Open Geospatial and Big Data for Airspace Risk Analysis
summary
The Airspace Risk Modelling System combines CASA operational data with open-source geospatial Python to quantify mid-air collision risk: a SQL Server backend, a Python risk engine, and an Angular UI process ~2.6M flights (2022) across five years — about 7 billion rows (~750 GB). Trajectories are interpolated, vectorized, reduced by PCA + DBSCAN clustering, and paired by intersection/parallel criteria; risk uses probabilistic spatial–temporal overlap calculations. Runs take ~30s–20min (Sydney ~2min). Planned extensions add drones/balloons/rockets and a move toward a data lake architecture.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 1:39Risk
- 3:10Data
- 6:53Example
- 8:37Assessment
- 8:57Grouping
- 9:09Clustering
- 11:06Outliers
- 13:07Risk Formula
- 13:57Summary Screen
- 15:51Lessons Learned
- 18:41Whats Next
- 19:32Questions
related talks
30mUnlocking Geospatial Data Science: A Strategic Overview
32mUsing spatial data to model biodiversity
15mOpen Source Spatial Tools for Biodiversity and Environmental Data...
20mTurbulence Ahead - A 3D Web-Based Aviation Weather Visualizer
37mJoin this live flight tracking demonstration on event enabling API's
15mThe turf wars on data - can be a matter of life and death
24mBuilding Aggregated Solutions to Scale Your Geospatial Strategies
33mBuilding Data Science Tools for Sustainable Transformation