Saving Lives with Predictive Geo - AI
- Liffey Hall 2
- Start (Dublin time):
- Start (your time):
- 30 minutes
Leveraging geospatial Python libraries to understand and predict High-risk houses during cyclone-induced floods in urban areas considering historical openly available satellite images and urban morphological data.
Assigning a flood risk score to each individual house near the coastal regions is a challenge. Also, as the land characteristics vary based on different geographical locations, prepare for emergencies on demand.
TalkPyData: Machine Learning, Stats
We will demonstrate an end-to-end methodology using geospatial Python libraries to understand the use of Multi-Criteria Decision making methods taking into account driving variables. This talk will also throw light upon:
- Getting the large imagery datasets into DL friendly format
- Resampling of Satellite image data in python
- Conducting overlay analysis with weights
- Calculation of zonal statistics at house level
- Future Scope
We'll also showcase the geo-visualization portal we created and the technologies used, how you can use Python to convert large GeoJSON output to light vector tiles, and create a seamless experience for the user through an intuitive front-end.