EMFusion: Conditional Diffusion Framework for Trustworthy Frequency Selective EMF Forecasting in Wireless Networks

ArXi:2512.15067v2 Announce Type: replace-cross The rapid growth in wireless infrastructure has increased the need to accurately estimate and forecast electromagnetic field (EMF) levels to ensure ongoing compliance, assess potential health impacts, and efficient network planning. While existing studies rely on univariate forecasting of wideband aggregate EMF data, frequency-selective multivariate forecasting is needed to capture the inter-operator and inter-frequency variations essential for proactive network planning. To this end, this paper.