Unpacking the geospatial engineering toolbox – an overview of data science techniques for spatial da
summary
Shows concrete workflows and working outputs: uses GeoPandas, Shapely, QGIS and NetworkX to read, intersect and buffer geometries, extract building footprints with a deep‑learning model, and batch‑process millions of features. Implements a pipe‑maintenance metric (percent built‑over and accessibility via buffering) and a swept‑path generator for electric trucks plus a cell‑based reversal simulator that runs thousands of days. Produces maps, dashboards and optimization inputs; algorithms and simulations are implemented, validated against constraints, and used to inform decisions.
AI-written summary · about
chapters (16)
- 0:00Intro
- 1:52Welcome
- 3:10What is spatial data
- 3:58Why is spatial data important
- 5:30Vector data
- 6:13Tools and algorithms
- 6:39QGIS
- 7:05Geopanders
- 9:13Shipley
- 10:11Search Pipe Maintenance
- 14:55Buffering
- 16:10Difference Buffer API
- 16:56Outputs
- 17:47Problem
- 20:41Solution
- 24:06Traffic modeling
related talks
01mA Practical Introduction to Geospatial Python
29mGeospatial Analysis using Python
26mgeospatial data and analysis is :exploding_head:
50mGeospatial Analysis
26mWho Said Wrangling Geospatial Data at Scale was Easy?
20mCloud Native Patterns for Geospatial Analytics and AI
37mSpatial Data Analysis With Python
41mHow to GIS with Python