# Radiomap Blind Prediction under Incomplete Observation: Error Characterization and Correctable Propagation-Prior Learning

arXiv: https://arxiv.org/abs/2609.32836 · HTML: https://mlsanity.com/paper/2609.32836/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https://mlsanity.com/paper/1911.09002/) (2019)
- [A Tutorial on Environment-Aware Communications via Channel Knowledge Map for 6G](https://mlsanity.com/paper/2309.07460/) (2023)
- [RadioDiff: An Effective Generative Diffusion Model for Sampling-Free Dynamic Radio Map Construction](https://mlsanity.com/paper/2408.08593/) (2024)
- [RME-GAN: A Learning Framework for Radio Map Estimation based on Conditional Generative Adversarial Network](https://mlsanity.com/paper/2212.12817/) (2022)
- [RadioDiff-k2: Helmholtz Equation Informed Generative Diffusion Model for Multi-Path Aware Radio Map Construction](https://mlsanity.com/paper/2504.15623/) (2025)
- [RadioGAT: A Joint Model-based and Data-driven Framework for Multi-band Radiomap Reconstruction via Graph Attention Networks](https://mlsanity.com/paper/2403.16397/) (2024)
- [Physics-Informed Representation Alignment for Sparse Radio-Map Reconstruction](https://mlsanity.com/paper/2501.19160/) (2025)
- [Radio Map Prediction from Aerial Images and Application to Coverage Optimization](https://mlsanity.com/paper/2410.17264/) (2024)
- [Tensor Completion for Radio Map Reconstruction using Low Rank and Smoothness](https://mlsanity.com/paper/1905.13689/) (2019)
- [A Physics-based and Data-driven Approach for Localized Statistical Channel Modeling](https://mlsanity.com/paper/2303.02308/) (2023)
- [A General 3D Non-Stationary Wireless Channel Model for 5G and Beyond](https://mlsanity.com/paper/2101.06610/) (2021)
- [Diffraction and Scattering Aware Radio Map and Environment Reconstruction using Geometry Model-Assisted Deep Learning](https://mlsanity.com/paper/2403.00229/) (2024)
- [BeamCKM: A Framework of Channel Knowledge Map Construction for Multi-Antenna Systems](https://mlsanity.com/paper/2511.18376/) (2025)
- [A Disentangled Representation Learning Framework for Low-altitude Network Coverage Prediction](https://mlsanity.com/paper/2507.14186/) (2025)
- [U6G XL-MIMO Radiomap Prediction: Multi-Config Dataset and Beam Map Approach](https://mlsanity.com/paper/2603.06401/) (2026)
- [A Fine-Grained 3D Radio Map Construction Paradigm with Ultra-Low Sampling Rates by Large Generative Models](https://mlsanity.com/paper/2509.11571/) (2025)
- [PINN and GNN-based RF Map Construction for Wireless Communication Systems](https://mlsanity.com/paper/2507.22513/) (2025)
- [6D Channel Knowledge Map Construction via Bidirectional Wireless Gaussian Splatting](https://mlsanity.com/paper/2510.26166/) (2025)
- [iRadioDiff: Physics-Informed Diffusion Model for Indoor Radio Map Construction and Localization](https://mlsanity.com/paper/2511.20015/) (2025)
- [TiRE-GAN: Task-Incentivized Generative Learning for Radiomap Estimation](https://mlsanity.com/paper/2405.02567/) (2024)
- [Radio Map Assisted Routing and Predictive Resource Allocation over Dynamic Low Altitude Networks](https://mlsanity.com/paper/2507.19111/) (2025)

## Abstract (arXiv)

Radiomap blind prediction aims to infer radiomaps from observable representations of the propagation environment and base station configuration without field measurements. In practice, the observable representations are inherently incomplete. Thus, the target radiomap is not fully determined by the inputs when generalizing to unseen configurations or environments. Under incomplete observation, we establish a population-level theory of deterministic radiomap blind prediction that identifies the conditional mean as its optimal target and separates prediction error into reducible predictor approximation and irreducible uncertainty caused by missing physical information. The framework further characterizes the train-test risk gap and the uncertainty reduction enabled by observation enrichment. Building on it, we reveal the dual role of propagation priors: they provide physically grounded guidance, yet their implementable forms may bias the attainable predictor. This motivates RadioDecomp, which treats a prior-guided predictor as a correctable base and learns its remaining predictable discrepancy through residual refinement. To evaluate RadioDecomp across distinct propagation-prior designs, we instantiate it with a feature-guided monolithic base and a LoS-Shadow structured base, yielding RadioFR and RadioLSR, respectively. Across random, cross-configuration, and cross-environment settings, experiments confirm the benefit of propagation-related representations and show that both instantiations improve upon their respective bases. Further controlled studies on base capacity, training-support coverage, and observation coarsening corroborate the proposed analysis.