Scenario Analysis using Global Climate Models
summary
Quantifies annual, asset-level climate risk from 2020–2100 using ensembles from CMIP6 and scenario pathways SSP5-8.5 and SSP2-4.5, mapping wildfire, inland flood and heat-wave hazards to individual asset coordinates. Uses MODIS fire detections to validate models (Pacific Northwest 2020 cumulative detections ~2x 2018), projects ~3.3% burnt-area per-cell in parts of Southern California, shows rapid future fire increase in Alaska, and flags high flood probability for specific mine sites in Mali and Gabon via spatial joins and probabilistic exposure metrics.
AI-written summary · about
chapters (15)
- 0:00Introduction
- 2:28Agenda
- 3:14Climate Landscape
- 4:41Data Components
- 6:19Scenarios
- 7:26Historical Perspective
- 10:13Climate Research
- 13:51Fire Detection Graph
- 16:05Fire Projections
- 18:04Flooding
- 18:31Max Flood Exposure
- 19:03Mining Sites
- 22:08Global vs Asset Level
- 23:19Temporal Uncertainty
- 24:23Conclusion
related talks
09mGen AI Workflows for Climate Risk Modeling in Food Systems
49mModeling our future: Advancing climate research with AI
32mPredicting Grid Faults Before They Happen: AI for Weather-Driven Grid Resilience
11mEnhancing Coastal Resilience with AI
22mLet's Terminate Climate Change with AI
48mTaking the planet’s pulse: AI to empower adaptation to global change
31mAI-supported transformation of the urban infrastructure
42mWITNESS: A "What if?" Tool for Exploring Policy Options and Climate Change