Geospatial AI: Where Can AI Help to Tackle Today’s Real-World Challenges?
summary
Demonstrates ArcGIS workflows that turn satellite, drone imagery and lidar into actionable outputs: pixel and object classification to detect damaged buildings, tree crowns, parked cars and power‑line vegetation; time‑series interferometry showing subsidence over an open‑pit mine and outlier detection flagging a bridge uplift; fusion with truck, weather and sensor feeds into a digital twin; pre‑trained models (tree detection, land‑cover) plus an Earth Intelligence pipeline and an ArcGIS assistant that generates Arcade code from prompts and an agent that auto‑runs spatial analyses.
AI-written summary · about
chapters (8)
- 0:00Geospatial AI introduction
- 2:14Data to AI analysis & prediction
- 5:26Earth Intelligence with sensors
- 8:12GeoAI for different data types
- 10:59AI in GIS workflows
- 13:46Future of AI agents & NLP
- 15:10AI framework & trusted principles
- 17:15Closing remarks
related talks
27mAI and Geospatial Analysis. What has changed?
28mGeoAI: Evolution of AI-Based Tree/Vegetation Detection Models Using Imagery
11mTerraKit: Standardising AI-Ready Geospatial Data...
46mData Discussion - AI for Good
22mSpatial Analysis and the Geoweb
31mUnpacking the geospatial engineering toolbox – an overview of data science techniques for spatial da
50mGeospatial Analysis
19mHow we leverage AI to build great maps at massive scale