This Azavea 10% Time project defines a process for converting big data files to vector tiles and allows a user to identify habitat areas in need of protection.
This Azavea 10% Time project defines a process for converting big data files to vector tiles and allows a user to identify habitat areas in need of protection.
Earlier this month, we presented, exhibited, and attended talks at FOSS4G NA in St. Louis. Read our recap of events and view the slides from our presentations.
The Open Civic Data Standards ebook outlines the status of open data standards in several civic domains and lists domains where there is strong potential for developing or defining new open data standards.
This high level analysis joins newly released open data with Police Districts to create a map of Complaints Against Philadelphia Police from 2013 to 2017.
Learn about our methods and results leveraging our RasterVision deep learning project to predict land use in satellite images of the Amazon.
We used GeoPySpark, Python binding for GeoTrellis, to analyze climate change data and determine Arizona airports at risk for excessive heat days.
Volunteer your lunch break for #HOTLunch to map features that NGOs use to plan aid efforts in response to natural disasters and humanitarian crises.
Which buildings should inspectors prioritize? We used machine learning models to predict building code compliance and address resource allocation questions.
In part 1 of our series on Azavea’s redistricting and gerrymandering work, we look at the history of our involvement in this space and what we’re currently working on. Gerrymandering, compactness, contiguity, the efficiency gap. These are the kinds of words that make a lot of redistricting nerds excited these days. Rarely does the application…
This post describes how to use deep learning to do semantic segmentation on aerial and satellite imagery, experiments on the ISPRS Potsdam dataset, and how to visualize model predictions on a map.