mlsanityData to 14 Oct 2026

EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecasting

arXiv 2512.15067 ↗First posted 17 Dec 2025cs.LG cs.AI cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

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. To this end, this paper introduces EMFusion, a conditional diffusion-based EMF forecasting framework that integrates diverse contextual factors, such as time of day, season, and holidays, while providing uncertainty-aware probabilistic forecasts. The proposed architecture features a residual U-Net backbone enhanced by a cross-attention mechanism that dynamically integrates external conditions to guide the generation process. Furthermore, EMFusion integrates an imputation-based sampling strategy that treats forecasting as a structural inpainting task, ensuring temporal coherence even with irregular measurements. 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. Numerical experiments conducted on the multivariate narrow-band EMF datasets demonstrate that EMFusion with the contextual information of working hours outperforms the baseline models with or without conditions. 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 87 references that are in the map. First posted on arXiv 17 Dec 2025.

Builds on

33 of 87 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2022Classifier-Free Diffusion Guidancecited by 5,847
  8. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  10. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  11. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 337
  12. 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generationcited by 184
21 more
  1. 2017Conditional Time Series Forecasting with Convolutional Neural Networkscited by 123
  2. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 90
  3. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecastingcited by 88
  4. 2021U-Net Transformer: Self and Cross Attention for Medical Image Segmentationcited by 81
  5. 2024Retrieval-Augmented Diffusion Models for Time Series Forecastingcited by 39
  6. 2024The Rise of Diffusion Models in Time-Series Forecastingcited by 25
  7. 2020If You Like It, GAN It. Probabilistic Multivariate Times Series Forecast With GANcited by 14
  8. 2024Latent Diffusion Model-Enabled Low-Latency Semantic Communication in the Presence of Semantic Ambiguities and Wireless Channel Noisescited by 13
  9. 2025Diffusion Models for Time Series Forecasting: A Surveycited by 11
  10. 2024Transformer-Based Wireless Traffic Prediction and Network Optimization in O-RANcited by 7
  11. 2022Denoising diffusion probabilistic models for probabilistic energy forecastingcited by 6
  12. 2023Detection and Imputation based Two-Stage Denoising Diffusion Power System Measurement Recovery under Cyber-Physical Uncertaintiescited by 5
  13. 2025Semantic-Aware Adaptive Video Streaming Using Latent Diffusion Models for Wireless Networkscited by 4
  14. 2022Rate-Splitting Multiple Access for Uplink Massive MIMO With Electromagnetic Exposure Constraintscited by 3
  15. 2020Health Risks Associated with 5G Exposure: A View from the Communications Engineering Perspectivecited by 2
  16. 2023Multivariate Time Series characterization and forecasting of VoIP traffic in real mobile networkscited by 2
  17. 2025EMForecaster: A Deep Learning Framework for Time Series Forecasting in Wireless Networks with Distribution-Free Uncertainty Quantificationcited by 2
  18. 2021EMF-Aware Cellular Networks in RIS-Assisted Environmentscited by 1
  19. 2022How Much Exposure from 5G Towers is Radiated over Children, Teenagers, Schools and Hospitals?cited by 1
  20. 2025Probabilistic Net Load Forecasting for High-Penetration RES Grids Utilizing Enhanced Conditional Diffusion Modelcited by 1
  21. 2025Probabilistic QoS Metric Forecasting in Delay-Tolerant Networks Using Conditional Diffusion Models on Latent Dynamicscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025STeP-Diff: Spatio-Temporal Physics-Informed Diffusion Models for Mobile Fine-Grained Pollution Forecasting
  2. 2025Double-Diffusion: Balancing Speed, Accuracy, and Uncertainty in Probabilistic Forecasting for Urban Sensor Networks
  3. 2024Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecasting
  4. 2026Active Learning for Channel Knowledge Map Construction via Bayesian Inference Diffusion Models
  5. 2025Non-stationary Diffusion For Probabilistic Time Series Forecasting
  6. 2025Effective Probabilistic Time Series Forecasting with Fourier Adaptive Noise-Separated Diffusion
  7. 2026DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting
  8. 2025Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics