DOE OSTI · 1782779
Regressing Nuclear Reactor Power Level Using Low-Cost Sensor Network Data
Abstract
Multisensor networks deployed at nuclear facilities can be leveraged to collect data used as inputs to machine learning models predicting nuclear safeguard relevant information. This work demonstrates an application of this idea by regressing nuclear reactor power levels, a key indicator for nuclear safeguard verification, at the McClellan Nuclear Research Center using data collected by five Merlyn multisensor platforms with LASSO and LSTM models. This work also demonstrates the use of Leave One Node Out to measure the importance of each multisensor for this regression problem providing insight into model explainability and allowing inferential hypotheses about the nuclear facility to be made. This work can be used as a starting point for future development of methods for regression on reactor power levels at nuclear facilities using multisensor network data.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Tibbetts, Jake M.. 2021-05-13. Regressing Nuclear Reactor Power Level Using Low-Cost Sensor Network Data. https://doi.org/10.2172/1782779. https://searchnasa.com/record/osti%3A1782779/regressing-nuclear-reactor-power-level-using-low-cost-sensor-network-data
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.