Artificial Intelligence Accurately Predicts Distribution of Radioactive Fallout
View list of research
View list of research
Artificial Intelligence Accurately Predicts Distribution of Radioactive Fallout
Artificial Intelligence Accurately Predicts Distribution of Radioactive Fallout
The white shaded area shows the hourly atmospheric concentration of 131I in the simulations using the estimated emission condition from 11 to 31 in March 2011.
Researchers at the University of Tokyo Institute of Industrial Science created a machine-learning-based tool that can predict where radioactive emissions from nuclear power plants will disperse. After training using extensive data on previous weather patterns, the tool consistently achieved over 85% predictive accuracy, and up to 95% in winter when large and predictable weather systems dominate. This tool can aid immediate evacuation in the aftermath of disasters like those at Fukushima and Chernobyl.
Related Articles
