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

2026-09-26

AI Summary

This study addresses the irreducible uncertainty in blind radio map prediction caused by incomplete observations by establishing an error decomposition theory and proposing the RadioDecomp framework. This framework employs a prior-guided predictor as a correctable base, innovatively leveraging the dual role of propagation priors. A residual refinement network is introduced to learn the remaining discrepancies, thereby overcoming prior bias. Experimental results demonstrate that the proposed method significantly outperforms baseline models across diverse scenarios. Furthermore, the experiments validate the effectiveness of observation enrichment in reducing predictive uncertainty.

Abstract

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.

Problem

• Radiomap blind prediction
• Incomplete observation
• Error characterization
• Propagation prior
• Irreducible uncertainty

Innovation

• Radiomap Blind Prediction
• Error Characterization
• Propagation-Prior Learning
• RadioDecomp
• Residual Refinement