Muons are produced by the decay of cosmic rays showering down onto Earth. The way they deflect after they pass through material indicates the density of the material. Detectors using muon radiography are potentially more sensitive than x-ray detectors and do not have the radiation risks.
Scientists from Los Alamos National Laboratory in Los Alamos, N. Mex., are now developing a prototype detector. By analyzing changes in energy and trajectory of the muons, scientists can build a three-dimensional mathematical map of dense items in the cargo.
"We've shown we can put the data through a machine-learning algorithm and train the system to spot objects of interest with a rate of false positives and false negatives that is less than 3 percent," said team member Rick Chartrand. "We think we can continue to improve that."
The research was presented Monday in Washington during the annual meeting of the American Association for the Advancement of Science.