Enhancing Coastal Resilience with AI
summary
Stantec expands Flood Predictor to coastal flood hazards, trained on decades of physics‑model outputs and four years of development, claiming near real‑time runs versus 20‑minute supercomputer jobs from 2004. The pipeline runs on Azure using Azure Data Factory, DevOps, Databricks, GPU clusters and MLflow for reproducibility, combining regression, time‑series and computer‑vision inputs. The system produces flood extents, probabilities and rapid what‑if scenarios for emergency logistics, planning and lower‑cost access for smaller communities.
AI-written summary · about
chapters (5)
- 0:00Coastal resilience AI project
- 1:37AI versus traditional models
- 3:51Real-time flood prediction
- 7:47Model complexity in storms
- 9:54Call to action
related talks
07mAI-Powered Risk Management
46mCombatting illegal fishing with Machine Learning and Azure
09mGen AI Workflows for Climate Risk Modeling in Food Systems
32mPredicting Grid Faults Before They Happen: AI for Weather-Driven Grid Resilience
01h 01mStreams, lakes and oceans – working with on big data with Azure ML
23mBuilding AI-Driven Real-Time Lakehouse APIs
28mReal Time Sensor Anomaly Detection with Sci Kit Learn and the Azure Stack
29mAI-Powered Anomaly Detection in Cloud Data Pipelines