Public Sector
❯
Disaster and Emergency
❯Disaster and Emergency Prediction & Impact Model
Disaster and Emergency Prediction & Impact Model
For:
National-level disaster management professionals, Climate change adaptation experts, Government agencies, At-risk communities
System for real-time earthquake simulation with data assimilation
For:
Information Technology Centre (ITC), The University of Tokyo
Earthquake Research Institute (ERI), The University of Tokyo
National Institute of Informatics (NII)
National Research Institute for Earth Science and Disaster Resilience (NIED)
Japan Meteorological Agency (JMA), Meteorological Research Institute (MRI)
Local Governments in Japan
Transportation Companies (railway, highway)
Scope:
This system provides accurate information for evacuation in an earthquake
disaster.
Goal:
Other
Disaster and Emergency Prediction & Impact Model
For:
National-level disaster management professionals, Climate change adaptation experts, Government agencies, At-risk communities.
Disaster and Emergency Prediction & Impact Model
For:
National-level disaster management professionals, Climate change adaptation experts, Government agencies, At-risk communities
Problem addressed
Whenever a natural disaster like a flood or a heat wave occurs, warnings and other risk-related information might be imprecise or out of date. Most of the risk-related information currently floats on a macro-level, covering hundreds of square meters, and is too complex for at-risk people to comprehend.
It was necessary to localize the risk data to a neighborhood level to support the development of long-term resilience in the communities that are most at risk. Their extensive experience reacting to many emergencies and disasters on the ground must be automated, scaled, and coded using a solution.
Description
A cutting-edge model blending AI and machine learning capabilities is developed to plan and react to disasters more successfully. This model forecasts hyper-local risk information for early warnings and intervention using historical data and satellite photos.
The basic tenet of the approach is that a house's roofing can serve as a stand-in for its socioeconomic status. Therefore, the adapting and recovering capacities of a family residing in a sizable concrete home and a family living in a temporary metal sheet home would be different.
The effects of the destruction brought on by a disaster are noticeably different for each of these dwellings when two of them are present in the same region. The backbone of this AI system is the mapping of this roof material data on satellite imagery and other spatial factors.
The solution generates hyper-localized risk data that can be used by various stakeholders in disaster response. These stakeholders include experts in climate change adaptation, government agencies, and communities at risk on a national scale. It provides people with precise instructions on how to protect their homes, pets, livelihood, and possessions.
The solution's scalability is another plus. It can respond to a variety of disasters, including earthquakes, heat waves, and floods.
Image
AI: Perceive
Machine Learning
AI: Understand
Predict / Forecast
AI: Act