Jul 2026· 2026 6th International Conference on Electrical, Computer and Energy Technologies (ICECET)· pp. 1-6· 0 citations· 16 references
Abstract
Accurate wireless channel prediction in urban environments is essential for network planning and optimization, but traditional ray tracing (RT) simulations are computationally expensive. This paper presents a deep learning approach that learns from sparse RT simulations to predict received power for unseen transmitter locations. We propose a spatial attention convolutional neural network with an encoder-decoder structure incorporating convolutional block attention modules to prioritize critical regions, such as propagation boundaries, complemented by a distance-aware loss emphasizing accuracy near transmitters and borders. Trained on 80 heatmaps from a $500 mathrm{m} \times 500 mathrm{m}$ urban area, each on a $\mathbf{3 4} \times \mathbf{3 4}$ receiver grid (1,156 positions), the model achieves RMSE of \~{}22 dB and MAE of \~{}12 dB, outperforming nearest-heatmap averaging by \~{}5 dB, with an $\mathbf{R}^{\mathbf{2}}$ of $\mathbf{0. 9 2}$. Results demonstrate effective capture of multipath, diffraction, and shadowing, offering a computationally efficient alternative to full RT for urban channel prediction.
Results show that the proposed method consistently outperforms classical path-loss modeling, interpolation, Kriging, and encoder–decoder baselines, especially when only a small fraction of measurement locations is available, support propagation-prior-guided model-aided learning as a practical approach for low-cost IoT radio-map construction and wireless signal management.
Ming-Kun Lu, A. Taparugssanagorn· IEEE Access· 0 citations
Reliable estimation of radio wave propagation across irregular terrain is essential for the effective planning and optimization of contemporary wireless communication systems, such as cellular networks, broadcasting infrastructure, and radar systems. The intricate interaction between electromagnetic waves and environmental features—including mountains, depressions, and artificial structures—requires sophisticated modeling approaches capable of accounting for diffraction, reflection, scattering, and shadowing effects caused by terrain variations. The use of the split-step parabolic equation (SSPE) method for modeling radio wave propagation over irregular terrain has become increasingly popular. However, high computational cost limits its practical deployment. This has led to growing interest in machine learning (ML) as a more efficient alternative. A major challenge of ML in electromagnetic applications lies in accurately predicting results for scenarios not represented in the training data—a limitation not yet fully addressed by existing ML-based propagation models. To overcome this challenge, a high-fidelity, scalable physics-inspired modeling framework is presented. The proposed method effectively adapts to various terrain profiles and antenna setups, demonstrating strong extrapolation performance beyond the training set. Furthermore, another key innovation is the integration of prior knowledge from deterministic physics-based models into the neural network architecture. Additionally, tailoring the network structure to reflect the physical characteristics of terrain-based wave propagation significantly enhances both prediction accuracy and scalability.
O. J. Famoriji, Michael O. Omojoyegbe, Ebenezer Esenogho· Telecom· 0 citations
This work proposes Physics-Unrolled Hybrid Neural Operator (PU-HNO), a three-stage cascade that predicts high-fidelity indoor radio maps from low-fidelity ray-tracing outputs and scene priors by progressively capturing reflection, diffraction, and scattering effects, rather than treating radio maps as generic images.
Rafid Umayer Murshed, S. ur Rahman, Mingyue Tang et al.· 0 citations
A deep learning-based approach is presented that optimizes environmental input construction for accurate channel path loss prediction and validate that the input feature construction improves channel prediction accuracy and provides guidance for future intelligent channel prediction.
Zhicheng Qiu, Rui-Si He, Bo Ai et al.· npj Wireless Technology· 0 citations
Wireless signal reconstruction is essential for RF-based positioning in GPS-denied environments. However, multipath propagation, shadowing, and non-Gaussian noise complicate this, and traditional methods require extensive site-specific calibration that precludes rapid deployment. We present In-Context Signal Completion (ICSC), demonstrating that small language models fine-tuned with Group Relative Policy Optimization and physics-informed rewards can reconstruct RSSI across sequential extrapolation and spatial interpolation tasks. Our 0.5B-parameter model attains 55% recall within 2 dB and a 2.85 dB mean absolute error on sequential prediction. This achieves a 49% error reduction over the untrained baseline, performing on par with GPT-4o (51%) with fewer parameters. Successful zero-shot transfer to spatial interpolation indicates the model acquires transferable physical reasoning rather than task-specific memorization. Operating at 3 ms latency for real-time edge inference, ICSC reduces deployment from weeks of per-site data collection to immediate inference using sequential context.
Link-level evaluations confirm improved error vector magnitude and maintained bit/block error rates relative to the RT baseline, validating that the proposed physical-data collaborative paradigm not only enhances estimation accuracy but also preserves communication reliability, while offering a promising foundation for future detection-aware and integrated-sensing-and-communication optimizations.
