Associate Professor Takashi Miyamoto of the University of Yamanashi Graduate School of Comprehensive Science has developed AI (artificial intelligence) technology that analyzes the surface-photographed images of artificial satellites and digital data of urban structures to immediately grasp the damage caused by a large earthquake.Not only will it save lives and speed up reconstruction, but it is also expected to be applied to various natural disasters such as floods and landslides.
According to the University of Yamanashi, the new technology can detect the collapse of a building with higher accuracy than the conventional image processing technology by comparing the ground surface images taken from artificial satellites before and after the big earthquake.In addition, we will utilize technology that extracts information on building age and building materials that are closely related to building damage during an earthquake from digital city data that is being developed nationwide, and combines it with satellite image processing results to improve accuracy. I'm raising it.When the new technology was applied to the damage data of the 2016 Kumamoto earthquake, we succeeded in detecting the buildings collapsed by the earthquake with a high accuracy of 90% or more.
Until now, local governments and police have been collecting information with a great deal of manpower in the event of a major earthquake, and it has taken a considerable amount of time to grasp the actual situation.By utilizing this technology, it is possible to grasp the damage situation in a short time and to devote the personnel of information gathering to saving lives.By applying this technology to natural disasters other than earthquakes such as floods and landslides, it seems that it can be used to grasp the actual situation of damage and speed up lifesaving.