O’Reilly Media
The official Jupyter Conference
Aug 21-22, 2018: Training
Aug 22-24, 2018: Tutorials & Conference
New York, NY

How JupyterLab and widgets enable interactive analysis of the Earth's past, present, and future

Tyler Erickson (Google)
11:55am–12:35pm Friday, August 24, 2018

Who is this presentation for?

  • Scientific programmers, data analysts, data journalists, and other concerned residents of Planet Earth

Prerequisite knowledge

  • A basic undertanding of Python and the Jupyter ecosystem
  • Familiarity with Earth science and geospatial datasets (useful but not required)

What you'll learn

  • Learn how to use JupyterLab to access remote terabyte- to petabyte-scale geospatial analysis platforms and how to utilize combinations of Jupyter widgets to interactively explore multidimensional data


The Earth is rapidly changing, and this change has numerous important environmental and societal impacts. There is a strong need to understand these changes at a global scale in high resolution so that we might reverse or adapt to them.

Access to public Earth observation and model data is exploding, driven by recent satellite launches by government, intergovernmental agencies, and private organizations as well as Earth system model simulations run by institutions around the world. Given this deluge of data, the old paradigm of downloading raw data for local processing is highly limiting. New approaches are needed. To address this, many organizations are building cloud- or HPC-based platforms that allow filtering, aggregation, and complex processing prior to transferring data to users. Jupyter Project technologies are increasingly useful for providing access to these large Earth science data stores and analysis platforms.

Tyler Erickson highlights the use of JupyterLab and Jupyter widgets in analyzing complex high-dimensional datasets, providing insights into how our Earth is changing and what the future might look like.

Topics include:

  • Trends in adoption of Jupyter technologies at Earth science conferences data and by Earth science data and information providers
  • How to combine multiple Jupyter widgets in JupyterLab to interactively explore and analyze high-dimensional data stored on remote platforms
  • Case studies of using Jupyter widgets for Earth science data analysis, such as analyzing land-cover change models and exploring projections of future climate conditions

While the case studies will use Google’s Earth Engine platform, the techniques demonstrated are applicable to most remote geospatial platforms that provide API access.

Photo of Tyler Erickson

Tyler Erickson


Tyler A. Erickson is a senior developer advocate at Google, where he fosters collaborations with researchers from academia, NGOs, and governmental organizations seeking to capitalize on Earth Engine’s capabilities for geospatial analyses that involve immense satellite and model-based datasets. Tyler leads the development of Earth Engine’s core efforts in water and climate, guides the evolution of Earth Engine to support these scientific domains, and leads support efforts for the Earth Engine Python API. A snow hydrologist by training, he holds degrees in civil and environmental engineering and geography from Colorado State University, CalTech, Stanford, and the University of Colorado at Boulder. Tyler is a longtime Python programmer, with contributions to the Open Source Geospatial (OSGeo) Foundation and the Free and Open Source Software for Geospatial (FOSS4G) conferences.

Comments on this page are now closed.


Picture of Tyler Erickson
09/28/2018 11:26am EDT

The presentation video is now available:

Juan Ramirez | DATA ANALYST
09/10/2018 7:05am EDT

Hi, can the presentation and/or video for this talk be shared?