All Tutorial Notebooks

This notebook is the third in a series of beginner tutorial to introduce news users to Jupyter Notebooks, working with satellite imagery and performing basic analytics. Specifically this notebook introduces the concepts of multispectral bands found in satellite imagery and how they can be used for analytics using "band math".
In this GBDX Notebook, we demonstrate how a combination of DigitalGlobe products can be used to start mapping the airspace for drones and unmanned aerial vehicles (UAVs) in urban environments.
Rechunking PDAP images for input into Tensorflow
A notebook that shows how to histogram match RDA imagery that is native to GBDX Notebooks to DigitalGlobe's Maps API using rio_hist. This method will help provide consistent color balanced imagery that is aesthetically pleasing for viewing.
This Notebook demonstrates a workflow to detect the installation of temporary blue roofing following Hurricane Maria in Puerto Rico. We then apply that workflow over neighborhoods in multiple towns, and review and interpret the results.
In the previous Notebook, we walked through how to deploy our coastline extraction algorithm as a GBDX Task, enabling us to run it on the GBDX platform instead of inside of our Notebook. In this final Notebook, we are going to use the GBDX Task we created to run coastline extraction over multiple images, in parallel, using GBDX Workflows. Using this approach, we'll be able to extract a highly detailed coastline for the entire island of Kauai, in less than 10 minutes.
In the previous Notebook, we demonstrated two different strategies for scaling our coastline extraction algorithm to run over a full image strip. The result was a Python function that we can point at any (coastal) image and efficiently delineate the coastlines, either in downsampled resolution or full resolution. The execution of that function was conducted within our Notebook, which is convenient for hands-on development and testing, but not necessarily ideal for production-level analysis. For example, what if we wanted to run the analysis over multiple strips at the same time? Or set up a recurring job that runs on every new strip that comes in over a given area? Handling production of coastline features from the Notebook in these cases would be relatively cumbersome. At this point in the development process, it's important to consider moving our algorithm from the Notebook environment to the GBDX Platform by deploying it as a GBDX Task. A GBDX Task is simply a stored version of an algorithm (or tool, or methodology, or really any operation) that we can execute on the GBDX Platform. The code itself isn't run locally; instead, it runs as part of a Workflow in the cloud. This means we can execute the same Task against multiple images all at the same time: each will be kicked off as a separate, parallel workflow, without being constrained to the computational limits of a single machine (or GBDX Notebook Kernel). In this Notebook, we provide a walkthrough of how to deploy our coastline extraction algorithm as a GBDX Task, using some helpful tools built right into the GBDX Notebooks interface. We also do a quick test of our new task and review the results to make sure it works.
In this Notebook, we will extend the simple methodology for extracting coastlines that we built in the previous tutorial. Our goal in this Notebook is to be able to run the same methodology over a much bigger geographic area. Specifically, we are going to show two different approaches to running the algorithm over an entire image rather than just one small part of that image, like we used last time.
In this Notebook, we walk through a simple methodology for extracting coastlines from 8-band multispectral imagery. This tutorial demonstrates how to link together several concepts from remote sensing, image science, and GIS to produce a complete geospatial analysis. The steps in the workflow include: (1) calculating a Normalized Difference Water Index; (2) thresholding the water index into a binary image; (3) cleaning up small features; and (4) converting the land/water boundaries into vector polylines representing coastlines. This tutorial is the first in a series that will demonstrate how to progress from prototyping an algorithm in GBDX Notebooks to deploying and running that algorithm at production scale over large geographic regions.
It's easy to think about GBDX and GBDX Notebooks as simply a place to access **imagery** and do **analysis**; however, the true power of these tools lies in their potential to produce new **information** and provide **insight** to specific research questions or business use-cases. This Notebook demonstrates a simple example of how GBDX can enable you to quickly climb the ladder from imagery to insights. To do so, we start by doing some analysis to extract boats from an image, extend that analysis over the historical archive of imagery in the selected location, and then bring in ancillary data to gain insights into the observed variability in boat traffic.
Ecopia Building Footprints powered by Digitalglobe are an off-the-shelf Information Product that are produced by one of DigitalGlobe's Information Partners, Ecopia. In this GBDX Notebook, we explore how products such as GBDX Building Footprints can be combined with the analytical capabilities of GBDX to produce additional data and insights.
In this tutorial we'll cover how to find SWIR imagery and use it for creating a Normalized Difference Built-Up Index for analysis of Central Park in Manhattan. This work includes discussion of the difference between VNIR and SWIR data as well as using downsampling techniques to enable the use of band math on imagery products with different resolutions.
This notebook provides a basic introduction to using Dask with satellite imagery. It covers a brief overview of Dask arrays, chunks and map_blocks to scale out an NDVI analysis for a entire strip of imagery over Sydney, Australia.
This is first time beginner's guide to notebooks. We'll answer questions like 1) what is a notebook? 2) how do you enter and use text and code? 3) how do you manage output from code?
In this GBDX Notebook, we demonstrate the potential for using GBDX and Ecopia Building Footprints to assess the forest fire risk to buildings in Shaver Lake, CA by quantifying the tree coverage in the area around each building.
Exploring ways to leverage DigitalGlobe imagery and OSM data for training ML models
This Notebook illustrates the idea of adjusting the RGB color values of a CatalogImage to match the colors in the "browse" (aka, "thumbnail") version of the same image. Normally, the RGB colors of a CatalogImage that are displayed when the .plot() method is called are produced by an automated algorithm that simply clips out the extreme light and dark colors, and then interpolates the values to the normal 0-255 scale. On the other hand, browse imagery is color adjusted by a human operator at DigitalGlobe, and therefore can be better suited for special conditions (e.g., very dark/shadowy imagery such as when the image was captured at a low sun elevation angle, or very bright imagery, such as a snowy scene). Although browse imagery is much lower spatial resolution than the CatalogImagery, the color values can still be used to produce imagery that is more suitable for some use cases.
Using SWIR data to explore and extract the location of active fires in Southern California.
An example showing how to pass every pixel of an image through a user defined method
This Notebook demonstrates a simple workflow for identifying standing water in an image, extracting and rasterizing roads vectors from OpenStreetMap, and assessing the extent of road flooding.
This notebook is a detailed introduction to ways to access DG imagery via the gbdxtools python package.
This notebooks shows how to work with various types of AOIs for indexing and cropping imagery via gbdxtools.
Animating imagery over time from a list of CatalogIDs
An example of comparing changes in imagery over time in Dubai. This notebook explores ways to collect several images, compute water indices from each, extract vector features, and compare changes to land area over time.
An introduction to various image classes supported by gbdxtools
Learn how to find satellite imagery and pull it in to the GBDX system for display in a notebook.
Exploring training data (Embassies) based on OSM geometries in VectorServices and Imagery in PDAP via RADD
Yo images, whats up!