Available for Licensing: Machine Learning-Enhanced Spectroscopy Technology for High-Resolution Radiation Detection Using Low-Cost Detectors

The Idaho National Laboratory (INL) is offering a machine learning-enhanced spectroscopy technology for licensing and commercialization. This technology enables high-energy-resolution radiation spectroscopy using low-cost, room-temperature detectors such as sodium iodide (NaI) scintillators. The technology applies a compact convolutional neural network (CNN) architecture to reconstruct high-energy-resolution spectra from low-resolution measurements. The key advantages of this technology include cost reduction, operational simplicity, higher throughput, improved deployability, and cross-technology applicability. The potential market applications of this technology include nuclear materials monitoring and safeguards, space-based radiation detection, industrial quality control and non-destructive testing, medical and environmental radiation monitoring, and homeland security and defense. • The technology uses a convolutional neural network to reconstruct high-resolution spectra from low-resolution detector inputs. • The compact, deployable model allows rapid inference on low-power devices. • The detector-agnostic implementation can be adapted for gamma, x-ray, neutron, or charged-particle spectroscopy. • The technology offers a cost reduction of at least 10 times lower system cost and maintenance. • The technology eliminates the need for liquid nitrogen or cryogenic cooling systems. • The technology supports higher count rates with minimal peak deformation. • The technology is suitable for remote, field, and mobile environments where HPGe is impractical.