English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Underground physics experiments such as dark matter direct detection need tokeep control of the background contribution. Hosting these experiments inunderground facilities helps to minimize certain background sources such as thecosmic rays. One of the largest remaining background sources is the radonemanated from the rocks enclosing the research facility. The radon particlescould be deposited inside the detectors when they are opened to perform themaintenance operations. Therefore, forecasting the radon levels is a crucialtask in an attempt to schedule the maintenance operations when radon level isminimum. In the past, deep learning models have been implemented to forecastthe radon time series at the Canfranc Underground Laboratory (LSC), in Spain,with satisfactory results. When forecasting time series, the past values of thetime series are taken as input variables. The present work focuses onunderstanding the relative contribution of these input variables to thepredictions generated by neural networks. The results allow us to understandhow the predictions of the time series depend on the input variables. Theseresults may be used to build better predictors in the future.

Understanding the input-output relationship of neural networks in the time series forecasting radon levels at Canfranc Underground Laboratory