24-h HF Spectral Occupancy Characteristics and Neural Network Modeling Over Northern Europe

This paper presents an analysis of the characteristics of HF (1.6-30 MHz) spectral occupancy and describes the development of neural network models to predict the likelihood of interference in the HF spectrum over a significant part of Northern Europe. The analysis and developed models are based upon several years of 24-h measurements recorded at four sites in Northern Europe over a substantial part of the previous sunspot cycle. The measure of occupancy used is congestion, which is defined as the fraction of channels within a certain frequency allocation with signals exceeding a given threshold.