📰 EMFusion paper proposes probabilistic forecasting for narrow-band EMF exposure
An arXiv paper accepted in IEEE Transactions on Network Science and Engineering proposes EMFusion, a conditional diffusion model for forecasting narrow-band electromagnetic-field exposure across frequencies, operators and time contexts.
The authors frame the work as infrastructure for compliance, health-impact assessment and network planning, arguing that narrow-band probabilistic forecasting can capture inter-operator and inter-frequency variation better than aggregate wideband forecasting. Their experiments report improved probabilistic and point-forecasting performance over baseline models.
"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 support efficient network planning."
"While existing studies rely on univariate forecasting of wideband aggregate EMF data, multivariate narrow-band EMF forecasting is needed to capture the inter-operator and inter-frequency variations essential for proactive network planning."
"Unlike standard point forecasters, EMFusion generates empirical probabilistic prediction intervals from the learned conditional distribution, providing uncertainty-aware probabilistic forecasting rather than simple point estimation."
"The proposed EMFusion outperforms the best baseline by 23.85% in continuous ranked probability score (CRPS) and 13.93% in normalized root mean square error."
📄 Underlying Research
EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecasting
Zijiang Yan, Yixiang Huang, Jianhua Pei, Hina Tabassum, Luca Chiaraviglio (2026) IEEE Transactions on Network Science and Engineering Journal Level 1ⓘ
📋 Source Archive
Archived copy for date/quote verification
📱 Social Card Preview
📤 Share Text (X / Bluesky)
📰 EMFusion paper proposes probabilistic forecasting for narrow-band EMF exposure The arXiv paper frames narrow-band EMF forecasting as support for compliance, health-impact assessment and network planning. Source: arXiv
🧭 Front page section (YAML field: categories)
categories:
research