AI System Identifies Buildings Damaged by Wildfire
AI System Identifies Buildings Damaged by Wildfire
U.S. researchers developed an AI system that helps classifying buildings with wildfire damage by relying solely on post-fire images with 92% accuracy.
Wildfires are increasing in frequency and intensity as climate change becomes more pronounced and visible. These are now causing disruptions in urban areas people left homes and their lives behind. Now, they will have to wait anxiously to know the state of their homes and the damage that they will need to fix.
Researchers at Stanford University and the California Polytechnic State University (Cal Poly) have developed an Artificial Intelligence (AI) algorithm system called DamageMap that is a damage classifier; it helps identify building damages within minutes of a catastrophe by studying aerial photographs. Instead of comparing before-and-after photos, they’ve trained a program using machine learning to rely solely on post-fire images.
We wanted to automate the process and make it much faster for first responders or even for citizens that might want to know what happened to their house after a wildfire. Our model results are on par with human accuracy.
– Lead study author
Previous systems would need pre-and-post damage photos and run a comparative test between the two. This has restricted rapid assessments since the system requires data from the same satellite, camera angle, and lighting conditions, which many-a-times would be either impossible or time-consuming.
However, unlike previous systems that did comparative analyses between pre-and-post-fire photographs, the AI system is a trained program that uses machine learning to study post-fire images so, it can adapt to sifting through unseen data. The researchers tested it using a variety of satellite, aerial and drone photography with at least 92% accuracy.
People can tell if a building is damaged or not without the before picture, so the researchers tested that hypothesis with machine learning. This can be a powerful tool for rapidly assessing damage and planning disaster recovery efforts.
Structural damage from wildfires in California is typically divided into four categories: almost no damage, minor damage, major damage or destroyed. Because the AI system is based on aerial images, the researchers quickly realised the system could not make assessments to that degree of detail and trained the machine to simply determine if fire damage was present or absent.
U.S. researchers developed an AI system that helps classifying buildings with wildfire damage by relying solely on post-fire images with 92% accuracy.
Wildfires are increasing in frequency and intensity as climate change becomes more pronounced and visible. These are now causing disruptions in urban areas people left homes and their lives behind. Now, they will have to wait anxiously to know the state of their homes and the damage that they will need to fix.
Researchers at Stanford University and the California Polytechnic State University (Cal Poly) have developed an Artificial Intelligence (AI) algorithm system called DamageMap that is a damage classifier; it helps identify building damages within minutes of a catastrophe by studying aerial photographs. Instead of comparing before-and-after photos, they’ve trained a program using machine learning to rely solely on post-fire images.
We wanted to automate the process and make it much faster for first responders or even for citizens that might want to know what happened to their house after a wildfire. Our model results are on par with human accuracy.
– Lead study author
Previous systems would need pre-and-post damage photos and run a comparative test between the two. This has restricted rapid assessments since the system requires data from the same satellite, camera angle, and lighting conditions, which many-a-times would be either impossible or time-consuming.
However, unlike previous systems that did comparative analyses between pre-and-post-fire photographs, the AI system is a trained program that uses machine learning to study post-fire images so, it can adapt to sifting through unseen data. The researchers tested it using a variety of satellite, aerial and drone photography with at least 92% accuracy.
People can tell if a building is damaged or not without the before picture, so the researchers tested that hypothesis with machine learning. This can be a powerful tool for rapidly assessing damage and planning disaster recovery efforts.
Structural damage from wildfires in California is typically divided into four categories: almost no damage, minor damage, major damage or destroyed. Because the AI system is based on aerial images, the researchers quickly realised the system could not make assessments to that degree of detail and trained the machine to simply determine if fire damage was present or absent.
opengovasia.com
