Happy New Year w/ Shapely, Rasterio and Percy!

Happy New Year PDXOSGeo! Join us on fourth Wednesday to hear from David Percy, aka “Percy”, one of the founders of our group :) Percy has been doing research on applying Reconstructability Analysis (RA) to categorical raster datasets since 2012, and is preparing to defend his dissertation on Spatial Reconstructability Analysis soon.

RA is a form of machine learning that works exclusively with discrete data, so categorical data such as the National Land Cover Database is a perfect source of data for it. Come hear how Percy analyzed NLCD data in attempts to predict forest dynamics (clearcuts), and wildfire size, specifically looking at how historical vegetation affects these outcomes. Results will be presented that show how these data are useful in modeling future events.

All of the extraction for analysis was done in Python using open source GIS libraries Shapely and Rasterio. Code will be shared and discussed!