Traditional and modern machine learning-based path loss models typically assume a constant prediction variance. We propose a neural network that jointly predicts the mean and link-specific variance by minimizing a Gaussian negative log-likelihood, enabling heteroscedastic uncertainty estimates. We compare shared, partially shared, and independent-parameter architectures using accuracy, calibration, and sharpness metrics on blind test sets from large public RF drive-test datasets. The shared-parameter architecture performs best, achieving an RMSE of 7.4 dB, 95.1 percent coverage for 95 percent prediction intervals, and a mean interval width of 29.6 dB. These uncertainty estimates further support link-specific coverage margins, improve RF planning and interference analyses, and provide effective self-diagnostics of model weaknesses.
@article{arxiv.2511.23243,
title = {Heteroscedastic Neural Networks for Path Loss Prediction with Link-Specific Uncertainty},
author = {Jonathan Ethier},
journal= {arXiv preprint arXiv:2511.23243},
year = {2025}
}
Comments
Submitted to IEEE AWPL in December 2025. 5 pages, 2 figures, 4 tables