Hurricane Ian left an extremely wide path of devastation through most of southern Florida. This was evident in reports from Earth, but it was also shown in satellite data. Use new wayour team of spatial and environmental analysts were able to provide a rare view of the big picture of damage across the state.
using satellite images By the storm and real-time images from four satellite sensors, plus Artificial intelligence، We built a disaster monitoring system that can map damage to Accuracy 30 meters Continuously updating the data.
It’s a snapshot of what faster, more targeted disaster monitoring could look like in the future — and something that could eventually be deployed nationwide.
How does artificial intelligence detect damage?
Satellites are already used Identification of high-risk areas For floods, wildfires, landslides and other disasters, determine the damage after these disasters. But most satellite-based disaster management approaches rely on visual assessment of the latest images, every neighborhood at a time.
Our technology automatically compares pre-storm imagery with current satellite imagery with Detect anomalies quickly in large areas. These anomalies could be sand or water where those sand or water shouldn’t be, or badly damaged roofs that didn’t fit their pre-storm appearance. Each area with significant anomalies is highlighted in yellow.
Five days after Ian struck Florida, the map showed yellow alert polygons throughout southern Florida. We found that it can detect spots of damage with up to 84% accuracy.
Natural disasters such as a hurricane or typhoon are often left big fields of spectral change On the surface, this means changes in how light is reflected on whatever is on it, such as homes, land or water. Our algorithm compares the reflection in models based on pre-storm images with the reflection after the storm.
The system monitors both changes in the physical properties of natural areas, such as changes in wetness or brightness, and the overall intensity of the change. that Brightness increase It is often associated with exposed sand or bare ground due to hurricane damage.
using a machine learning model, we can use these images to predict disruption probability, which measures the effects of natural disasters on Earth’s surfaces. This approach allows us to automate disaster mapping and provide complete coverage of an entire situation with just satellite data release him.
The system uses data from four satellites, Landsat 8 And the Landsat 9both operated by NASA and the US Geological Survey, and Sentinel 2A and Sentinel 2Blaunched as part of the European Commission’s Copernicus programme.
Real-time monitoring, nationwide
Severe storms with devastating floods have been documented with increasing frequency over large parts of the world in recent years.
While disaster response teams can rely on monitoring aircraft and drones to identify damage in small areas, it is very difficult to see the big picture in a large-scale disaster such as hurricanes and others. tropical cyclonesAnd time is of the essence. Our system provides a quick approach using free government-produced images to see the big picture. One current drawback is the timing of those images, which are often not made public until a few days after the disaster.
We are now developing near real-time monitoring of the entire contiguous United States to quickly provide up-to-date land information for the next natural disaster.
the quote: AI satellite mapping can quickly identify tornado damage across the state to determine where people might be trapped (2022, Oct 10), retrieved Oct 10, 2022 from https://phys.org/news/ 2022-10-ai-satellite-quickly-hurricane-whole.html
This document is subject to copyright. Notwithstanding any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.