Applying the Kolmogorov-Zurbenko filter followed by random forest models to Be observations in Spain (2006-2021).

In this study, we analysed Be weekly surface measurements from six Spanish laboratories from 2006 to 2021. The Kolmogorov-Zurbenko filter was applied to the six Be time series, and following an iterative process, the original data were divided into two fractions: one related to variations characterized by periods above 33 days (including, among others, the seasonal cycle) and the second noisier fraction related to mechanisms originating from variations with periods below 33 days. Both fractions were independent at the six locations. The second machine-based step using random forest models was applied with the aim of identifying the most influential inputs to the observed Be concentrations, and machine learning-inspired regression models were fitted. With respect to seasonal components, the results indicated that the memory of the system was the most influential input, as expected by the large fraction of variance explained by the seasonal cycle, followed by that of humidity and wind-related variables. For the fraction corresponding to periods below 33 d, precipitation-, humidity-, and radiation-related variables were the most influential. This methodology has made it possible to successfully describe the major mechanisms known to be involved in the generation of the surface Be concentrations observed in Spain.