Machine learning models trained on simulated gamma peak ratios achieve over 95% accuracy classifying yields near a 1 kg TNT threshold and 12.4% mean absolute relative error in yield regression for measurements taken months after the test.
For each threshold, the model was only trained and tested on a local yield window spanning one order of magnitude on both sides of the threshold (e.g
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.ins-det 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Machine learning inference of fission yields from gamma spectroscopy for very low-yield nuclear test verification
Machine learning models trained on simulated gamma peak ratios achieve over 95% accuracy classifying yields near a 1 kg TNT threshold and 12.4% mean absolute relative error in yield regression for measurements taken months after the test.